While Graph Convolutional Networks (GCNs) have shown great potential in recommender systems and collaborative filtering (CF), they suffer from expensive computational complexity and poor scalability. On top of that, recent works mostly combine GCNs with other advanced algorithms which further sacrifice model efficiency and scalability. In this work, we unveil the redundancy of existing GCN-based methods in three aspects: (1) Feature redundancy. By reviewing GCNs from a spectral perspective, we show that most spectral graph features are noisy for recommendation, while stacking graph convolution layers can suppress but cannot completely remove the noisy features, which we mostly summarize from our previous work; (2) Structure redundancy. By providing a deep insight into how user/item representations are generated, we show that what makes them distinctive lies in the spectral graph features, while the core idea of GCNs (i.e., neighborhood aggregation) is not the reason making GCNs effective; and (3) Distribution redundancy. Following observations from (1), we further show that the number of required spectral features is closely related to the spectral distribution, where important information tends to be concentrated in more (fewer) spectral features on a flatter (sharper) distribution. To make important information be concentrated in as few features as possible, we sharpen the spectral distribution by increasing the node similarity without changing the original data, thereby reducing the computational cost. To remove these three kinds of redundancies, we propose a Simplified Graph Denoising Encoder (SGDE) only exploiting the top-K singular vectors without explicitly aggregating neighborhood, which significantly reduces the complexity of GCN-based methods. We further propose a scalable contrastive learning framework to alleviate data sparsity and to boost model robustness and generalization, leading to significant improvement. Extensive experiments on three real-world datasets show that our proposed SGDE not only achieves state-of-the-art but also shows higher scalability and efficiency than our previously proposed GDE as well as traditional and GCN-based CF methods.
{"title":"Less is More: Removing Redundancy of Graph Convolutional Networks for Recommendation","authors":"Shaowen Peng, Kazunari Sugiyama, Tsunenori Mine","doi":"10.1145/3632751","DOIUrl":"https://doi.org/10.1145/3632751","url":null,"abstract":"<p>While Graph Convolutional Networks (GCNs) have shown great potential in recommender systems and collaborative filtering (CF), they suffer from expensive computational complexity and poor scalability. On top of that, recent works mostly combine GCNs with other advanced algorithms which further sacrifice model efficiency and scalability. In this work, we unveil the redundancy of existing GCN-based methods in three aspects: (1) <b>Feature redundancy</b>. By reviewing GCNs from a spectral perspective, we show that most spectral graph features are noisy for recommendation, while stacking graph convolution layers can suppress but cannot completely remove the noisy features, which we mostly summarize from our previous work; (2) <b>Structure redundancy</b>. By providing a deep insight into how user/item representations are generated, we show that what makes them distinctive lies in the spectral graph features, while the core idea of GCNs (<i>i.e.,</i> neighborhood aggregation) is not the reason making GCNs effective; and (3) <b>Distribution redundancy</b>. Following observations from (1), we further show that the number of required spectral features is closely related to the spectral distribution, where important information tends to be concentrated in more (fewer) spectral features on a flatter (sharper) distribution. To make important information be concentrated in as few features as possible, we sharpen the spectral distribution by increasing the node similarity without changing the original data, thereby reducing the computational cost. To remove these three kinds of redundancies, we propose a Simplified Graph Denoising Encoder (SGDE) only exploiting the top-<i>K</i> singular vectors without explicitly aggregating neighborhood, which significantly reduces the complexity of GCN-based methods. We further propose a scalable contrastive learning framework to alleviate data sparsity and to boost model robustness and generalization, leading to significant improvement. Extensive experiments on three real-world datasets show that our proposed SGDE not only achieves state-of-the-art but also shows higher scalability and efficiency than our previously proposed GDE as well as traditional and GCN-based CF methods.</p>","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":5.6,"publicationDate":"2023-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138537119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Antonios Minas Krasakis, Andrew Yates, Evangelos Kanoulas
Most conversational passage retrieval systems try to resolve conversational dependencies by using an intermediate query resolution step. To do so, they synthesize conversational data or assume the availability of large-scale question rewritting datasets. To relax those conditions, we propose a zero-shot unified resolution–retrieval approach, that (i) contextualizes and (ii) expands query embeddings using the conversation history and without fine-tuning on conversational data. Contextualization biases the last user question embeddings towards the conversation. Query expansion is used in two ways: (i) abstractive expansion generates embeddings based on the current question and previous history, whereas (ii) extractive expansion tries to identify history term embeddings based on attention weights from the retriever. Our experiments demonstrate the effectiveness of both contextualization and unified expansion in improving conversational retrieval. Contextualization does so mostly by resolving anaphoras to the conversation and bringing their embeddings closer to the important resolution terms that were omitted. By adding embeddings to the query, expansion targets phenomena of ellipsis more explicitly, with our analysis verifying its effectiveness on identifying and adding important resolutions to the query. By combining contextualization and expansion, we find that our zero-shot unified resolution–retrieval methods are competitive and can even outperform supervised methods.
