João Vinagre, Marie Al-Ghossein, A. Jorge, A. Bifet, Ladislav Peška
Modern online systems for user modeling and recommendation need to continuously deal with complex data streams generated by users at very fast rates. This can be overwhelming for systems and algorithms designed to train recommendation models in batches, given the continuous and potentially fast change of content, context and user preferences or intents. Therefore, it is important to investigate methods able to transparently and continuously adapt to the inherent dynamics of user interactions, preferably for long periods of time. Online models that continuously learn from such flows of data are gaining attention in the recommender systems community, given their natural ability to deal with data generated in dynamic, complex environments. User modeling and personalization can particularly benefit from algorithms capable of maintaining models incrementally and online. The objective of this workshop is to foster contributions and bring together a growing community of researchers and practitioners interested in online, adaptive approaches to user modeling, recommendation and personalization, and their implications regarding multiple dimensions, such as evaluation, reproducibility, privacy, fairness and transparency.
{"title":"ORSUM 2022 - 5th Workshop on Online Recommender Systems and User Modeling","authors":"João Vinagre, Marie Al-Ghossein, A. Jorge, A. Bifet, Ladislav Peška","doi":"10.1145/3523227.3547411","DOIUrl":"https://doi.org/10.1145/3523227.3547411","url":null,"abstract":"Modern online systems for user modeling and recommendation need to continuously deal with complex data streams generated by users at very fast rates. This can be overwhelming for systems and algorithms designed to train recommendation models in batches, given the continuous and potentially fast change of content, context and user preferences or intents. Therefore, it is important to investigate methods able to transparently and continuously adapt to the inherent dynamics of user interactions, preferably for long periods of time. Online models that continuously learn from such flows of data are gaining attention in the recommender systems community, given their natural ability to deal with data generated in dynamic, complex environments. User modeling and personalization can particularly benefit from algorithms capable of maintaining models incrementally and online. The objective of this workshop is to foster contributions and bring together a growing community of researchers and practitioners interested in online, adaptive approaches to user modeling, recommendation and personalization, and their implications regarding multiple dimensions, such as evaluation, reproducibility, privacy, fairness and transparency.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"27 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":"115646280","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}
Typical recommender systems models are trained to have good average performance across all users or items. In practice, this results in model performance that is good for some users but sub-optimal for many users. In this work, we consider adversarially trained machine learning models and extend them to recommender systems problems. The adversarial models are trained with no additional demographic or other information than already available to the learning algorithm. We show that adversarially reweighted learning models give more emphasis to dense areas of the feature-space that incur high loss during training. We show that a straightforward adversarial model adapted to recommender systems can fail to perform well and that a carefully designed adversarial model can perform much better. The proposed models are trained using a standard gradient descent/ascent approach that can be easily adapted to many recommender problems. We compare our results with an inverse propensity weighting based baseline that also works well in practice. We delve deep into the underlying experimental results and show that, for the users who are under-served by the baseline model, the adversarial models can achieve significantly better results.
