Giuseppe Spillo, C. Musto, M. Degemmis, P. Lops, G. Semeraro
In this paper, we present a knowledge-aware recommendation framework based on neuro-symbolic graph embeddings that encode first-order logical (FOL) rules. In particular, our workflow starts from a knowledge graph (KG) encoding user preferences (based on explicit ratings [13]) and item properties. Next, knowledge-aware recommendation are obtained through the combination of three modules: (i) a rule learner, that extracts FOL rules from the KG; (ii) a graph embedding module, that learns the embeddings of users and items based on the triples of the KG and the FOL rules previously extracted; (iii) a recommendation module that uses the embeddings to feed a deep learning architecture. In the experimental session, we evaluate the effectiveness of our strategy on two datasets and the results show that the combination of KG embeddings and FOL rules led to an improvement in the accuracy and in the novelty of the recommendations.
{"title":"Knowledge-aware Recommendations Based on Neuro-Symbolic Graph Embeddings and First-Order Logical Rules","authors":"Giuseppe Spillo, C. Musto, M. Degemmis, P. Lops, G. Semeraro","doi":"10.1145/3523227.3551484","DOIUrl":"https://doi.org/10.1145/3523227.3551484","url":null,"abstract":"In this paper, we present a knowledge-aware recommendation framework based on neuro-symbolic graph embeddings that encode first-order logical (FOL) rules. In particular, our workflow starts from a knowledge graph (KG) encoding user preferences (based on explicit ratings [13]) and item properties. Next, knowledge-aware recommendation are obtained through the combination of three modules: (i) a rule learner, that extracts FOL rules from the KG; (ii) a graph embedding module, that learns the embeddings of users and items based on the triples of the KG and the FOL rules previously extracted; (iii) a recommendation module that uses the embeddings to feed a deep learning architecture. In the experimental session, we evaluate the effectiveness of our strategy on two datasets and the results show that the combination of KG embeddings and FOL rules led to an improvement in the accuracy and in the novelty of the recommendations.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134430375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
From autocomplete and smart replies to video filters and deepfakes, we increasingly live in a world where communication between humans is augmented by artificial intelligence. AI often operates on behalf of a human communicator by recommending, suggesting, modifying, or generating messages to accomplish communication goals. We call this phenomenon AI-Mediated Communication (or AI-MC) [1, 4]. While AI-MC has the potential of making human communication more efficient, it impacts other aspects of our communication in ways that are not yet well understood. Over the last three years, my collaborators and I have been documenting the impact of AI-MC on communication outcomes, language use, interpersonal trust, and more. The talk will outline early experimental findings from this work, mostly led by Cornell and Stanford graduate students Maurice Jakesch, Hannah Mieczkowski, and Jess Hohenstein. For example, the research shows that AI-MC involvement can result in language shifting towards positivity [2, 7]; impact the evaluation of others [2, 4]; change the extent to which we take ownership over our messages [6]; and shift assignment of blame for communication outcomes [3]. Given the impact of AI-MC on interpersonal evaluations, the talk will also cover our recent research examining the (mostly false) heuristics humans use when evaluating whether text was written by AI [5]. Overall, AI-MC raises significant practical and ethical concerns as it stands to reshape human communication, calling for new approaches to the development and regulation of these technologies.
