Sequential recommendation has attracted a lot of attention from both academia and industry. Since item embeddings directly affect the recommendation results, their learning process is very important. However, most existing sequential models may introduce bias when updating the item embeddings. For example, in a sequence where all items are endorsed by a same celebrity, the co-occurrence of two items only indicates their similarity in terms of endorser, and is independent of the other aspects such as category and color. The existing models often update the entire item as a whole or update different aspects of the item without distinction, which fails to capture the contributions of different aspects to the co-occurrence pattern. To overcome the above limitations, we propose aspect re-distribution (ARD) to focus on updating the aspects that are important for co-occurrence. Specifically, we represent an item using several aspect embeddings with the same initial importance. We then re-calculate the importance of each aspect according to the other items in the sequence. Finally, we aggregate these aspect embeddings into a single aspect-aware embedding according to their importance. The aspect-aware embedding can be provided as input to a successor sequential model. Updates of the aspect-aware embedding are passed back to the aspect embeddings based on their importance. Therefore, different from the existing models, our method pays more attention to updating the important aspects. In our experiments, we choose self-attention networks as the successor model. The experimental results on four real-world datasets indicate that our method achieves very promising performance in comparison with seven state-of-the-art models.
{"title":"Aspect Re-distribution for Learning Better Item Embeddings in Sequential Recommendation","authors":"Wei Cai, Weike Pan, Jingwen Mao, Zhechao Yu, Congfu Xu","doi":"10.1145/3523227.3546764","DOIUrl":"https://doi.org/10.1145/3523227.3546764","url":null,"abstract":"Sequential recommendation has attracted a lot of attention from both academia and industry. Since item embeddings directly affect the recommendation results, their learning process is very important. However, most existing sequential models may introduce bias when updating the item embeddings. For example, in a sequence where all items are endorsed by a same celebrity, the co-occurrence of two items only indicates their similarity in terms of endorser, and is independent of the other aspects such as category and color. The existing models often update the entire item as a whole or update different aspects of the item without distinction, which fails to capture the contributions of different aspects to the co-occurrence pattern. To overcome the above limitations, we propose aspect re-distribution (ARD) to focus on updating the aspects that are important for co-occurrence. Specifically, we represent an item using several aspect embeddings with the same initial importance. We then re-calculate the importance of each aspect according to the other items in the sequence. Finally, we aggregate these aspect embeddings into a single aspect-aware embedding according to their importance. The aspect-aware embedding can be provided as input to a successor sequential model. Updates of the aspect-aware embedding are passed back to the aspect embeddings based on their importance. Therefore, different from the existing models, our method pays more attention to updating the important aspects. In our experiments, we choose self-attention networks as the successor model. The experimental results on four real-world datasets indicate that our method achieves very promising performance in comparison with seven state-of-the-art models.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124234163","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}
Shuchang Liu, Yingqiang Ge, Shuyuan Xu, Yongfeng Zhang, A. Marian
Achieving fairness over different user groups in recommender systems is an important problem. The majority of existing works achieve fairness through constrained optimization that combines the recommendation loss and the fairness constraint. To achieve fairness, the algorithm usually needs to know each user’s group affiliation feature such as gender or race. However, such involved user group feature is usually sensitive and requires protection. In this work, we seek a federated learning solution for the fair recommendation problem and identify the main challenge as an algorithmic conflict between the global fairness objective and the localized federated optimization process. On one hand, the fairness objective usually requires access to all users’ group information. On the other hand, the federated learning systems restrain the personal data in each user’s local space. As a resolution, we propose to communicate group statistics during federated optimization and use differential privacy techniques to avoid exposure of users’ group information when users require privacy protection. We illustrate the theoretical bounds of the noisy signal used in our method that aims to enforce privacy without overwhelming the aggregated statistics. Empirical results show that federated learning may naturally improve user group fairness and the proposed framework can effectively control this fairness with low communication overheads.