{"title":"Adversary or Friend? An adversarial Approach to Improving Recommender Systems","authors":"Pannagadatta K. Shivaswamy, Dario García-García","doi":"10.1145/3523227.3546784","DOIUrl":"https://doi.org/10.1145/3523227.3546784","url":null,"abstract":"Typical recommender systems models are trained to have good average performance across all users or items. In practice, this results in model performance that is good for some users but sub-optimal for many users. In this work, we consider adversarially trained machine learning models and extend them to recommender systems problems. The adversarial models are trained with no additional demographic or other information than already available to the learning algorithm. We show that adversarially reweighted learning models give more emphasis to dense areas of the feature-space that incur high loss during training. We show that a straightforward adversarial model adapted to recommender systems can fail to perform well and that a carefully designed adversarial model can perform much better. The proposed models are trained using a standard gradient descent/ascent approach that can be easily adapted to many recommender problems. We compare our results with an inverse propensity weighting based baseline that also works well in practice. We delve deep into the underlying experimental results and show that, for the users who are under-served by the baseline model, the adversarial models can achieve significantly better results.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"28 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":"114795285","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}
Toine Bogers, David Graus, Mesut Kaya, Francisco Gutiérrez, S. Mesbah, Chris Johnson
Citation for published version (APA): Bogers, T., Graus, D., Kaya, M., Gutiérrez, F., Mesbah, S., & Johnson, C. (2022). Second Workshop on Recommender Systems for Human Resources (RecSys in HR 2022). In RecSys 2022 Proceedings of the 16th ACM Conference on Recommender Systems (pp. 671-674). Association for Computing Machinery. RecSys 2022 Proceedings of the 16th ACM Conference on Recommender Systems https://doi.org/10.1145/3523227.3547414
{"title":"Second Workshop on Recommender Systems for Human Resources (RecSys in HR 2022)","authors":"Toine Bogers, David Graus, Mesut Kaya, Francisco Gutiérrez, S. Mesbah, Chris Johnson","doi":"10.1145/3523227.3547414","DOIUrl":"https://doi.org/10.1145/3523227.3547414","url":null,"abstract":"Citation for published version (APA): Bogers, T., Graus, D., Kaya, M., Gutiérrez, F., Mesbah, S., & Johnson, C. (2022). Second Workshop on Recommender Systems for Human Resources (RecSys in HR 2022). In RecSys 2022 Proceedings of the 16th ACM Conference on Recommender Systems (pp. 671-674). Association for Computing Machinery. RecSys 2022 Proceedings of the 16th ACM Conference on Recommender Systems https://doi.org/10.1145/3523227.3547414","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"1 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":"127413562","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}
Evaluation of recommender systems is a central activity when developing recommender systems, both in industry and academia. The second edition of the PERSPECTIVES workshop held at RecSys 2022 brought together academia and industry to critically reflect on the evaluation of recommender systems. In the 2022 edition of PERSPECTIVES, we discussed problems and lessons learned, encouraged the exchange of the various perspectives on evaluation, and aimed to move the discourse forward within the community. We deliberately solicited papers reporting a reflection on problems regarding recommender systems evaluation and lessons learned. The workshop featured interactive parts with discussions in small groups as well as in the plenum, both on-site and online, and an industry keynote.
{"title":"Second Workshop: Perspectives on the Evaluation of Recommender Systems (PERSPECTIVES 2022)","authors":"Eva Zangerle, Christine Bauer, A. Said","doi":"10.1145/3523227.3547408","DOIUrl":"https://doi.org/10.1145/3523227.3547408","url":null,"abstract":"Evaluation of recommender systems is a central activity when developing recommender systems, both in industry and academia. The second edition of the PERSPECTIVES workshop held at RecSys 2022 brought together academia and industry to critically reflect on the evaluation of recommender systems. In the 2022 edition of PERSPECTIVES, we discussed problems and lessons learned, encouraged the exchange of the various perspectives on evaluation, and aimed to move the discourse forward within the community. We deliberately solicited papers reporting a reflection on problems regarding recommender systems evaluation and lessons learned. The workshop featured interactive parts with discussions in small groups as well as in the plenum, both on-site and online, and an industry keynote.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"78 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":"126964103","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}
Lin Ning, Steve Chien, Shuang Song, Mei Chen, Yunqi Xue, D. Berlowitz
Embedding-based deep neural networks (DNNs) are widely used in large-scale recommendation systems. Differentially-private stochastic gradient descent (DP-SGD) provides a way to enable personalized experiences while preserving user privacy by injecting noise into every model parameter during the training process. However, it is challenging to apply DP-SGD to large-scale embedding-based DNNs due to its effect on training speed. This happens because the noise added by DP-SGD causes normally sparse gradients to become dense, introducing a large communication overhead between workers and parameter servers in a typical distributed training framework. This paper proposes embedding-aware noise addition (EANA) to mitigate the communication overhead, making training a large-scale embedding-based DNN possible. We examine the privacy benefit of EANA both analytically and empirically using secret sharer techniques. We demonstrate that training with EANA can achieve reasonable model precision while providing good practical privacy protection as measured by the secret sharer tests. Experiments on a real-world, large-scale dataset and model show that EANA is much faster than standard DP-SGD, improving the training speed by 54X and unblocking the training of a large-scale embedding-based DNN with reduced privacy risk.