从自动补全和智能回复，到视频过滤器和深度造假，我们越来越生活在一个人工智能增强了人与人之间交流的世界。人工智能通常通过推荐、建议、修改或生成消息来代表人类沟通者进行操作，以实现沟通目标。我们将这种现象称为AI-Mediated Communication (AI-MC)[1,4]。虽然AI-MC有可能使人类的沟通更有效率，但它对我们沟通的其他方面的影响还没有得到很好的理解。在过去的三年里，我和我的合作者一直在记录AI-MC对沟通结果、语言使用、人际信任等方面的影响。讲座将概述这项工作的早期实验结果，主要由康奈尔大学和斯坦福大学的研究生莫里斯·杰克什、汉娜·米茨科夫斯基和杰斯·霍恩斯坦领导。例如，研究表明AI-MC参与可以导致语言向积极方向转变[2,7];影响他人评价[2,4];改变我们对信息的掌控程度[6];并转移沟通结果的责任分配[3]。鉴于AI- mc对人际评价的影响，演讲还将涵盖我们最近的研究，该研究检查了人类在评估文本是否由AI编写时使用的启发式(大多是错误的)[5]。总的来说，AI-MC引起了重大的实践和伦理问题，因为它将重塑人类的沟通，要求对这些技术的开发和监管采取新的方法。
{"title":"“My AI must have been broken”: How AI Stands to Reshape Human Communication","authors":"Mor Naaman","doi":"10.1145/3523227.3555724","DOIUrl":"https://doi.org/10.1145/3523227.3555724","url":null,"abstract":"From autocomplete and smart replies to video filters and deepfakes, we increasingly live in a world where communication between humans is augmented by artificial intelligence. AI often operates on behalf of a human communicator by recommending, suggesting, modifying, or generating messages to accomplish communication goals. We call this phenomenon AI-Mediated Communication (or AI-MC) [1, 4]. While AI-MC has the potential of making human communication more efficient, it impacts other aspects of our communication in ways that are not yet well understood. Over the last three years, my collaborators and I have been documenting the impact of AI-MC on communication outcomes, language use, interpersonal trust, and more. The talk will outline early experimental findings from this work, mostly led by Cornell and Stanford graduate students Maurice Jakesch, Hannah Mieczkowski, and Jess Hohenstein. For example, the research shows that AI-MC involvement can result in language shifting towards positivity [2, 7]; impact the evaluation of others [2, 4]; change the extent to which we take ownership over our messages [6]; and shift assignment of blame for communication outcomes [3]. Given the impact of AI-MC on interpersonal evaluations, the talk will also cover our recent research examining the (mostly false) heuristics humans use when evaluating whether text was written by AI [5]. Overall, AI-MC raises significant practical and ethical concerns as it stands to reshape human communication, calling for new approaches to the development and regulation of these technologies.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132551047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zehuan Wang, Yingcan Wei, Minseok Lee, Matthias Langer, F. Yu, Jie Liu, Shijie Liu, Daniel G. Abel, Xu Guo, Jianbing Dong, Ji Shi, Kunlun Li
In this talk, we introduce Merlin HugeCTR. Merlin HugeCTR is an open source, GPU-accelerated integration framework for click-through rate estimation. It optimizes both training and inference, whilst enabling model training at scale with model-parallel embeddings and data-parallel neural networks. In particular, Merlin HugeCTR combines a high-performance GPU embedding cache with an hierarchical storage architecture, to realize low-latency retrieval of embeddings for online model inference tasks. In the MLPerf v1.0 DLRM model training benchmark, Merlin HugeCTR achieves a speedup of up to 24.6x on a single DGX A100 (8x A100) over PyTorch on 4x4-socket CPU nodes (4x4x28 cores). Merlin HugeCTR can also take advantage of multi-node environments to accelerate training even further. Since late 2021, Merlin HugeCTR additionally features a hierarchical parameter server (HPS) and supports deployment via the NVIDIA Triton server framework, to leverage the computational capabilities of GPUs for high-speed recommendation model inference. Using this HPS, Merlin HugeCTR users can achieve a 5~62x speedup (batch size dependent) for popular recommendation models over CPU baseline implementations, and dramatically reduce their end-to-end inference latency.