{"title":"Fairness-aware Federated Matrix Factorization","authors":"Shuchang Liu, Yingqiang Ge, Shuyuan Xu, Yongfeng Zhang, A. Marian","doi":"10.1145/3523227.3546771","DOIUrl":"https://doi.org/10.1145/3523227.3546771","url":null,"abstract":"Achieving fairness over different user groups in recommender systems is an important problem. The majority of existing works achieve fairness through constrained optimization that combines the recommendation loss and the fairness constraint. To achieve fairness, the algorithm usually needs to know each user’s group affiliation feature such as gender or race. However, such involved user group feature is usually sensitive and requires protection. In this work, we seek a federated learning solution for the fair recommendation problem and identify the main challenge as an algorithmic conflict between the global fairness objective and the localized federated optimization process. On one hand, the fairness objective usually requires access to all users’ group information. On the other hand, the federated learning systems restrain the personal data in each user’s local space. As a resolution, we propose to communicate group statistics during federated optimization and use differential privacy techniques to avoid exposure of users’ group information when users require privacy protection. We illustrate the theoretical bounds of the noisy signal used in our method that aims to enforce privacy without overwhelming the aggregated statistics. Empirical results show that federated learning may naturally improve user group fairness and the proposed framework can effectively control this fairness with low communication overheads.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127720808","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}
Peter Brusilovsky, Marco de Gemmis, A. Felfernig, P. Lops, Marco Polignano, G. Semeraro, M. Willemsen
The constant increase in the amount of data and information available on the Web has made the development of systems that can support users in making relevant decisions increasingly important. Recommender systems (RSs) have emerged as tools to address this task. RSs use the preferences expressed by a user, either explicitly or implicitly, to filter the available information and proactively suggest items that might be of interest to him or her. Although in early works about the topic there was a strong interest in ways to make such systems proactive, user-friendly, and persuasive, over time they became increasingly focused on the algorithmic component solely. However, this trend is gradually being reversed and always more attention is nowadays placed also on Human Decision Making models that focus on supporting the end user in understanding what is being proposed through RSs by using dynamic and persuasive interfaces. A recommender system should be based on valuable strategies for proactively guiding users to items that match their preferences and therefore should put attention on how it is possible to make this process trustable, pleasant, and user-friendly. Such systems, moreover, should take into account psychological, cognitive and emotional aspects to enable personalization that is appropriate not only to the context of use but also to the psychological reactions of the end user. The workshop provides a venue for works that invest in the design of recommender systems which consider users’ experience during the interaction, as well as for works that explore the implications of human-computer interactions with different theories of human decision-making. In this summary, we introduce the Joint Workshop on Interfaces and Human Decision Making for Recommender Systems at RecSys’22, review its history, and discuss the most important topics considered at the workshop.
{"title":"Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS’22)","authors":"Peter Brusilovsky, Marco de Gemmis, A. Felfernig, P. Lops, Marco Polignano, G. Semeraro, M. Willemsen","doi":"10.1145/3523227.3547413","DOIUrl":"https://doi.org/10.1145/3523227.3547413","url":null,"abstract":"The constant increase in the amount of data and information available on the Web has made the development of systems that can support users in making relevant decisions increasingly important. Recommender systems (RSs) have emerged as tools to address this task. RSs use the preferences expressed by a user, either explicitly or implicitly, to filter the available information and proactively suggest items that might be of interest to him or her. Although in early works about the topic there was a strong interest in ways to make such systems proactive, user-friendly, and persuasive, over time they became increasingly focused on the algorithmic component solely. However, this trend is gradually being reversed and always more attention is nowadays placed also on Human Decision Making models that focus on supporting the end user in understanding what is being proposed through RSs by using dynamic and persuasive interfaces. A recommender system should be based on valuable strategies for proactively guiding users to items that match their preferences and therefore should put attention on how it is possible to make this process trustable, pleasant, and user-friendly. Such systems, moreover, should take into account psychological, cognitive and emotional aspects to enable personalization that is appropriate not only to the context of use but also to the psychological reactions of the end user. The workshop provides a venue for works that invest in the design of recommender systems which consider users’ experience during the interaction, as well as for works that explore the implications of human-computer interactions with different theories of human decision-making. In this summary, we introduce the Joint Workshop on Interfaces and Human Decision Making for Recommender Systems at RecSys’22, review its history, and discuss the most important topics considered at the workshop.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125685211","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}
In this extended abstract, we present an end to end approach for building a taxonomy of home attribute terms that enables hierarchical recommendations of real estate properties. We cover the methodology for building a real-estate taxonomy, metrics for measuring this structure’s quality, and then conclude with a production use-case of making recommendations from search keywords at different levels of topical similarity.
