Clemencia Siro, Mohammad Aliannejadi, Maarten de Rijke
User satisfaction depicts the effectiveness of a system from the user’s perspective. Understanding and predicting user satisfaction is vital for the design of user-oriented evaluation methods for conversational recommender systems (CRSs) . Current approaches rely on turn-level satisfaction ratings to predict a user’s overall satisfaction with CRS. These methods assume that all users perceive satisfaction similarly, failing to capture the broader dialogue aspects that influence overall user satisfaction. We investigate the effect of several dialogue aspects on user satisfaction when interacting with a CRS. To this end, we annotate dialogues based on six aspects (i.e., relevance , interestingness , understanding , task-completion , interest-arousal , and efficiency ) at the turn and dialogue levels. We find that the concept of satisfaction varies per user. At the turn level, a system’s ability to make relevant recommendations is a significant factor in satisfaction. We adopt these aspects as features for predicting response quality and user satisfaction. We achieve an F1-score of 0.80 in classifying dissatisfactory dialogues, and a Pearson’s r of 0.73 for turn-level response quality estimation, demonstrating the effectiveness of the proposed dialogue aspects in predicting user satisfaction and being able to identify dialogues where the system is failing. With this article, we release our annotated data. 1
{"title":"Understanding and Predicting User Satisfaction with Conversational Recommender Systems","authors":"Clemencia Siro, Mohammad Aliannejadi, Maarten de Rijke","doi":"10.1145/3624989","DOIUrl":"https://doi.org/10.1145/3624989","url":null,"abstract":"User satisfaction depicts the effectiveness of a system from the user’s perspective. Understanding and predicting user satisfaction is vital for the design of user-oriented evaluation methods for conversational recommender systems (CRSs) . Current approaches rely on turn-level satisfaction ratings to predict a user’s overall satisfaction with CRS. These methods assume that all users perceive satisfaction similarly, failing to capture the broader dialogue aspects that influence overall user satisfaction. We investigate the effect of several dialogue aspects on user satisfaction when interacting with a CRS. To this end, we annotate dialogues based on six aspects (i.e., relevance , interestingness , understanding , task-completion , interest-arousal , and efficiency ) at the turn and dialogue levels. We find that the concept of satisfaction varies per user. At the turn level, a system’s ability to make relevant recommendations is a significant factor in satisfaction. We adopt these aspects as features for predicting response quality and user satisfaction. We achieve an F1-score of 0.80 in classifying dissatisfactory dialogues, and a Pearson’s r of 0.73 for turn-level response quality estimation, demonstrating the effectiveness of the proposed dialogue aspects in predicting user satisfaction and being able to identify dialogues where the system is failing. With this article, we release our annotated data. 1","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135293667","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}
Information retrieval aims to find information that meets users’ needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, and so on, while they share the same schema to estimate the relationship between texts. It indicates that a good IR model can generalize to different tasks and domains. However, previous studies indicate that state-of-the-art neural information retrieval (NIR) models, e.g., pre-trained language models (PLMs) are hard to generalize. It is mainly because the end-to-end fine-tuning paradigm makes the model overemphasize task-specific signals and domain biases but loses the ability to capture generalized essential signals. To address this problem, we propose a novel NIR training framework named NIR-Prompt for retrieval and reranking stages based on the idea of decoupling signal capturing and combination. NIR-Prompt exploits Essential Matching Module (EMM) to capture the essential matching signals and gets the description of tasks by Matching Description Module (MDM). The description is used as task-adaptation information to combine the essential matching signals to adapt to different tasks. Experiments under in-domain multi-task, out-of-domain multi-task, and new task adaptation settings show that NIR-Prompt can improve the generalization of PLMs in NIR for both retrieval and reranking stages compared with baselines.