{"title":"Contextualizing and Expanding Conversational Queries without Supervision","authors":"Antonios Minas Krasakis, Andrew Yates, Evangelos Kanoulas","doi":"10.1145/3632622","DOIUrl":"https://doi.org/10.1145/3632622","url":null,"abstract":"<p>Most conversational passage retrieval systems try to resolve conversational dependencies by using an intermediate query resolution step. To do so, they synthesize conversational data or assume the availability of large-scale question rewritting datasets. To relax those conditions, we propose a zero-shot unified resolution–retrieval approach, that (i) contextualizes and (ii) expands query embeddings using the conversation history and without fine-tuning on conversational data. Contextualization biases the last user question embeddings towards the conversation. Query expansion is used in two ways: (i) abstractive expansion generates embeddings based on the current question and previous history, whereas (ii) extractive expansion tries to identify history term embeddings based on attention weights from the retriever. Our experiments demonstrate the effectiveness of both contextualization and unified expansion in improving conversational retrieval. Contextualization does so mostly by resolving anaphoras to the conversation and bringing their embeddings closer to the important resolution terms that were omitted. By adding embeddings to the query, expansion targets phenomena of ellipsis more explicitly, with our analysis verifying its effectiveness on identifying and adding important resolutions to the query. By combining contextualization and expansion, we find that our zero-shot unified resolution–retrieval methods are competitive and can even outperform supervised methods.</p>","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":5.6,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138537118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tian Lan, Deng Cai, Yan Wang, Yixuan Su, Heyan Huang, Xian-Ling Mao
Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. However, in real-world scenarios, the high computation cost forces existing dialogue response selection models to rank only a small number of candidates, recalled by a coarse-grained model, precluding many high-quality candidates. To overcome this problem, we present a novel and efficient response selection model and a set of tailor-designed learning strategies to train it effectively. The proposed model consists of a dense retrieval module and an interaction layer, which could directly select the proper response from a large corpus. We conduct re-rank and full-rank evaluations on widely used benchmarks to evaluate our proposed model. Extensive experimental results demonstrate that our proposed model notably outperforms the state-of-the-art baselines on both re-rank and full-rank evaluations. Moreover, human evaluation results show that the response quality could be improved further by enlarging the candidate pool with nonparallel corpora. In addition, we also release high-quality benchmarks that are carefully annotated for more accurate dialogue response selection evaluation. All source codes, datasets, model parameters, and other related resources have been publicly available.