{"title":"Taxonomic Recommendations of Real Estate Properties with Textual Attribute Information","authors":"Zachary Harrison, Anish Khazane","doi":"10.1145/3523227.3547386","DOIUrl":"https://doi.org/10.1145/3523227.3547386","url":null,"abstract":"In this extended abstract, we present an end to end approach for building a taxonomy of home attribute terms that enables hierarchical recommendations of real estate properties. We cover the methodology for building a real-estate taxonomy, metrics for measuring this structure’s quality, and then conclude with a production use-case of making recommendations from search keywords at different levels of topical similarity.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130875999","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}
Richard Liaw, Paige Bailey, Ying Li, Maria Dimakopoulou, Yves Raimond
Recommendation systems are increasingly modelled as a sequential decision making process, where the system decides which items to recommend to a given user. Each decision to recommend an item or slate of items has a significant impact on immediate and future user responses, long-term satisfaction or engagement with the system, and possibly valuable exposure for the item provider. The REVEAL workshop will focus on how to optimise this multi-step decision-making process, where a stream of interactions occurs between the user and the system. Deriving reward signals from these interactions, and creating a scalable, performant, and maintainable recommendation model to use for inference is a key challenge for machine learning teams, both in industry and academia. We will discuss the following challenges at the workshop: How can recommendation system models take into account the delayed effects of each recommendation? What are the right ways to reason and plan for longer-term user satisfaction? How can we leverage techniques such as Reinforcement Learning (RL) at scale?
{"title":"REVEAL 2022: Reinforcement Learning-Based Recommender Systems at Scale","authors":"Richard Liaw, Paige Bailey, Ying Li, Maria Dimakopoulou, Yves Raimond","doi":"10.1145/3523227.3547418","DOIUrl":"https://doi.org/10.1145/3523227.3547418","url":null,"abstract":"Recommendation systems are increasingly modelled as a sequential decision making process, where the system decides which items to recommend to a given user. Each decision to recommend an item or slate of items has a significant impact on immediate and future user responses, long-term satisfaction or engagement with the system, and possibly valuable exposure for the item provider. The REVEAL workshop will focus on how to optimise this multi-step decision-making process, where a stream of interactions occurs between the user and the system. Deriving reward signals from these interactions, and creating a scalable, performant, and maintainable recommendation model to use for inference is a key challenge for machine learning teams, both in industry and academia. We will discuss the following challenges at the workshop: How can recommendation system models take into account the delayed effects of each recommendation? What are the right ways to reason and plan for longer-term user satisfaction? How can we leverage techniques such as Reinforcement Learning (RL) at scale?","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115343470","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}
Click-through rate (CTR) Prediction is of great importance in real-world online ads systems. One challenge for the CTR prediction task is to capture the real interest of users from their clicked items, which is inherently influenced by presented positions of items, i.e., more front positions tend to obtain higher CTR values. Therefore, It is crucial to make CTR models aware of the exposed position of the items. A popular line of existing works focuses on explicitly model exposed position by result randomization which is expensive and inefficient, or by inverse propensity weighting (IPW) which relies heavily on the quality of the propensity estimation. Another common solution is modeling position as features during offline training and simply adopting fixed value or dropout tricks when serving. However, training-inference inconsistency can lead to sub-optimal performance. This work proposes a simple yet efficient knowledge distillation framework to model the impact of exposed position and leverage position information to improve CTR prediction. We demonstrate the performance of our proposed method on a real-world production dataset and online A/B tests, achieving significant improvements over competing baseline models. The proposed method has been deployed in the real world online ads systems of JD, serving main traffic of hundreds of millions of active users.