{"title":"NIR-Prompt: A Multi-task Generalized Neural Information Retrieval Training Framework","authors":"Shicheng Xu, Liang Pang, Huawei Shen, Xueqi Cheng","doi":"10.1145/3626092","DOIUrl":"https://doi.org/10.1145/3626092","url":null,"abstract":"Information retrieval aims to find information that meets users’ needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, and so on, while they share the same schema to estimate the relationship between texts. It indicates that a good IR model can generalize to different tasks and domains. However, previous studies indicate that state-of-the-art neural information retrieval (NIR) models, e.g., pre-trained language models (PLMs) are hard to generalize. It is mainly because the end-to-end fine-tuning paradigm makes the model overemphasize task-specific signals and domain biases but loses the ability to capture generalized essential signals. To address this problem, we propose a novel NIR training framework named NIR-Prompt for retrieval and reranking stages based on the idea of decoupling signal capturing and combination. NIR-Prompt exploits Essential Matching Module (EMM) to capture the essential matching signals and gets the description of tasks by Matching Description Module (MDM). The description is used as task-adaptation information to combine the essential matching signals to adapt to different tasks. Experiments under in-domain multi-task, out-of-domain multi-task, and new task adaptation settings show that NIR-Prompt can improve the generalization of PLMs in NIR for both retrieval and reranking stages compared with baselines.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135293550","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}
Zhongwei Wan, Xin Liu, Benyou Wang, Jiezhong Qiu, Boyu Li, Ting Guo, Guangyong Chen, Yang Wang
Session-based recommendation (SBR) systems aim to utilize the user’s short-term behavior sequence to predict the next item without the detailed user profile. Most recent works try to model the user preference by treating the sessions as between-item transition graphs and utilize various graph neural networks (GNNs) to encode the representations of pair-wise relations among items and their neighbors. Some of the existing GNN-based models mainly focus on aggregating information from the view of spatial graph structure, which ignores the temporal relations within neighbors of an item during message passing and the information loss results in a sub-optimal problem. Other works embrace this challenge by incorporating additional temporal information but lack sufficient interaction between the spatial and temporal patterns. To address this issue, inspired by the uniformity and alignment properties of contrastive learning techniques, we propose a novel framework called Session-based Recommendation with Spatio-temporal Contrastive Learning-enhanced GNNs (RESTC). The idea is to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism. Furthermore, a novel global collaborative filtering graph embedding is leveraged to enhance the spatial view in the main task. Extensive experiments demonstrate the significant performance of RESTC compared with the state-of-the-art baselines. We release our source code at https://github.com/SUSTechBruce/RESTC-Source-code .
{"title":"Spatio-Temporal Contrastive Learning Enhanced GNNs for Session-based Recommendation","authors":"Zhongwei Wan, Xin Liu, Benyou Wang, Jiezhong Qiu, Boyu Li, Ting Guo, Guangyong Chen, Yang Wang","doi":"10.1145/3626091","DOIUrl":"https://doi.org/10.1145/3626091","url":null,"abstract":"Session-based recommendation (SBR) systems aim to utilize the user’s short-term behavior sequence to predict the next item without the detailed user profile. Most recent works try to model the user preference by treating the sessions as between-item transition graphs and utilize various graph neural networks (GNNs) to encode the representations of pair-wise relations among items and their neighbors. Some of the existing GNN-based models mainly focus on aggregating information from the view of spatial graph structure, which ignores the temporal relations within neighbors of an item during message passing and the information loss results in a sub-optimal problem. Other works embrace this challenge by incorporating additional temporal information but lack sufficient interaction between the spatial and temporal patterns. To address this issue, inspired by the uniformity and alignment properties of contrastive learning techniques, we propose a novel framework called Session-based Recommendation with Spatio-temporal Contrastive Learning-enhanced GNNs (RESTC). The idea is to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism. Furthermore, a novel global collaborative filtering graph embedding is leveraged to enhance the spatial view in the main task. Extensive experiments demonstrate the significant performance of RESTC compared with the state-of-the-art baselines. We release our source code at https://github.com/SUSTechBruce/RESTC-Source-code .","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135293559","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}
Information retrieval (IR) evaluation measures are essential for capturing the relevance of documents to topics, and determining the task performance efficiency of retrieval systems. The study of IR evaluation measures through their formal properties enables a better understanding of their suitability for a specific task. Some works have modelled the effectiveness of retrieval measures with axioms, heuristics or desirable properties, leading to order relationships on the set where they are defined. Each of these ordering structures constitute an axiomatic model of preferences (AMP), which can be considered as an ’ideal’ scenario of retrieval. Based on lattice theory and on the representational theory of measurement, this work formally explores numeric, metric and scale properties of some effectiveness measures defined on AMPs. In some of these scenarios, retrieval measures are completely determined from the scores of a subset of document rankings: join-irreducible elements. All the possible metrics and pseudometrics, defined on these structures are expressed in terms of the join-irreducible elements. The deduced scale properties of the precision, recall, F -measure, RBP , DCG and AP confirm some recent results in the IR field.