{"title":"EANA: Reducing Privacy Risk on Large-scale Recommendation Models","authors":"Lin Ning, Steve Chien, Shuang Song, Mei Chen, Yunqi Xue, D. Berlowitz","doi":"10.1145/3523227.3546769","DOIUrl":"https://doi.org/10.1145/3523227.3546769","url":null,"abstract":"Embedding-based deep neural networks (DNNs) are widely used in large-scale recommendation systems. Differentially-private stochastic gradient descent (DP-SGD) provides a way to enable personalized experiences while preserving user privacy by injecting noise into every model parameter during the training process. However, it is challenging to apply DP-SGD to large-scale embedding-based DNNs due to its effect on training speed. This happens because the noise added by DP-SGD causes normally sparse gradients to become dense, introducing a large communication overhead between workers and parameter servers in a typical distributed training framework. This paper proposes embedding-aware noise addition (EANA) to mitigate the communication overhead, making training a large-scale embedding-based DNN possible. We examine the privacy benefit of EANA both analytically and empirically using secret sharer techniques. We demonstrate that training with EANA can achieve reasonable model precision while providing good practical privacy protection as measured by the secret sharer tests. Experiments on a real-world, large-scale dataset and model show that EANA is much faster than standard DP-SGD, improving the training speed by 54X and unblocking the training of a large-scale embedding-based DNN with reduced privacy risk.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"1 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":"125833117","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}
Deep Reinforcement Learning (DRL) uses the best of both Reinforcement Learning and Deep Learning for solving problems which cannot be addressed by them individually. Deep Reinforcement Learning has been used widely for games, robotics etc. Limited work has been done for applying DRL for Conversational Recommender System (CRS). Hence, this tutorial covers the application of DRL for CRS. We give conceptual introduction to Reinforcement Learning and Deep Reinforcement Learning and cover Deep Q-Network, Dyna, REINFORCE and Actor Critic methods. We then cover various real life case studies with increasing complexity starting from CRS, deep CRS, adaptivity, topic guided CRS, deep and large-scale CRSs. We plan to share pre-read for Reinforcement Learning and Deep Reinforcement learning so that participants can grasp the material well.
{"title":"Conversational Recommender System Using Deep Reinforcement Learning","authors":"Omprakash Sonie","doi":"10.1145/3523227.3547376","DOIUrl":"https://doi.org/10.1145/3523227.3547376","url":null,"abstract":"Deep Reinforcement Learning (DRL) uses the best of both Reinforcement Learning and Deep Learning for solving problems which cannot be addressed by them individually. Deep Reinforcement Learning has been used widely for games, robotics etc. Limited work has been done for applying DRL for Conversational Recommender System (CRS). Hence, this tutorial covers the application of DRL for CRS. We give conceptual introduction to Reinforcement Learning and Deep Reinforcement Learning and cover Deep Q-Network, Dyna, REINFORCE and Actor Critic methods. We then cover various real life case studies with increasing complexity starting from CRS, deep CRS, adaptivity, topic guided CRS, deep and large-scale CRSs. We plan to share pre-read for Reinforcement Learning and Deep Reinforcement learning so that participants can grasp the material well.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"29 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":"126328218","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}
Repetition in music consumption is a common phenomenon. It is notably more frequent when compared to the consumption of other media, such as books and movies. In this paper, we show that one particularly interesting repetitive behavior arises when users are consuming new items. Users’ interest tends to rise with the first repetitions and attains a peak after which interest will decrease with subsequent exposures, resulting in an inverted-U shape. This behavior, which has been extensively studied in psychology, is called the mere exposure effect. In this paper, we show how a number of factors, both content and user-based, well documented in the literature on the mere exposure effect, modulate the magnitude of the effect. Due to the vast availability of data of users discovering new songs everyday in music streaming platforms, this findings enable new ways to characterize both the music, users and their relationships. Ultimately, it opens up the possibility of developing new recommender systems paradigms based on these characterizations.