{"title":"Position Awareness Modeling with Knowledge Distillation for CTR Prediction","authors":"Congcong Liu, Yuejiang Li, Jian Zhu, Fei Teng, Xiwei Zhao, Changping Peng, Zhangang Lin, Jingping Shao","doi":"10.1145/3523227.3551475","DOIUrl":"https://doi.org/10.1145/3523227.3551475","url":null,"abstract":"Click-through rate (CTR) Prediction is of great importance in real-world online ads systems. One challenge for the CTR prediction task is to capture the real interest of users from their clicked items, which is inherently influenced by presented positions of items, i.e., more front positions tend to obtain higher CTR values. Therefore, It is crucial to make CTR models aware of the exposed position of the items. A popular line of existing works focuses on explicitly model exposed position by result randomization which is expensive and inefficient, or by inverse propensity weighting (IPW) which relies heavily on the quality of the propensity estimation. Another common solution is modeling position as features during offline training and simply adopting fixed value or dropout tricks when serving. However, training-inference inconsistency can lead to sub-optimal performance. This work proposes a simple yet efficient knowledge distillation framework to model the impact of exposed position and leverage position information to improve CTR prediction. We demonstrate the performance of our proposed method on a real-world production dataset and online A/B tests, achieving significant improvements over competing baseline models. The proposed method has been deployed in the real world online ads systems of JD, serving main traffic of hundreds of millions of active users.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114246233","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}
Multi-modal interactive recommendation is a type of task that allows users to receive visual recommendations and express natural-language feedback about the recommended items across multiple iterations of interactions. However, such multi-modal dialog sequences (i.e. turns consisting of the system’s visual recommendations and the user’s natural-language feedback) make it challenging to correctly incorporate the users’ preferences across multiple turns. Indeed, the existing formulations of interactive recommender systems suffer from their inability to capture the multi-modal sequential dependencies of textual feedback and visual recommendations because of their use of recurrent neural network-based (i.e., RNN-based) or transformer-based models. To alleviate the multi-modal sequential dependency issue, we propose a novel multi-modal recurrent attention network (MMRAN) model to effectively incorporate the users’ preferences over the long visual dialog sequences of the users’ natural-language feedback and the system’s visual recommendations. Specifically, we leverage a gated recurrent network (GRN) with a feedback gate to separately process the textual and visual representations of natural-language feedback and visual recommendations into hidden states (i.e. representations of the past interactions) for multi-modal sequence combination. In addition, we apply a multi-head attention network (MAN) to refine the hidden states generated by the GRN and to further enhance the model’s ability in dynamic state tracking. Following previous work, we conduct extensive experiments on the Fashion IQ Dresses, Shirts, and Tops & Tees datasets to assess the effectiveness of our proposed model by using a vision-language transformer-based user simulator as a surrogate for real human users. Our results show that our proposed MMRAN model can significantly outperform several existing state-of-the-art baseline models.
多模态交互推荐是一种允许用户接收视觉推荐并跨多个交互迭代表达关于推荐项目的自然语言反馈的任务。然而，这种多模式对话序列(即由系统的视觉建议和用户的自然语言反馈组成的回合)使得在多个回合中正确整合用户的偏好变得具有挑战性。事实上，现有的交互式推荐系统由于使用基于循环神经网络(即基于rnn)或基于变压器的模型而无法捕获文本反馈和视觉推荐的多模态顺序依赖关系。为了缓解多模态顺序依赖问题，我们提出了一种新的多模态循环注意网络(MMRAN)模型，以有效地将用户的偏好与用户自然语言反馈的长视觉对话序列和系统的视觉推荐相结合。具体来说，我们利用带有反馈门的门控循环网络(GRN)将自然语言反馈和视觉推荐的文本和视觉表示分别处理为多模态序列组合的隐藏状态(即过去相互作用的表示)。此外，我们采用多头注意网络(MAN)对GRN产生的隐藏状态进行细化，进一步增强了模型的动态跟踪能力。在之前的工作之后，我们对Fashion IQ Dresses, Shirts和Tops & Tees数据集进行了广泛的实验，通过使用基于视觉语言转换器的用户模拟器作为真实人类用户的代理来评估我们提出的模型的有效性。我们的研究结果表明，我们提出的MMRAN模型可以显著优于几个现有的最先进的基线模型。