{"title":"Information Retrieval Evaluation Measures Defined on Some Axiomatic Models of Preferences","authors":"Fernando Giner","doi":"10.1145/3632171","DOIUrl":"https://doi.org/10.1145/3632171","url":null,"abstract":"Information retrieval (IR) evaluation measures are essential for capturing the relevance of documents to topics, and determining the task performance efficiency of retrieval systems. The study of IR evaluation measures through their formal properties enables a better understanding of their suitability for a specific task. Some works have modelled the effectiveness of retrieval measures with axioms, heuristics or desirable properties, leading to order relationships on the set where they are defined. Each of these ordering structures constitute an axiomatic model of preferences (AMP), which can be considered as an ’ideal’ scenario of retrieval. Based on lattice theory and on the representational theory of measurement, this work formally explores numeric, metric and scale properties of some effectiveness measures defined on AMPs. In some of these scenarios, retrieval measures are completely determined from the scores of a subset of document rankings: join-irreducible elements. All the possible metrics and pseudometrics, defined on these structures are expressed in terms of the join-irreducible elements. The deduced scale properties of the precision, recall, F -measure, RBP , DCG and AP confirm some recent results in the IR field.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135341766","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}
Yifang Qin, Hongjun Wu, Wei Ju, Xiao Luo, Ming Zhang
Next Point-of-Interest (POI) recommendation is a critical task in location-based services that aim to provide personalized suggestions for the user’s next destination. Previous works on POI recommendation have laid focus on modeling the user’s spatial preference. However, existing works that leverage spatial information are only based on the aggregation of users’ previous visited positions, which discourages the model from recommending POIs in novel areas. This trait of position-based methods will harm the model’s performance in many situations. Additionally, incorporating sequential information into the user’s spatial preference remains a challenge. In this article, we propose Diff-POI : a Diffu sion-based model that samples the user’s spatial preference for the next POI recommendation. Inspired by the wide application of diffusion algorithm in sampling from distributions, Diff-POI encodes the user’s visiting sequence and spatial character with two tailor-designed graph encoding modules, followed by a diffusion-based sampling strategy to explore the user’s spatial visiting trends. We leverage the diffusion process and its reverse form to sample from the posterior distribution and optimized the corresponding score function. We design a joint training and inference framework to optimize and evaluate the proposed Diff-POI. Extensive experiments on four real-world POI recommendation datasets demonstrate the superiority of our Diff-POI over state-of-the-art baseline methods. Further ablation and parameter studies on Diff-POI reveal the functionality and effectiveness of the proposed diffusion-based sampling strategy for addressing the limitations of existing methods.
{"title":"A Diffusion model for POI recommendation","authors":"Yifang Qin, Hongjun Wu, Wei Ju, Xiao Luo, Ming Zhang","doi":"10.1145/3624475","DOIUrl":"https://doi.org/10.1145/3624475","url":null,"abstract":"Next Point-of-Interest (POI) recommendation is a critical task in location-based services that aim to provide personalized suggestions for the user’s next destination. Previous works on POI recommendation have laid focus on modeling the user’s spatial preference. However, existing works that leverage spatial information are only based on the aggregation of users’ previous visited positions, which discourages the model from recommending POIs in novel areas. This trait of position-based methods will harm the model’s performance in many situations. Additionally, incorporating sequential information into the user’s spatial preference remains a challenge. In this article, we propose Diff-POI : a Diffu sion-based model that samples the user’s spatial preference for the next POI recommendation. Inspired by the wide application of diffusion algorithm in sampling from distributions, Diff-POI encodes the user’s visiting sequence and spatial character with two tailor-designed graph encoding modules, followed by a diffusion-based sampling strategy to explore the user’s spatial visiting trends. We leverage the diffusion process and its reverse form to sample from the posterior distribution and optimized the corresponding score function. We design a joint training and inference framework to optimize and evaluate the proposed Diff-POI. Extensive experiments on four real-world POI recommendation datasets demonstrate the superiority of our Diff-POI over state-of-the-art baseline methods. Further ablation and parameter studies on Diff-POI reveal the functionality and effectiveness of the proposed diffusion-based sampling strategy for addressing the limitations of existing methods.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135293660","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}
Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transformer-based language models, which are notoriously inefficient in terms of resources and latency. We propose Fast-Forward indexes—vector forward indexes which exploit the semantic matching capabilities of dual-encoder models for efficient and effective re-ranking. Our framework enables re-ranking at very high retrieval depths and combines the merits of both lexical and semantic matching via score interpolation. Furthermore, in order to mitigate the limitations of dual-encoders, we tackle two main challenges: Firstly, we improve computational efficiency by either pre-computing representations, avoiding unnecessary computations altogether, or reducing the complexity of encoders. This allows us to considerably improve ranking efficiency and latency. Secondly, we optimize the memory footprint and maintenance cost of indexes; we propose two complementary techniques to reduce the index size and show that, by dynamically dropping irrelevant document tokens, the index maintenance efficiency can be improved substantially. We perform evaluation to show the effectiveness and efficiency of Fast-Forward indexes—our method has low latency and achieves competitive results without the need for hardware acceleration, such as GPUs.