{"title":"Discovery Dynamics: Leveraging Repeated Exposure for User and Music Characterization","authors":"B. Sguerra, Viet-Anh Tran, Romain Hennequin","doi":"10.1145/3523227.3551474","DOIUrl":"https://doi.org/10.1145/3523227.3551474","url":null,"abstract":"Repetition in music consumption is a common phenomenon. It is notably more frequent when compared to the consumption of other media, such as books and movies. In this paper, we show that one particularly interesting repetitive behavior arises when users are consuming new items. Users’ interest tends to rise with the first repetitions and attains a peak after which interest will decrease with subsequent exposures, resulting in an inverted-U shape. This behavior, which has been extensively studied in psychology, is called the mere exposure effect. In this paper, we show how a number of factors, both content and user-based, well documented in the literature on the mere exposure effect, modulate the magnitude of the effect. Due to the vast availability of data of users discovering new songs everyday in music streaming platforms, this findings enable new ways to characterize both the music, users and their relationships. Ultimately, it opens up the possibility of developing new recommender systems paradigms based on these characterizations.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"1 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":"131007712","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}
J. Neidhardt, W. Wörndl, T. Kuflik, Dmitri Goldenberg, M. Zanker
The Workshop on Recommenders in Tourism (RecTour) 2022, which is held in conjunction with the 16th ACM Conference on Recommender Systems (RecSys), addresses specific challenges for recommender systems in the tourism domain. In this overview paper, we summarize our motivations to organize the RecTour workshop and present the main topic areas of RecTour submissions. These include context-aware recommendations, group recommender systems, recommending composite items, decision making and user interaction issues, different information sources and various application scenarios.
{"title":"Workshop on Recommenders in Tourism (RecTour)","authors":"J. Neidhardt, W. Wörndl, T. Kuflik, Dmitri Goldenberg, M. Zanker","doi":"10.1145/3523227.3547416","DOIUrl":"https://doi.org/10.1145/3523227.3547416","url":null,"abstract":"The Workshop on Recommenders in Tourism (RecTour) 2022, which is held in conjunction with the 16th ACM Conference on Recommender Systems (RecSys), addresses specific challenges for recommender systems in the tourism domain. In this overview paper, we summarize our motivations to organize the RecTour workshop and present the main topic areas of RecTour submissions. These include context-aware recommendations, group recommender systems, recommending composite items, decision making and user interaction issues, different information sources and various application scenarios.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"31 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":"134153496","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}
Movielens dataset has become a default choice for recommender systems evaluation. In this paper we analyze the best strategies of a Reinforcement Learning agent on Movielens (1M) dataset studying the balance between precision and diversity of recommendations. We found that trivial strategies are able to maximize ranking quality criteria, but useless for users of the recommendation system due to the lack of diversity in final predictions. Our proposed method stimulates the agent to explore the environment using the stochasticity of Ornstein-Uhlenbeck processes. Experiments show that optimization of the Ornstein-Uhlenbeck process drift coefficient improves the diversity of recommendations while maintaining high nDCG and HR criteria. To the best of our knowledge, the analysis of agent strategies in recommendation environments has not been studied excessively in previous works.