{"title":"Merlin HugeCTR: GPU-accelerated Recommender System Training and Inference","authors":"Zehuan Wang, Yingcan Wei, Minseok Lee, Matthias Langer, F. Yu, Jie Liu, Shijie Liu, Daniel G. Abel, Xu Guo, Jianbing Dong, Ji Shi, Kunlun Li","doi":"10.1145/3523227.3547405","DOIUrl":"https://doi.org/10.1145/3523227.3547405","url":null,"abstract":"In this talk, we introduce Merlin HugeCTR. Merlin HugeCTR is an open source, GPU-accelerated integration framework for click-through rate estimation. It optimizes both training and inference, whilst enabling model training at scale with model-parallel embeddings and data-parallel neural networks. In particular, Merlin HugeCTR combines a high-performance GPU embedding cache with an hierarchical storage architecture, to realize low-latency retrieval of embeddings for online model inference tasks. In the MLPerf v1.0 DLRM model training benchmark, Merlin HugeCTR achieves a speedup of up to 24.6x on a single DGX A100 (8x A100) over PyTorch on 4x4-socket CPU nodes (4x4x28 cores). Merlin HugeCTR can also take advantage of multi-node environments to accelerate training even further. Since late 2021, Merlin HugeCTR additionally features a hierarchical parameter server (HPS) and supports deployment via the NVIDIA Triton server framework, to leverage the computational capabilities of GPUs for high-speed recommendation model inference. Using this HPS, Merlin HugeCTR users can achieve a 5~62x speedup (batch size dependent) for popular recommendation models over CPU baseline implementations, and dramatically reduce their end-to-end inference latency.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"212 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132790792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Many online personalization platforms today are recommending heterogeneous contents in a multi-sided marketplace consisting of consumers, merchants and other partners. For a recommender system to be successful in these contexts, it faces two main challenges. First, each side in the marketplace has different and potentially conflicting utilities. Recommending for a multi-sided marketplace therefore entails jointly optimizing multiple objectives with trade-offs. Second, the off-the-shelf recommendation algorithms are not applicable to the heterogeneous content space, where a recommendation item could be an aggregation of other recommendation items. In this work, we develop a general framework for recommender systems in a multi-sided marketplace with heterogeneous and hierarchical contents. We propose a constrained optimization framework with machine learning models for each objective as inputs, and a probabilistic structural model for users’ engagement patterns on heterogeneous contents. Our proposed structural modeling approach ensures consistent user experience across different levels of aggregation of the contents, and provides levels of transparency to the merchants and content providers. We further develop an efficient optimization solution for ranking and recommendation in large-scale online systems in real time. We implement the framework at Uber Eats, one of the largest online food delivery platforms in the world and a three-sided marketplace consisting of eaters, restaurant partners and delivery partners. Online experiments demonstrate the effectiveness of our framework in ranking heterogeneous contents and optimizing for the three sides in the marketplace. Our framework has been deployed globally as the recommendation algorithm for Uber Eats’ homepage.
{"title":"Recommending for a multi-sided marketplace with heterogeneous contents","authors":"Yuyan Wang, Long Tao, Xian-Xing Zhang","doi":"10.1145/3523227.3547379","DOIUrl":"https://doi.org/10.1145/3523227.3547379","url":null,"abstract":"Many online personalization platforms today are recommending heterogeneous contents in a multi-sided marketplace consisting of consumers, merchants and other partners. For a recommender system to be successful in these contexts, it faces two main challenges. First, each side in the marketplace has different and potentially conflicting utilities. Recommending for a multi-sided marketplace therefore entails jointly optimizing multiple objectives with trade-offs. Second, the off-the-shelf recommendation algorithms are not applicable to the heterogeneous content space, where a recommendation item could be an aggregation of other recommendation items. In this work, we develop a general framework for recommender systems in a multi-sided marketplace with heterogeneous and hierarchical contents. We propose a constrained optimization framework with machine learning models for each objective as inputs, and a probabilistic structural model for users’ engagement patterns on heterogeneous contents. Our proposed structural modeling approach ensures consistent user experience across different levels of aggregation of the contents, and provides levels of transparency to the merchants and content providers. We further develop an efficient optimization solution for ranking and recommendation in large-scale online systems in real time. We implement the framework at Uber Eats, one of the largest online food delivery platforms in the world and a three-sided marketplace consisting of eaters, restaurant partners and delivery partners. Online experiments demonstrate the effectiveness of our framework in ranking heterogeneous contents and optimizing for the three sides in the marketplace. Our framework has been deployed globally as the recommendation algorithm for Uber Eats’ homepage.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132340870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