{"title":"Efficient Neural Ranking using Forward Indexes and Lightweight Encoders","authors":"Jurek Leonhardt, Henrik Müller, Koustav Rudra, Megha Khosla, Abhijit Anand, Avishek Anand","doi":"10.1145/3631939","DOIUrl":"https://doi.org/10.1145/3631939","url":null,"abstract":"Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transformer-based language models, which are notoriously inefficient in terms of resources and latency. We propose Fast-Forward indexes—vector forward indexes which exploit the semantic matching capabilities of dual-encoder models for efficient and effective re-ranking. Our framework enables re-ranking at very high retrieval depths and combines the merits of both lexical and semantic matching via score interpolation. Furthermore, in order to mitigate the limitations of dual-encoders, we tackle two main challenges: Firstly, we improve computational efficiency by either pre-computing representations, avoiding unnecessary computations altogether, or reducing the complexity of encoders. This allows us to considerably improve ranking efficiency and latency. Secondly, we optimize the memory footprint and maintenance cost of indexes; we propose two complementary techniques to reduce the index size and show that, by dynamically dropping irrelevant document tokens, the index maintenance efficiency can be improved substantially. We perform evaluation to show the effectiveness and efficiency of Fast-Forward indexes—our method has low latency and achieves competitive results without the need for hardware acceleration, such as GPUs.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135342067","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}
Deep learning-based recommender systems have achieved remarkable success in recent years. However, these methods usually heavily rely on labeled data (i.e., user-item interactions), suffering from problems such as data sparsity and cold-start. Self-supervised learning, an emerging paradigm that extracts information from unlabeled data, provides insights into addressing these problems. Specifically, contrastive self-supervised learning, due to its flexibility and promising performance, has attracted considerable interest and recently become a dominant branch in self-supervised learning-based recommendation methods. In this survey, we provide an up-to-date and comprehensive review of current contrastive self-supervised learning-based recommendation methods. Firstly, we propose a unified framework for these methods. We then introduce a taxonomy based on the key components of the framework, including view generation strategy, contrastive task, and contrastive objective. For each component, we provide detailed descriptions and discussions to guide the choice of the appropriate method. Finally, we outline open issues and promising directions for future research.