{"title":"Multi-Modal Dialog State Tracking for Interactive Fashion Recommendation","authors":"Yaxiong Wu, C. Macdonald, I. Ounis","doi":"10.1145/3523227.3546774","DOIUrl":"https://doi.org/10.1145/3523227.3546774","url":null,"abstract":"Multi-modal interactive recommendation is a type of task that allows users to receive visual recommendations and express natural-language feedback about the recommended items across multiple iterations of interactions. However, such multi-modal dialog sequences (i.e. turns consisting of the system’s visual recommendations and the user’s natural-language feedback) make it challenging to correctly incorporate the users’ preferences across multiple turns. Indeed, the existing formulations of interactive recommender systems suffer from their inability to capture the multi-modal sequential dependencies of textual feedback and visual recommendations because of their use of recurrent neural network-based (i.e., RNN-based) or transformer-based models. To alleviate the multi-modal sequential dependency issue, we propose a novel multi-modal recurrent attention network (MMRAN) model to effectively incorporate the users’ preferences over the long visual dialog sequences of the users’ natural-language feedback and the system’s visual recommendations. Specifically, we leverage a gated recurrent network (GRN) with a feedback gate to separately process the textual and visual representations of natural-language feedback and visual recommendations into hidden states (i.e. representations of the past interactions) for multi-modal sequence combination. In addition, we apply a multi-head attention network (MAN) to refine the hidden states generated by the GRN and to further enhance the model’s ability in dynamic state tracking. Following previous work, we conduct extensive experiments on the Fashion IQ Dresses, Shirts, and Tops & Tees datasets to assess the effectiveness of our proposed model by using a vision-language transformer-based user simulator as a surrogate for real human users. Our results show that our proposed MMRAN model can significantly outperform several existing state-of-the-art baseline models.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114436794","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}
Alessandro B. Melchiorre, Navid Rekabsaz, Christian Ganhör, M. Schedl
Recent studies show the benefits of reformulating common machine learning models through the concept of prototypes – representatives of the underlying data, used to calculate the prediction score as a linear combination of similarities of a data point to prototypes. Such prototype-based formulation of a model, in addition to preserving (sometimes enhancing) the performance, enables explainability of the model’s decisions, as the prediction can be linearly broken down into the contributions of distinct definable prototypes. Following this direction, we extend the idea of prototypes to the recommender system domain by introducing ProtoMF, a novel collaborative filtering algorithm. ProtoMF learns sets of user/item prototypes that represent the general consumption characteristics of users/items in the underlying dataset. Using these prototypes, ProtoMF then represents users and items as vectors of similarities to the corresponding prototypes. These user/item representations are ultimately leveraged to make recommendations that are both effective in terms of accuracy metrics, and explainable through the interpretation of prototypes’ contributions to the affinity scores. We conduct experiments on three datasets to assess both the effectiveness and the explainability of ProtoMF. Addressing the former, we show that ProtoMF exhibits higher Hit Ratio and NDCG compared to other relevant collaborative filtering approaches. As for the latter, we qualitatively show how ProtoMF can provide explainable recommendations and how its explanation capabilities can expose the existence of statistical biases in the learned representations, which we exemplify for the case of gender bias.