{"title":"Exploring Dense Retrieval for Dialogue Response Selection","authors":"Tian Lan, Deng Cai, Yan Wang, Yixuan Su, Heyan Huang, Xian-Ling Mao","doi":"10.1145/3632750","DOIUrl":"https://doi.org/10.1145/3632750","url":null,"abstract":"Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. However, in real-world scenarios, the high computation cost forces existing dialogue response selection models to rank only a small number of candidates, recalled by a coarse-grained model, precluding many high-quality candidates. To overcome this problem, we present a novel and efficient response selection model and a set of tailor-designed learning strategies to train it effectively. The proposed model consists of a dense retrieval module and an interaction layer, which could directly select the proper response from a large corpus. We conduct re-rank and full-rank evaluations on widely used benchmarks to evaluate our proposed model. Extensive experimental results demonstrate that our proposed model notably outperforms the state-of-the-art baselines on both re-rank and full-rank evaluations. Moreover, human evaluation results show that the response quality could be improved further by enlarging the candidate pool with nonparallel corpora. In addition, we also release high-quality benchmarks that are carefully annotated for more accurate dialogue response selection evaluation. All source codes, datasets, model parameters, and other related resources have been publicly available.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134953620","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cross-modal representation learning has become a new normal for bridging the semantic gap between text and visual data. Learning modality agnostic representations in a continuous latent space, however, is often treated as a black-box data-driven training process. It is well-known that the effectiveness of representation learning depends heavily on the quality and scale of training data. For video representation learning, having a complete set of labels that annotate the full spectrum of video content for training is highly difficult, if not impossible. These issues, black-box training and dataset bias, make representation learning practically challenging to be deployed for video understanding due to unexplainable and unpredictable results. In this paper, we propose two novel training objectives, likelihood and unlikelihood functions, to unroll the semantics behind embeddings while addressing the label sparsity problem in training. The likelihood training aims to interpret semantics of embeddings beyond training labels, while the unlikelihood training leverages prior knowledge for regularization to ensure semantically coherent interpretation. With both training objectives, a new encoder-decoder network, which learns interpretable cross-modal representation, is proposed for ad-hoc video search. Extensive experiments on TRECVid and MSR-VTT datasets show that the proposed network outperforms several state-of-the-art retrieval models with a statistically significant performance margin.
{"title":"(Un)likelihood Training for Interpretable Embedding","authors":"Jiaxin Wu, Chong-Wah Ngo, Wing-Kwong Chan, Zhijian Hou","doi":"10.1145/3632752","DOIUrl":"https://doi.org/10.1145/3632752","url":null,"abstract":"Cross-modal representation learning has become a new normal for bridging the semantic gap between text and visual data. Learning modality agnostic representations in a continuous latent space, however, is often treated as a black-box data-driven training process. It is well-known that the effectiveness of representation learning depends heavily on the quality and scale of training data. For video representation learning, having a complete set of labels that annotate the full spectrum of video content for training is highly difficult, if not impossible. These issues, black-box training and dataset bias, make representation learning practically challenging to be deployed for video understanding due to unexplainable and unpredictable results. In this paper, we propose two novel training objectives, likelihood and unlikelihood functions, to unroll the semantics behind embeddings while addressing the label sparsity problem in training. The likelihood training aims to interpret semantics of embeddings beyond training labels, while the unlikelihood training leverages prior knowledge for regularization to ensure semantically coherent interpretation. With both training objectives, a new encoder-decoder network, which learns interpretable cross-modal representation, is proposed for ad-hoc video search. Extensive experiments on TRECVid and MSR-VTT datasets show that the proposed network outperforms several state-of-the-art retrieval models with a statistically significant performance margin.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136348319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hongzu Su, Jingjing Li, Zhekai Du, Lei Zhu, Ke Lu, Heng Tao Shen
Data scarcity is a perpetual challenge of recommendation systems, and researchers have proposed a variety of cross-domain recommendation methods to alleviate the problem of data scarcity in target domains. However, in many real-world cross-domain recommendation systems, the source domain and the target domain are sampled from different data distributions, which obstructs the cross-domain knowledge transfer. In this paper, we propose to specifically align the data distributions between the source domain and the target domain to alleviate imbalanced sample distribution and thus challenge the data scarcity issue in the target domain. Technically, our proposed approach builds a dual adversarial adaptation (DAA) framework to adversarially train the target model together with a pre-trained source model. Two domain discriminators play the two-player minmax game with the target model and guide the target model to learn reliable domain-invariant features that can be transferred across domains. At the same time, the target model is calibrated to learn domain-specific information of the target domain. In addition, we formulate our approach as a plug-and-play module to boost existing recommendation systems. We apply the proposed method to address the issues of insufficient data and imbalanced sample distribution in real-world Click-Through Rate (CTR)/Conversion Rate (CVR) predictions on two large-scale industrial datasets. We evaluate the proposed method in scenarios with and without overlapping users/items, and extensive experiments verify that the proposed method is able to significantly improve the prediction performance on the target domain. For instance, our method can boost PLE with a performance improvement of 15.4% in terms of Area Under Curve (AUC) compared with single-domain PLE on our private game dataset. In addition, our method is able to surpass single-domain MMoE by 6.85% on the public datasets. Code: https://github.com/TL-UESTC/DAA.