W. Shalaby, Sejoon Oh, Amir Afsharinejad, Srijan Kumar, Xiquan Cui
Session-based recommender systems (SBRSs) have shown superior performance over conventional methods. However, they show limited scalability on large-scale industrial datasets since most models learn one embedding per item. This leads to a large memory requirement (of storing one vector per item) and poor performance on sparse sessions with cold-start or unpopular items. Using one public and one large industrial dataset, we experimentally show that state-of-the-art SBRSs have low performance on sparse sessions with sparse items. We propose M2TRec, a Metadata-aware Multi-task Transformer model for session-based recommendations. Our proposed method learns a transformation function from item metadata to embeddings, and is thus, item-ID free (i.e., does not need to learn one embedding per item). It integrates item metadata to learn shared representations of diverse item attributes. During inference, new or unpopular items will be assigned identical representations for the attributes they share with items previously observed during training, and thus will have similar representations with those items, enabling recommendations of even cold-start and sparse items. Additionally, M2TRec is trained in a multi-task setting to predict the next item in the session along with its primary category and subcategories. Our multi-task strategy makes the model converge faster and significantly improves the overall performance. Experimental results show significant performance gains using our proposed approach on sparse items on the two datasets.
{"title":"M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations","authors":"W. Shalaby, Sejoon Oh, Amir Afsharinejad, Srijan Kumar, Xiquan Cui","doi":"10.1145/3523227.3551477","DOIUrl":"https://doi.org/10.1145/3523227.3551477","url":null,"abstract":"Session-based recommender systems (SBRSs) have shown superior performance over conventional methods. However, they show limited scalability on large-scale industrial datasets since most models learn one embedding per item. This leads to a large memory requirement (of storing one vector per item) and poor performance on sparse sessions with cold-start or unpopular items. Using one public and one large industrial dataset, we experimentally show that state-of-the-art SBRSs have low performance on sparse sessions with sparse items. We propose M2TRec, a Metadata-aware Multi-task Transformer model for session-based recommendations. Our proposed method learns a transformation function from item metadata to embeddings, and is thus, item-ID free (i.e., does not need to learn one embedding per item). It integrates item metadata to learn shared representations of diverse item attributes. During inference, new or unpopular items will be assigned identical representations for the attributes they share with items previously observed during training, and thus will have similar representations with those items, enabling recommendations of even cold-start and sparse items. Additionally, M2TRec is trained in a multi-task setting to predict the next item in the session along with its primary category and subcategories. Our multi-task strategy makes the model converge faster and significantly improves the overall performance. Experimental results show significant performance gains using our proposed approach on sparse items on the two datasets.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133162867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Group Recommender Systems (GRSs), unlike recommendations for individuals, provide suggestions for groups of people. Clearly, many activities are often experienced by a group rather than an individual (visiting a restaurant, traveling, watching a movie, etc.) hence the requirement for such systems. The topic is gradually receiving more and more attention, with an increased number of papers published at significant venues, which is enabled by the predominance of online social platforms that allow their users to interact in groups, as well as to plan group activities. However, the research area lacks certain ground rules, such as basic evaluation agreements. We believe this is one of the main obstacles to make advances in the research area, and to enable researchers to compare and continue each others’ works. In other words, setting the basic evaluation agreements is a stepping-stone towards reproducible Group Recommenders research. The goal of this tutorial is to tackle this problem, by providing the basic principles of the GRSs offline evaluation approaches.