{"title":"Multiobjective Evaluation of Reinforcement Learning Based Recommender Systems","authors":"A. Grishanov, A. Ianina, K. Vorontsov","doi":"10.1145/3523227.3551485","DOIUrl":"https://doi.org/10.1145/3523227.3551485","url":null,"abstract":"Movielens dataset has become a default choice for recommender systems evaluation. In this paper we analyze the best strategies of a Reinforcement Learning agent on Movielens (1M) dataset studying the balance between precision and diversity of recommendations. We found that trivial strategies are able to maximize ranking quality criteria, but useless for users of the recommendation system due to the lack of diversity in final predictions. Our proposed method stimulates the agent to explore the environment using the stochasticity of Ornstein-Uhlenbeck processes. Experiments show that optimization of the Ornstein-Uhlenbeck process drift coefficient improves the diversity of recommendations while maintaining high nDCG and HR criteria. To the best of our knowledge, the analysis of agent strategies in recommendation environments has not been studied excessively in previous works.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"47 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":"132689968","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}
Huiyuan Chen, Yusan Lin, Menghai Pan, Lan Wang, Chin-Chia Michael Yeh, Xiaoting Li, Yan Zheng, Fei Wang, Hao Yang
Transformer-based sequential recommenders are very powerful for capturing both short-term and long-term sequential item dependencies. This is mainly attributed to their unique self-attention networks to exploit pairwise item-item interactions within the sequence. However, real-world item sequences are often noisy, which is particularly true for implicit feedback. For example, a large portion of clicks do not align well with user preferences, and many products end up with negative reviews or being returned. As such, the current user action only depends on a subset of items, not on the entire sequences. Many existing Transformer-based models use full attention distributions, which inevitably assign certain credits to irrelevant items. This may lead to sub-optimal performance if Transformers are not regularized properly. Here we propose the Rec-denoiser model for better training of self-attentive recommender systems. In Rec-denoiser, we aim to adaptively prune noisy items that are unrelated to the next item prediction. To achieve this, we simply attach each self-attention layer with a trainable binary mask to prune noisy attentions, resulting in sparse and clean attention distributions. This largely purifies item-item dependencies and provides better model interpretability. In addition, the self-attention network is typically not Lipschitz continuous and is vulnerable to small perturbations. Jacobian regularization is further applied to the Transformer blocks to improve the robustness of Transformers for noisy sequences. Our Rec-denoiser is a general plugin that is compatible to many Transformers. Quantitative results on real-world datasets show that our Rec-denoiser outperforms the state-of-the-art baselines.
{"title":"Denoising Self-Attentive Sequential Recommendation","authors":"Huiyuan Chen, Yusan Lin, Menghai Pan, Lan Wang, Chin-Chia Michael Yeh, Xiaoting Li, Yan Zheng, Fei Wang, Hao Yang","doi":"10.1145/3523227.3546788","DOIUrl":"https://doi.org/10.1145/3523227.3546788","url":null,"abstract":"Transformer-based sequential recommenders are very powerful for capturing both short-term and long-term sequential item dependencies. This is mainly attributed to their unique self-attention networks to exploit pairwise item-item interactions within the sequence. However, real-world item sequences are often noisy, which is particularly true for implicit feedback. For example, a large portion of clicks do not align well with user preferences, and many products end up with negative reviews or being returned. As such, the current user action only depends on a subset of items, not on the entire sequences. Many existing Transformer-based models use full attention distributions, which inevitably assign certain credits to irrelevant items. This may lead to sub-optimal performance if Transformers are not regularized properly. Here we propose the Rec-denoiser model for better training of self-attentive recommender systems. In Rec-denoiser, we aim to adaptively prune noisy items that are unrelated to the next item prediction. To achieve this, we simply attach each self-attention layer with a trainable binary mask to prune noisy attentions, resulting in sparse and clean attention distributions. This largely purifies item-item dependencies and provides better model interpretability. In addition, the self-attention network is typically not Lipschitz continuous and is vulnerable to small perturbations. Jacobian regularization is further applied to the Transformer blocks to improve the robustness of Transformers for noisy sequences. Our Rec-denoiser is a general plugin that is compatible to many Transformers. Quantitative results on real-world datasets show that our Rec-denoiser outperforms the state-of-the-art baselines.","PeriodicalId":443279,"journal":{"name":"Proceedings of the 16th ACM Conference on Recommender Systems","volume":"33 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":"114559793","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：