{"title":"ProtoMF: Prototype-based Matrix Factorization for Effective and Explainable Recommendations","authors":"Alessandro B. Melchiorre, Navid Rekabsaz, Christian Ganhör, M. Schedl","doi":"10.1145/3523227.3546756","DOIUrl":"https://doi.org/10.1145/3523227.3546756","url":null,"abstract":"Recent studies show the benefits of reformulating common machine learning models through the concept of prototypes – representatives of the underlying data, used to calculate the prediction score as a linear combination of similarities of a data point to prototypes. Such prototype-based formulation of a model, in addition to preserving (sometimes enhancing) the performance, enables explainability of the model’s decisions, as the prediction can be linearly broken down into the contributions of distinct definable prototypes. Following this direction, we extend the idea of prototypes to the recommender system domain by introducing ProtoMF, a novel collaborative filtering algorithm. ProtoMF learns sets of user/item prototypes that represent the general consumption characteristics of users/items in the underlying dataset. Using these prototypes, ProtoMF then represents users and items as vectors of similarities to the corresponding prototypes. These user/item representations are ultimately leveraged to make recommendations that are both effective in terms of accuracy metrics, and explainable through the interpretation of prototypes’ contributions to the affinity scores. We conduct experiments on three datasets to assess both the effectiveness and the explainability of ProtoMF. Addressing the former, we show that ProtoMF exhibits higher Hit Ratio and NDCG compared to other relevant collaborative filtering approaches. As for the latter, we qualitatively show how ProtoMF can provide explainable recommendations and how its explanation capabilities can expose the existence of statistical biases in the learned representations, which we exemplify for the case of gender bias.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126309684","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}
In this work, we present our journey to revolutionize the personalized recommendation engine through end-to-end learning from raw user actions. We encode user’s long-term interest in PinnerFormer, a user embedding optimized for long-term future actions via a new dense all-action loss, and capture user’s short-term intention by directly learning from the real-time action sequences. We conducted both offline and online experiments to validate the performance of the new model architecture, and also address the challenge of serving such a complex model using mixed CPU/GPU setup in production. The proposed system has been deployed in production at Pinterest and has delivered significant online gains across organic and Ads applications.
{"title":"Rethinking Personalized Ranking at Pinterest: An End-to-End Approach","authors":"Jiajing Xu, Andrew Zhai, Charles R. Rosenberg","doi":"10.1145/3523227.3547394","DOIUrl":"https://doi.org/10.1145/3523227.3547394","url":null,"abstract":"In this work, we present our journey to revolutionize the personalized recommendation engine through end-to-end learning from raw user actions. We encode user’s long-term interest in PinnerFormer, a user embedding optimized for long-term future actions via a new dense all-action loss, and capture user’s short-term intention by directly learning from the real-time action sequences. We conducted both offline and online experiments to validate the performance of the new model architecture, and also address the challenge of serving such a complex model using mixed CPU/GPU setup in production. The proposed system has been deployed in production at Pinterest and has delivered significant online gains across organic and Ads applications.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126109217","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}
Nick Landia, Frederick Cheung, Donna North, Saikishore Kalloori, Abhishek Srivastava, B. Ferwerda
The RecSys 2022 Challenge was a session-based recommendation task in the fashion domain. The dataset was supplied by Dressipi. Given session data consisting of views and purchases, as well as content data representing the fashion characteristics of the items, the task was to predict which item was purchased at the end of the session. The challenge ran for 3 months with a public leaderboard and final result on a separate hidden test set. There were over 300 teams that submitted a solution to the leaderboard and about 50 that submitted a solution for the final test set. The winning team achieved a MRR score of 0.216 which means that the correct target item was on average ranked 5th in the list of predictions. We identify some interesting common themes among the solutions in this paper and the winning approaches are presented in the workshop.
{"title":"RecSys Challenge 2022: Fashion Purchase Prediction","authors":"Nick Landia, Frederick Cheung, Donna North, Saikishore Kalloori, Abhishek Srivastava, B. Ferwerda","doi":"10.1145/3523227.3552534","DOIUrl":"https://doi.org/10.1145/3523227.3552534","url":null,"abstract":"The RecSys 2022 Challenge was a session-based recommendation task in the fashion domain. The dataset was supplied by Dressipi. Given session data consisting of views and purchases, as well as content data representing the fashion characteristics of the items, the task was to predict which item was purchased at the end of the session. The challenge ran for 3 months with a public leaderboard and final result on a separate hidden test set. There were over 300 teams that submitted a solution to the leaderboard and about 50 that submitted a solution for the final test set. The winning team achieved a MRR score of 0.216 which means that the correct target item was on average ranked 5th in the list of predictions. We identify some interesting common themes among the solutions in this paper and the winning approaches are presented in the workshop.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133875523","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：