{"title":"Tutorial on Offline Evaluation for Group Recommender Systems","authors":"F. Barile, Amra Delic, Ladislav Peška","doi":"10.1145/3523227.3547371","DOIUrl":"https://doi.org/10.1145/3523227.3547371","url":null,"abstract":"Group Recommender Systems (GRSs), unlike recommendations for individuals, provide suggestions for groups of people. Clearly, many activities are often experienced by a group rather than an individual (visiting a restaurant, traveling, watching a movie, etc.) hence the requirement for such systems. The topic is gradually receiving more and more attention, with an increased number of papers published at significant venues, which is enabled by the predominance of online social platforms that allow their users to interact in groups, as well as to plan group activities. However, the research area lacks certain ground rules, such as basic evaluation agreements. We believe this is one of the main obstacles to make advances in the research area, and to enable researchers to compare and continue each others’ works. In other words, setting the basic evaluation agreements is a stepping-stone towards reproducible Group Recommenders research. The goal of this tutorial is to tackle this problem, by providing the basic principles of the GRSs offline evaluation approaches.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123762889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maximum inner product search (or k-MIPS) is a fundamental operation in recommender systems that infer preferable items for users. To support large-scale recommender systems, existing studies designed scalable k-MIPS algorithms. However, these studies do not consider diversity, although recommending diverse items is important to improve user satisfaction. We therefore formulate a new problem, namely diversity-aware k-MIPS. In this problem, users can control the degree of diversity in their recommendation lists through a parameter. However, exactly solving this problem is unfortunately NP-hard, so it is challenging to devise an efficient, effective, and practical algorithm for the diversity-aware k-MIPS problem. This paper overcomes this challenge and proposes IP-Greedy, which incorporates new early termination and skipping techniques into a greedy algorithm. We conduct extensive experiments on real datasets, and the results demonstrate the efficiency and effectiveness of our algorithm. Also, we conduct a case study of the diversity-aware k-MIPS problem on a real dataset. We confirm that this problem can make recommendation lists diverse while preserving high inner products of user and item vectors in the lists.
{"title":"Solving Diversity-Aware Maximum Inner Product Search Efficiently and Effectively","authors":"Kohei Hirata, Daichi Amagata, Sumio Fujita, Takahiro Hara","doi":"10.1145/3523227.3546779","DOIUrl":"https://doi.org/10.1145/3523227.3546779","url":null,"abstract":"Maximum inner product search (or k-MIPS) is a fundamental operation in recommender systems that infer preferable items for users. To support large-scale recommender systems, existing studies designed scalable k-MIPS algorithms. However, these studies do not consider diversity, although recommending diverse items is important to improve user satisfaction. We therefore formulate a new problem, namely diversity-aware k-MIPS. In this problem, users can control the degree of diversity in their recommendation lists through a parameter. However, exactly solving this problem is unfortunately NP-hard, so it is challenging to devise an efficient, effective, and practical algorithm for the diversity-aware k-MIPS problem. This paper overcomes this challenge and proposes IP-Greedy, which incorporates new early termination and skipping techniques into a greedy algorithm. We conduct extensive experiments on real datasets, and the results demonstrate the efficiency and effectiveness of our algorithm. Also, we conduct a case study of the diversity-aware k-MIPS problem on a real dataset. We confirm that this problem can make recommendation lists diverse while preserving high inner products of user and item vectors in the lists.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125243562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Online Fashion retailers have significantly increased in popularity over the last decade, making it possible for customers to explore hundreds of thousands of products without the need to visit multiple stores or stand in long queues for checkout. Recommender Systems are often used to solve different complex problems in this domain, such as social fashion-aware recommendations (outfits inspired by influencers), product recommendations, or size and fit recommendations. Moreover, the research interest on this area is increasing, demonstrated by the success of the past three editions of the fashionXrecsys Workshops 2019-21. The Fourth edition of the workshop aims at providing an avenue for continuing the discussion of novel approaches and applications of recommendation systems in fashion and e-commerce with a particular focus on pandemic era events and their short and long lasting effects on e-commerce and Fashion.