{"title":"Cross-domain Recommendation via Dual Adversarial Adaptation","authors":"Hongzu Su, Jingjing Li, Zhekai Du, Lei Zhu, Ke Lu, Heng Tao Shen","doi":"10.1145/3632524","DOIUrl":"https://doi.org/10.1145/3632524","url":null,"abstract":"Data scarcity is a perpetual challenge of recommendation systems, and researchers have proposed a variety of cross-domain recommendation methods to alleviate the problem of data scarcity in target domains. However, in many real-world cross-domain recommendation systems, the source domain and the target domain are sampled from different data distributions, which obstructs the cross-domain knowledge transfer. In this paper, we propose to specifically align the data distributions between the source domain and the target domain to alleviate imbalanced sample distribution and thus challenge the data scarcity issue in the target domain. Technically, our proposed approach builds a dual adversarial adaptation (DAA) framework to adversarially train the target model together with a pre-trained source model. Two domain discriminators play the two-player minmax game with the target model and guide the target model to learn reliable domain-invariant features that can be transferred across domains. At the same time, the target model is calibrated to learn domain-specific information of the target domain. In addition, we formulate our approach as a plug-and-play module to boost existing recommendation systems. We apply the proposed method to address the issues of insufficient data and imbalanced sample distribution in real-world Click-Through Rate (CTR)/Conversion Rate (CVR) predictions on two large-scale industrial datasets. We evaluate the proposed method in scenarios with and without overlapping users/items, and extensive experiments verify that the proposed method is able to significantly improve the prediction performance on the target domain. For instance, our method can boost PLE with a performance improvement of 15.4% in terms of Area Under Curve (AUC) compared with single-domain PLE on our private game dataset. In addition, our method is able to surpass single-domain MMoE by 6.85% on the public datasets. Code: https://github.com/TL-UESTC/DAA.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135087072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Arian Askari, Suzan Verberne, Amin Abolghasemi, Wessel Kraaij, Gabriella Pasi
Retrieval with extremely long queries and documents is a well-known and challenging task in information retrieval and is commonly known as Query-by-Document (QBD) retrieval. Specifically designed Transformer models that can handle long input sequences have not shown high effectiveness in QBD tasks in previous work. We propose a R e-Ranker based on the novel P roportional R elevance S core (RPRS) to compute the relevance score between a query and the top-k candidate documents. Our extensive evaluation shows RPRS obtains significantly better results than the state-of-the-art models on five different datasets. Furthermore, RPRS is highly efficient since all documents can be pre-processed, embedded, and indexed before query time which gives our re-ranker the advantage of having a complexity of O ( N ) where N is the total number of sentences in the query and candidate documents. Furthermore, our method solves the problem of the low-resource training in QBD retrieval tasks as it does not need large amounts of training data, and has only three parameters with a limited range that can be optimized with a grid search even if a small amount of labeled data is available. Our detailed analysis shows that RPRS benefits from covering the full length of candidate documents and queries.