{"title":"Contrastive Self-supervised Learning in Recommender Systems: A Survey","authors":"Mengyuan Jing, Yanmin Zhu, Tianzi Zang, Ke Wang","doi":"10.1145/3627158","DOIUrl":"https://doi.org/10.1145/3627158","url":null,"abstract":"Deep learning-based recommender systems have achieved remarkable success in recent years. However, these methods usually heavily rely on labeled data (i.e., user-item interactions), suffering from problems such as data sparsity and cold-start. Self-supervised learning, an emerging paradigm that extracts information from unlabeled data, provides insights into addressing these problems. Specifically, contrastive self-supervised learning, due to its flexibility and promising performance, has attracted considerable interest and recently become a dominant branch in self-supervised learning-based recommendation methods. In this survey, we provide an up-to-date and comprehensive review of current contrastive self-supervised learning-based recommendation methods. Firstly, we propose a unified framework for these methods. We then introduce a taxonomy based on the key components of the framework, including view generation strategy, contrastive task, and contrastive objective. For each component, we provide detailed descriptions and discussions to guide the choice of the appropriate method. Finally, we outline open issues and promising directions for future research.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135293385","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}
Lang Mei, Jiaxin Mao, Juan Hu, Naiqiang Tan, Hua Chai, Ji-rong Wen
Point-of-interest (POI) search is important for location-based services, such as navigation and online ride-hailing service. The goal of POI search is to find the most relevant destinations from a large-scale POI database given a text query. To improve the effectiveness and efficiency of POI search, most existing approaches are based on a multi-stage pipeline that consists of an efficiency-oriented retrieval stage and one or more effectiveness-oriented re-rank stages. In this paper, we focus on the first efficiency-oriented retrieval stage of the POI search. We first identify the limitations of existing first-stage POI retrieval models in capturing the semantic-geography relationship and modeling the fine-grained geographical context information. Then, we propose a Geo-Enhanced Dense Retrieval framework for POI search to alleviate the above problems. Specifically, the proposed framework leverages the capacity of pre-trained language models (e.g., BERT) and designs a pre-training approach to better model the semantic match between the query prefix and POIs. With the POI collection, we first perform a token-level pre-training task based on a geographical-sensitive masked language prediction, and design two retrieval-oriented pre-training tasks that link the address of each POI to its name and geo-location. With the user behavior logs collected from an online POI search system, we design two additional pre-training tasks based on users’ query reformulation behavior and the transitions between POIs. We also utilize a late-interaction network structure to model the fine-grained interactions between the text and geographical context information within an acceptable query latency. Extensive experiments on the real-world datasets collected from the Didichuxing application demonstrate that the proposed framework can achieve superior retrieval performance over existing first-stage POI retrieval methods.
{"title":"Improving First-stage Retrieval of Point-of-Interest Search by Pre-training Models","authors":"Lang Mei, Jiaxin Mao, Juan Hu, Naiqiang Tan, Hua Chai, Ji-rong Wen","doi":"10.1145/3631937","DOIUrl":"https://doi.org/10.1145/3631937","url":null,"abstract":"Point-of-interest (POI) search is important for location-based services, such as navigation and online ride-hailing service. The goal of POI search is to find the most relevant destinations from a large-scale POI database given a text query. To improve the effectiveness and efficiency of POI search, most existing approaches are based on a multi-stage pipeline that consists of an efficiency-oriented retrieval stage and one or more effectiveness-oriented re-rank stages. In this paper, we focus on the first efficiency-oriented retrieval stage of the POI search. We first identify the limitations of existing first-stage POI retrieval models in capturing the semantic-geography relationship and modeling the fine-grained geographical context information. Then, we propose a Geo-Enhanced Dense Retrieval framework for POI search to alleviate the above problems. Specifically, the proposed framework leverages the capacity of pre-trained language models (e.g., BERT) and designs a pre-training approach to better model the semantic match between the query prefix and POIs. With the POI collection, we first perform a token-level pre-training task based on a geographical-sensitive masked language prediction, and design two retrieval-oriented pre-training tasks that link the address of each POI to its name and geo-location. With the user behavior logs collected from an online POI search system, we design two additional pre-training tasks based on users’ query reformulation behavior and the transitions between POIs. We also utilize a late-interaction network structure to model the fine-grained interactions between the text and geographical context information within an acceptable query latency. Extensive experiments on the real-world datasets collected from the Didichuxing application demonstrate that the proposed framework can achieve superior retrieval performance over existing first-stage POI retrieval methods.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135476078","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}
The recent development of recommender systems has a focus on collaborative ranking, which provides users with a sorted list rather than rating prediction. The sorted item lists can more directly reflect the preferences for users and usually perform better than rating prediction in practice. While considerable efforts have been made in this direction, the well-known pairwise and listwise approaches have still been limited by various challenges. Specifically, for the pairwise approaches, the assumption of independent pairwise preference is not always held in practice. Also, the listwise approaches cannot efficiently accommodate “ties” and unobserved data due to the precondition of the entire list permutation. To this end, in this article, we propose a novel setwise Bayesian approach for collaborative ranking, namely, SetRank, to inherently accommodate the characteristics of user feedback in recommender systems. SetRank aims to maximize the posterior probability of novel setwise preference structures and three implementations for SetRank are presented. We also theoretically prove that the bound of excess risk in SetRank can be proportional to (sqrt {M/N}) , where M and N are the numbers of items and users, respectively. Finally, extensive experiments on four real-world datasets clearly validate the superiority of SetRank compared with various state-of-the-art baselines.