{"title":"Fourth Workshop on Recommender Systems in Fashion and Retail – fashionXrecsys2022","authors":"Reza Shirvany, Humberto Jesús Corona Pampín","doi":"10.1145/3523227.3547417","DOIUrl":"https://doi.org/10.1145/3523227.3547417","url":null,"abstract":"Online Fashion retailers have significantly increased in popularity over the last decade, making it possible for customers to explore hundreds of thousands of products without the need to visit multiple stores or stand in long queues for checkout. Recommender Systems are often used to solve different complex problems in this domain, such as social fashion-aware recommendations (outfits inspired by influencers), product recommendations, or size and fit recommendations. Moreover, the research interest on this area is increasing, demonstrated by the success of the past three editions of the fashionXrecsys Workshops 2019-21. The Fourth edition of the workshop aims at providing an avenue for continuing the discussion of novel approaches and applications of recommendation systems in fashion and e-commerce with a particular focus on pandemic era events and their short and long lasting effects on e-commerce and Fashion.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127518486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
RecPack is an easy-to-use, flexible and extensible toolkit for top-N recommendation with implicit feedback data. Its goal is to support researchers with the development of their recommendation algorithms, from similarity-based to deep learning algorithms, and allow for correct, reproducible and reusable experimentation. In this demo, we give an overview of the package and show how researchers can use it to their advantage when developing recommendation algorithms.
{"title":"RecPack: An(other) Experimentation Toolkit for Top-N Recommendation using Implicit Feedback Data","authors":"L. Michiels, Robin Verachtert, Bart Goethals","doi":"10.1145/3523227.3551472","DOIUrl":"https://doi.org/10.1145/3523227.3551472","url":null,"abstract":"RecPack is an easy-to-use, flexible and extensible toolkit for top-N recommendation with implicit feedback data. Its goal is to support researchers with the development of their recommendation algorithms, from similarity-based to deep learning algorithms, and allow for correct, reproducible and reusable experimentation. In this demo, we give an overview of the package and show how researchers can use it to their advantage when developing recommendation algorithms.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126223748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fernando Benjamín Pérez Maurera, Maurizio Ferrari Dacrema, P. Cremonesi
In Recommender Systems, impressions are a relatively new type of information that records all products previously shown to the users. They are also a complex source of information, combining the effects of the recommender system that generated them, search results, or business rules that may select specific products for recommendations. The fact that the user interacted with a specific item given a list of recommended ones may benefit from a richer interaction signal, in which some items the user did not interact with may be considered negative interactions. This work presents a preliminary evaluation of recommendation models with impressions. First, impressions are characterized by describing their assumptions, signals, and challenges. Then, an evaluation study with impressions is described. The study’s goal is two-fold: to measure the effects of impressions data on properly-tuned recommendation models using current open-source datasets and disentangle the signals within impressions data. Preliminary results suggest that impressions data and signals are nuanced, complex, and effective at improving the recommendation quality of recommenders. This work publishes the source code, datasets, and scripts used in the evaluation to promote reproducibility in the domain.
{"title":"Towards the Evaluation of Recommender Systems with Impressions","authors":"Fernando Benjamín Pérez Maurera, Maurizio Ferrari Dacrema, P. Cremonesi","doi":"10.1145/3523227.3551483","DOIUrl":"https://doi.org/10.1145/3523227.3551483","url":null,"abstract":"In Recommender Systems, impressions are a relatively new type of information that records all products previously shown to the users. They are also a complex source of information, combining the effects of the recommender system that generated them, search results, or business rules that may select specific products for recommendations. The fact that the user interacted with a specific item given a list of recommended ones may benefit from a richer interaction signal, in which some items the user did not interact with may be considered negative interactions. This work presents a preliminary evaluation of recommendation models with impressions. First, impressions are characterized by describing their assumptions, signals, and challenges. Then, an evaluation study with impressions is described. The study’s goal is two-fold: to measure the effects of impressions data on properly-tuned recommendation models using current open-source datasets and disentangle the signals within impressions data. Preliminary results suggest that impressions data and signals are nuanced, complex, and effective at improving the recommendation quality of recommenders. This work publishes the source code, datasets, and scripts used in the evaluation to promote reproducibility in the domain.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121803698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：