{"title":"Retrieval for Extremely Long Queries and Documents with RPRS: a Highly Efficient and Effective Transformer-based Re-Ranker","authors":"Arian Askari, Suzan Verberne, Amin Abolghasemi, Wessel Kraaij, Gabriella Pasi","doi":"10.1145/3631938","DOIUrl":"https://doi.org/10.1145/3631938","url":null,"abstract":"Retrieval with extremely long queries and documents is a well-known and challenging task in information retrieval and is commonly known as Query-by-Document (QBD) retrieval. Specifically designed Transformer models that can handle long input sequences have not shown high effectiveness in QBD tasks in previous work. We propose a R e-Ranker based on the novel P roportional R elevance S core (RPRS) to compute the relevance score between a query and the top-k candidate documents. Our extensive evaluation shows RPRS obtains significantly better results than the state-of-the-art models on five different datasets. Furthermore, RPRS is highly efficient since all documents can be pre-processed, embedded, and indexed before query time which gives our re-ranker the advantage of having a complexity of O ( N ) where N is the total number of sentences in the query and candidate documents. Furthermore, our method solves the problem of the low-resource training in QBD retrieval tasks as it does not need large amounts of training data, and has only three parameters with a limited range that can be optimized with a grid search even if a small amount of labeled data is available. Our detailed analysis shows that RPRS benefits from covering the full length of candidate documents and queries.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135043233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Technology Assisted Review (TAR), which aims to reduce the effort required to screen collections of documents for relevance, is used to develop systematic reviews of medical evidence and identify documents that must be disclosed in response to legal proceedings. Stopping methods are algorithms which determine when to stop screening documents during the TAR process, helping to ensure that workload is minimised while still achieving a high level of recall. This paper proposes a novel stopping method based on point processes, which are statistical models that can be used to represent the occurrence of random events. The approach uses rate functions to model the occurrence of relevant documents in the ranking and compares four candidates, including one that has not previously been used for this purpose (hyperbolic). Evaluation is carried out using standard datasets (CLEF e-Health, TREC Total Recall, TREC Legal), and this work is the first to explore stopping method robustness by reporting performance on a range of rankings of varying effectiveness. Results show that the proposed method achieves the desired level of recall without requiring an excessive number of documents to be examined in the majority of cases and also compares well against multiple alternative approaches.
技术辅助审查(TAR)的目的是减少对收集的文件进行相关性筛选所需的努力，用于对医学证据进行系统审查，并确定为应对法律诉讼而必须披露的文件。停止方法是确定在TAR过程中何时停止筛选文件的算法，有助于确保在实现高水平召回的同时最大限度地减少工作量。本文提出了一种新的基于点过程的停止方法，点过程是一种可以用来表示随机事件发生的统计模型。该方法使用比率函数对相关文档在排名中的出现情况进行建模，并比较四个候选文档，包括一个以前未用于此目的的文档(双曲线)。使用标准数据集(CLEF e-Health, TREC Total Recall, TREC Legal)进行评估，这项工作是第一个通过在一系列不同有效性排名上报告性能来探索停止方法稳健性的工作。结果表明，在大多数情况下，所提出的方法达到了所需的召回水平，而不需要检查过多的文档，并且与多种替代方法相比也比较好。
{"title":"Stopping Methods for Technology Assisted Reviews based on Point Processes","authors":"Mark Stevenson, Reem Bin-Hezam","doi":"10.1145/3631990","DOIUrl":"https://doi.org/10.1145/3631990","url":null,"abstract":"Technology Assisted Review (TAR), which aims to reduce the effort required to screen collections of documents for relevance, is used to develop systematic reviews of medical evidence and identify documents that must be disclosed in response to legal proceedings. Stopping methods are algorithms which determine when to stop screening documents during the TAR process, helping to ensure that workload is minimised while still achieving a high level of recall. This paper proposes a novel stopping method based on point processes, which are statistical models that can be used to represent the occurrence of random events. The approach uses rate functions to model the occurrence of relevant documents in the ranking and compares four candidates, including one that has not previously been used for this purpose (hyperbolic). Evaluation is carried out using standard datasets (CLEF e-Health, TREC Total Recall, TREC Legal), and this work is the first to explore stopping method robustness by reporting performance on a range of rankings of varying effectiveness. Results show that the proposed method achieves the desired level of recall without requiring an excessive number of documents to be examined in the majority of cases and also compares well against multiple alternative approaches.