{"title":"SetRank: A Setwise Bayesian Approach for Collaborative Ranking in Recommender System","authors":"Chao Wang, Hengshu Zhu, Chen Zhu, Chuan Qin, Enhong Chen, Hui Xiong","doi":"10.1145/3626194","DOIUrl":"https://doi.org/10.1145/3626194","url":null,"abstract":"The recent development of recommender systems has a focus on collaborative ranking, which provides users with a sorted list rather than rating prediction. The sorted item lists can more directly reflect the preferences for users and usually perform better than rating prediction in practice. While considerable efforts have been made in this direction, the well-known pairwise and listwise approaches have still been limited by various challenges. Specifically, for the pairwise approaches, the assumption of independent pairwise preference is not always held in practice. Also, the listwise approaches cannot efficiently accommodate “ties” and unobserved data due to the precondition of the entire list permutation. To this end, in this article, we propose a novel setwise Bayesian approach for collaborative ranking, namely, SetRank, to inherently accommodate the characteristics of user feedback in recommender systems. SetRank aims to maximize the posterior probability of novel setwise preference structures and three implementations for SetRank are presented. We also theoretically prove that the bound of excess risk in SetRank can be proportional to (sqrt {M/N}) , where M and N are the numbers of items and users, respectively. Finally, extensive experiments on four real-world datasets clearly validate the superiority of SetRank compared with various state-of-the-art baselines.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135432011","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}
Xiaokun Zhang, Bo Xu, Fenglong Ma, Chenliang Li, Yuan Lin, Hongfei Lin
Session-based recommendation intends to predict next purchased items based on anonymous behavior sequences. Numerous economic studies have revealed that item price is a key factor influencing user purchase decisions. Unfortunately, existing methods for session-based recommendation only aim at capturing user interest preference, while ignoring user price preference. Actually, there are primarily two challenges preventing us from accessing price preference. Firstly, the price preference is highly associated to various item features ( i.e., category and brand), which asks us to mine price preference from heterogeneous information. Secondly, price preference and interest preference are interdependent and collectively determine user choice, necessitating that we jointly consider both price and interest preference for intent modeling. To handle above challenges, we propose a novel approach Bi-Preference Learning Heterogeneous Hypergraph Networks (BiPNet) for session-based recommendation. Specifically, the customized heterogeneous hypergraph networks with a triple-level convolution are devised to capture user price and interest preference from heterogeneous features of items. Besides, we develop a Bi-Preference Learning schema to explore mutual relations between price and interest preference and collectively learn these two preferences under the multi-task learning architecture. Extensive experiments on multiple public datasets confirm the superiority of BiPNet over competitive baselines. Additional research also supports the notion that the price is crucial for the task.
{"title":"Bi-Preference Learning Heterogeneous Hypergraph Networks for Session-based Recommendation","authors":"Xiaokun Zhang, Bo Xu, Fenglong Ma, Chenliang Li, Yuan Lin, Hongfei Lin","doi":"10.1145/3631940","DOIUrl":"https://doi.org/10.1145/3631940","url":null,"abstract":"Session-based recommendation intends to predict next purchased items based on anonymous behavior sequences. Numerous economic studies have revealed that item price is a key factor influencing user purchase decisions. Unfortunately, existing methods for session-based recommendation only aim at capturing user interest preference, while ignoring user price preference. Actually, there are primarily two challenges preventing us from accessing price preference. Firstly, the price preference is highly associated to various item features ( i.e., category and brand), which asks us to mine price preference from heterogeneous information. Secondly, price preference and interest preference are interdependent and collectively determine user choice, necessitating that we jointly consider both price and interest preference for intent modeling. To handle above challenges, we propose a novel approach Bi-Preference Learning Heterogeneous Hypergraph Networks (BiPNet) for session-based recommendation. Specifically, the customized heterogeneous hypergraph networks with a triple-level convolution are devised to capture user price and interest preference from heterogeneous features of items. Besides, we develop a Bi-Preference Learning schema to explore mutual relations between price and interest preference and collectively learn these two preferences under the multi-task learning architecture. Extensive experiments on multiple public datasets confirm the superiority of BiPNet over competitive baselines. Additional research also supports the notion that the price is crucial for the task.","PeriodicalId":50936,"journal":{"name":"ACM Transactions on Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135475334","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：