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135042712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cross-domain recommendation (CDR), which leverages information collected from other domains, has been empirically demonstrated to effectively alleviate data sparsity and cold-start problems encountered in traditional recommendation systems. However, current CDR methods, including those considering time information, do not jointly model the general and current interests within and across domains, which is pivotal for accurately predicting users’ future interactions. In this paper, we propose a Contrastive learning enhanced Multi-View interest learning model (CMVCDR) for cross-domain sequential recommendation. Specifically, we design a static view and a sequential view to model uses’ general interests and current interests, respectively. We divide a user’s general interest representation into a domain-invariant part and a domain-specific part. A cross-domain contrastive learning objective is introduced to impose constraints for optimizing these representations. In the sequential view, we first devise an attention mechanism guided by users’ domain-invariant interest representations to distill cross-domain knowledge pertaining to domain-invariant factors while reducing noise from irrelevant factors. We further design a domain-specific interest-guided temporal information aggregation mechanism to generate users’ current interest representations. Extensive experiments demonstrate the effectiveness of our proposed model compared with state-of-the-art methods.
{"title":"Contrastive Multi-View Interest Learning for Cross-Domain Sequential Recommendation","authors":"Tianzi Zang, Yanmin Zhu, Ruohan Zhang, Chunyang Wang, Ke Wang, Jiadi Yu","doi":"10.1145/3632402","DOIUrl":"https://doi.org/10.1145/3632402","url":null,"abstract":"Cross-domain recommendation (CDR), which leverages information collected from other domains, has been empirically demonstrated to effectively alleviate data sparsity and cold-start problems encountered in traditional recommendation systems. However, current CDR methods, including those considering time information, do not jointly model the general and current interests within and across domains, which is pivotal for accurately predicting users’ future interactions. In this paper, we propose a Contrastive learning enhanced Multi-View interest learning model (CMVCDR) for cross-domain sequential recommendation. Specifically, we design a static view and a sequential view to model uses’ general interests and current interests, respectively. We divide a user’s general interest representation into a domain-invariant part and a domain-specific part. A cross-domain contrastive learning objective is introduced to impose constraints for optimizing these representations. In the sequential view, we first devise an attention mechanism guided by users’ domain-invariant interest representations to distill cross-domain knowledge pertaining to domain-invariant factors while reducing noise from irrelevant factors. We further design a domain-specific interest-guided temporal information aggregation mechanism to generate users’ current interest representations. Extensive experiments demonstrate the effectiveness of our proposed model compared with state-of-the-art methods.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135242579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ambiguity in queries is a common problem in information retrieval. There are currently two solutions: Search result personalization and diversification. The former aims to tailor results for different users based on their preferences, but the limitations are redundant results and incomplete capture of user intents. The goal of the latter is to return results that cover as many aspects related to the query as possible. It improves diversity yet loses personality and cannot return the exact results the user wants. Intuitively, such two solutions can complement each other and bring more satisfactory reranking results. In this paper, we propose a novel framework, namely PnD to integrate personalization and diversification reasonably. We employ the degree of refinding to determine the weight of personalization dynamically. Moreover, to improve the diversity and relevance of reranked results simultaneously, we design a reset RNN structure (RRNN) with the “reset gate” to measure the influence of the newly selected document on novelty. Besides, we devise a “subtopic learning layer” to learn the virtual subtopics, which can yield fine-grained representations of queries, documents, and user profiles. Experimental results illustrate that our model can significantly outperform existing search result personalization and diversification methods.
{"title":"Personalized and Diversified: Ranking Search Results in an Integrated Way","authors":"Shuting Wang, Zhicheng Dou, Jiongnan Liu, Qiannan Zhu, Ji-Rong Wen","doi":"10.1145/3631989","DOIUrl":"https://doi.org/10.1145/3631989","url":null,"abstract":"Ambiguity in queries is a common problem in information retrieval. There are currently two solutions: Search result personalization and diversification. The former aims to tailor results for different users based on their preferences, but the limitations are redundant results and incomplete capture of user intents. The goal of the latter is to return results that cover as many aspects related to the query as possible. It improves diversity yet loses personality and cannot return the exact results the user wants. Intuitively, such two solutions can complement each other and bring more satisfactory reranking results. In this paper, we propose a novel framework, namely PnD to integrate personalization and diversification reasonably. We employ the degree of refinding to determine the weight of personalization dynamically. Moreover, to improve the diversity and relevance of reranked results simultaneously, we design a reset RNN structure (RRNN) with the “reset gate” to measure the influence of the newly selected document on novelty. Besides, we devise a “subtopic learning layer” to learn the virtual subtopics, which can yield fine-grained representations of queries, documents, and user profiles. Experimental results illustrate that our model can significantly outperform existing search result personalization and diversification methods.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135285578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sequential prediction has great value for resource allocation due to its capability in analyzing intents for next prediction. A fundamental challenge arises from real-world interaction dynamics where similar sequences involving multiple intents may exhibit different next items. More importantly, the character of volume candidate items in sequential prediction may amplify such dynamics, making deep networks hard to capture comprehensive intents. This paper presents a sequential prediction framework with De coupled P r o gressive D istillation (DePoD), drawing on the progressive nature of human cognition. We redefine target and non-target item distillation according to their different effects in the decoupled formulation. This can be achieved through two aspects: (1) Regarding how to learn, our target item distillation with progressive difficulty increases the contribution of low-confidence samples in the later training phase while keeping high-confidence samples in the earlier phase. And, the non-target item distillation starts from a small subset of non-target items from which size increases according to the item frequency. (2) Regarding whom to learn from, a difference evaluator is utilized to progressively select an expert that provides informative knowledge among items from the cohort of peers. Extensive experiments on four public datasets show DePoD outperforms state-of-the-art methods in terms of accuracy-based metrics.
{"title":"Decoupled Progressive Distillation for Sequential Prediction with Interaction Dynamics","authors":"Kaixi Hu, Lin Li, Qing Xie, Jianquan Liu, Xiaohui Tao, Guandong Xu","doi":"10.1145/3632403","DOIUrl":"https://doi.org/10.1145/3632403","url":null,"abstract":"Sequential prediction has great value for resource allocation due to its capability in analyzing intents for next prediction. A fundamental challenge arises from real-world interaction dynamics where similar sequences involving multiple intents may exhibit different next items. More importantly, the character of volume candidate items in sequential prediction may amplify such dynamics, making deep networks hard to capture comprehensive intents. This paper presents a sequential prediction framework with De coupled P r o gressive D istillation (DePoD), drawing on the progressive nature of human cognition. We redefine target and non-target item distillation according to their different effects in the decoupled formulation. This can be achieved through two aspects: (1) Regarding how to learn, our target item distillation with progressive difficulty increases the contribution of low-confidence samples in the later training phase while keeping high-confidence samples in the earlier phase. And, the non-target item distillation starts from a small subset of non-target items from which size increases according to the item frequency. (2) Regarding whom to learn from, a difference evaluator is utilized to progressively select an expert that provides informative knowledge among items from the cohort of peers. Extensive experiments on four public datasets show DePoD outperforms state-of-the-art methods in terms of accuracy-based metrics.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135242374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号