{"type":"ScholarlyArticle","title":"Feature Staleness Aware Incremental Learning for CTR Prediction","authors":[{"name":"Zhikai Wang","slug":"zhikai-wang","given":"Zhikai","family":"Wang","affiliation":"Department of Computer Science and Engineering , Shanghai Jiao Tong University"},{"name":"Yanyan Shen","slug":"yanyan-shen","given":"Yanyan","family":"Shen","affiliation":"Department of Computer Science and Engineering , Shanghai Jiao Tong University"},{"name":"Zibin Zhang","slug":"zibin-zhang","given":"Zibin","family":"Zhang","affiliation":"Tencent"},{"name":"Kangyi Lin","slug":"kangyi-lin","given":"Kangyi","family":"Lin","affiliation":"Tencent"}],"abstract":"Click-through Rate (CTR) prediction in real-world recommender systems often deals with billions of user interactions every day. To improve the training efficiency, it is common to update the CTR prediction model incrementally using the new incremental data and a subset of historical data. However, the feature embeddings of a CTR prediction model often get stale when the corresponding features do not appear in current incremental data. In the next period, the model would have a performance degradation on samples containing stale features, which we call the feature staleness problem. To mitigate this problem, we propose a Feature Staleness Aware Incremental Learning method for CTR prediction (FeSAIL) which adaptively replays samples containing stale features. We first introduce a staleness-aware sampling algorithm (SAS) to sample a fixed number of stale samples with high sampling efficiency. We then introduce a staleness-aware regularization mechanism (SAR) for a fine-grained control of the feature embedding updating. We instantiate FeSAIL with a general deep learning-based CTR prediction model and the experimental results demonstrate FeSAIL outperforms various state-of-the-art methods on four benchmark datasets. The code can be found in https://github.com/cloudcatcher888/FeSAIL.","doi":"10.24963/ijcai.2023/261","url":"https://ijcai.org/proceedings/2023/261","pdf":"https://ijcai.org/proceedings/2023/0261.pdf","markdown":"https://ijcai.org/proceedings/2023/261.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/261","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Data Mining","track":"Main Track","number":261,"pages":{"first":2352,"last":2360},"keywords":["Data Mining: DM: Recommender systems","Machine Learning: ML: Incremental learning"],"videos":[],"references":[{"position":1,"raw":"[Barrett et al., 2017] Rick Barrett, Rick Cummings, and Eu- gene Agichtein. Streaming Recommender Systems. In IJCAI, pages 381-389, 2017.","title":"Rick Barrett, Rick Cummings, and Eugene Agichtein. Streaming Recommender Systems","authors":"Barrett","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Caverlee et al., 2020] James Caverlee, Xia \"Ben\" Hu, Mou- nia Lalmas, Wei Wang, Jiacheng Li, Yujie Wang, and Ju- lian McAuley. Time Interval Aware Self-Attention for Sequential Recommendation. In WSDM, pages 322-330, 2020.","title":"Time Interval Aware Self-Attention for Sequential Recommendation","authors":"James Caverlee, \" Xia, \" Ben, Mounia Hu, Wei Lalmas, Jiacheng Wang, Yujie Li, Julian Wang, Mcauley","year":"2020","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chekuri and Kumar, 2004] Chandra Chekuri and Amit Ku- mar. Maximum coverage problem with group budget con- straints and applications. In Approximation, Random- ization, and Combinatorial Optimization. Algorithms and Techniques, pages 72-83. Springer, 2004.","title":"Chandra Chekuri and Amit Kumar. Maximum coverage problem with group budget constraints and applications","authors":"Kumar Chekuri","year":"2004","venue":"Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2013] Chen Chen, Hongzhi Yin, Junjie Yao, and Bin Cui. TeRec: a temporal recommender system over tweet stream. In RecSys, volume 6, pages 1254-1257, 2013.","title":"TeRec: a temporal recommender system over tweet stream","authors":"Chen Chen, Hongzhi Yin, Junjie Yao, Bin Cui","year":"2013","venue":"RecSys","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cheng et al., 2020] Weiyu Cheng, Yanyan Shen, and Lin- peng Huang. Adaptive factorization network: Learning adaptive-order feature interactions. In AAAI, volume 34, pages 3609-3616, 2020.","title":"Adaptive factorization network: Learning adaptive-order feature interactions","authors":"Weiyu Cheng, Yanyan Shen, Linpeng Huang","year":"2020","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"['Aquin et al., 2020] Mathieu d'Aquin, Stefan Dietze, Claudia Hauff, Edward Curry, Philippe Cudre Mauroux, Xiang Li, Chao Wang, Bin Tong, Jiwei Tan, Xiaoyi Zeng, and Tao Zhuang. Deep Time-Aware Item Evolution Net- work for Click-Through Rate Prediction. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pages 785-794, 2020.","title":"Deep Time-Aware Item Evolution Network for Click-Through Rate Prediction","authors":"Aquin","year":"2020","venue":"Proceedings of the 29th ACM International Conference on Information & Knowledge Management","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Diaz-Aviles et al., 2012] Ernesto Diaz-Aviles, Lucas Dru- mond, Lars Schmidt-Thieme, and Wolfgang Nejdl. Real- time top-n recommendation in social streams. In WWW, pages 59-66. 2012.","title":"Realtime top-n recommendation in social streams","authors":"Ernesto Diaz-Aviles, Lucas Drumond, Lars Schmidt-Thieme, Wolfgang Nejdl","year":"2012","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Diederik P. Kingma, 2015] Jimmy Lei Ba Diederik P. Kingma. Adam: A Method for Stochastic Optimization. In ICLR, pages 785-794, 2015.","title":"Adam: A Method for Stochastic Optimization","authors":"P Diederik, Jimmy Kingma, Ba Lei, P Diederik, Kingma","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Guo et al., 2017] Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, and Xiuqiang He. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction. In IJCAI, pages 1725-1731, 2017.","title":"DeepFM: A Factorization-Machine based Neural Network for CTR Prediction","authors":"Guo","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/239"},{"position":10,"raw":"[Guo et al., 2018] Yike Guo, Faisal Farooq, Guorui Zhou, Xiaoqiang Zhu, Chenru Song, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, and Kun Gai. Deep Interest Network for Click-Through Rate Prediction. In AAAI, pages 1059-1068, 2018.","title":"Deep Interest Network for Click-Through Rate Prediction","authors":"Yike Guo, Faisal Farooq, Guorui Zhou, Xiaoqiang Zhu, Chenru Song, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, Kun Gai","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[He and McAuley, 2016] Ruining He and Julian McAuley. Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation. ICDM, pages 191-200, 2016.","title":"Ruining He and Julian McAuley. Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation","authors":"Mcauley He","year":"2016","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Huang et al., 2020a] Jimmy Huang, Yi Chang, and Xueqi Cheng. How to Retrain Recommender System? A Se- quential Meta-Learning Method. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 1479- 1488, 2020.","title":"How to Retrain Recommender System? A Sequential Meta-Learning Method","authors":"Huang","year":"2020","venue":"Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Huang et al., 2020b] Jimmy Huang, Yi Chang, and Xueqi and Cheng. GAG: Global Attributed Graph Neural Network for Streaming Session-based Recommendation. In SIGIR, pages 669-678, 2020.","title":"GAG: Global Attributed Graph Neural Network for Streaming Session-based Recommendation","authors":"Huang","year":"2020","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kang and McAuley, 2018] Wang-Cheng Kang and Julian McAuley. Self-Attentive Sequential Recommendation. In ICDM, pages 197-206, 2018.","title":"Self-Attentive Sequential Recommendation","authors":"Wang-Cheng Kang, Julian Mcauley","year":"2018","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kirkpatrick et al., 2016] James Kirkpatrick, Razvan Pas- canu, Neil Rabinowitz, Joel Veness, Guillaume Des- jardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hass- abis, Claudia Clopath, Dharshan Kumaran, and Raia Had- sell. Overcoming catastrophic forgetting in neural net- works. ICDM, pages 229-338, 2016.","title":"Overcoming catastrophic forgetting in neural networks","authors":"James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, Raia Hadsell","year":"2016","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Krishnapuram et al., 2016] Balaji Krishnapuram, Mohak Shah, and JC Mao. Deep Crossing: Web-Scale Model- ing without Manually Crafted Combinatorial Features. In KDD, pages 255-262, 2016.","title":"Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features","authors":"Balaji Krishnapuram, Mohak Shah, J C Mao","year":"2016","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lim et al., 2017] Ee-Peng Lim, Marianne Winslett, Mark Sanderson, Ada Fu, Jimeng Sun, and Shane Culpepper. Neural Attentive Session-based Recommendation. CIKM, pages 1419-1428, 2017.","title":"Neural Attentive Session-based Recommendation","authors":"Ee-Peng Lim, Marianne Winslett, Mark Sanderson, Ada Fu, Jimeng Sun, Shane Culpepper","year":"2017","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Mi and Faltings, 2020] Fei Mi and Boi Faltings. Memory Augmented Neural Model for Incremental Session-based Recommendation. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, pages 2169-2176, 2020.","title":"Memory Augmented Neural Model for Incremental Session-based Recommendation","authors":"Mi, Faltings ;, Fei Mi, Boi Faltings","year":"2020","venue":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2020/300"},{"position":19,"raw":"[Mi et al., 2020] Fei Mi, Xiaoyu Lin, and Boi Faltings. ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation. Recsys, pages 391-402, 2020.","title":"ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation","authors":"Fei Mi, Xiaoyu Lin, Boi Faltings","year":"2020","venue":"Recsys","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Peng et al., 2021] Danni Peng, Sinno Jialin Pan, Jie Zhang, and Anxiang Zeng. Learning an Adaptive Meta Model- Generator for Incrementally Updating Recommender Sys- tems. In SIGIR, pages 411-421, 2021.","title":"Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems","authors":"Danni Peng, Sinno Jialin Pan, Jie Zhang, Anxiang Zeng","year":"2021","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Qu et al., 2016] Yanru Qu, Han Cai, Kan Ren, Weinan Zhang, Yong Yu, Ying Wen, and Jun Wang. Product- based neural networks for user response prediction. In 2016 IEEE 16th International Conference on Data Min- ing (ICDM), pages 1149-1154. IEEE, 2016.","title":"Productbased neural networks for user response prediction","authors":"Qu","year":"2016","venue":"IEEE 16th International Conference on Data Mining (ICDM)","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rendle et al., 2010] Steffen Rendle, Christoph Freuden- thaler, and Lars Schmidt-Thieme. Factorizing person- alized Markov chains for next-basket recommendation. WWW, pages 811-820, 2010.","title":"Factorizing personalized Markov chains for next-basket recommendation","authors":"Steffen Rendle, Christoph Freudenthaler, Lars Schmidt-Thieme","year":"2010","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sun et al., 2019] Fei Sun, Jun Liu, Jian Wu, Changhua Pei, Xiao Lin, Wenwu Ou, and Peng Jiang. BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer. In Proceedings of the 28th ACM International Conference on Information & Knowledge Management, 2019.","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","authors":"Fei Sun, Jun Liu, Jian Wu, Changhua Pei, Xiao Lin, Wenwu Ou, Peng Jiang","year":"2019","venue":"Proceedings of the 28th ACM International Conference on Information & Knowledge Management","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Sun et al., 2022] Li Sun, Junda Ye, Hao Peng, Feiyang Wang, and Philip S Yu. Self-supervised continual graph learning in adaptive riemannian spaces. In IJCAI, 2022.","title":"Self-supervised continual graph learning in adaptive riemannian spaces","authors":"Li Sun, Junda Ye, Hao Peng, Feiyang Wang, Philip S Yu","year":"2022","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Teredesai et al., 2019] Ankur Teredesai, Vipin Kumar, and Ying Li. Streaming Session-based Recommendation. In IJCAI, pages 1569-1577, 2019.","title":"Streaming Session-based Recommendation","authors":"Ankur Teredesai, Vipin Kumar, Ying Li","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang et al., 2017] Ruoxi Wang, Bin Fu, Gang Fu, and Min- gliang Wang. Deep & Cross Network for Ad Click Predic- tions. In ADKDD, pages 1-7, 2017.","title":"Deep & Cross Network for Ad Click Predictions","authors":"Wang","year":"2017","venue":"ADKDD","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang et al., 2020] Yichao Wang, Huifeng Guo, Ruiming Tang, Zhirong Liu, and Xiuqiang He. A Practical Incre- mental Method to Train Deep CTR Models. KDD, pages 582-589, 2020.","title":"A Practical Incremental Method to Train Deep CTR Models","authors":"Wang","year":"2020","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2014] Weinan Zhang, Shuai Yuan, Jun Wang, and Xuehua Shen. Real-Time Bidding Benchmarking with iPinYou Dataset. WSDM, pages 121-132, 2014.","title":"Real-Time Bidding Benchmarking with iPinYou Dataset","authors":"Weinan Zhang, Shuai Yuan, Jun Wang, Xuehua Shen","year":"2014","venue":"WSDM","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhikai and Yanyan, 2022] Wang Zhikai and Shen Yanyan. Time-aware multi-interest capsule network for sequential recommendation. In SDM, pages 558-566, 2022.","title":"Time-aware multi-interest capsule network for sequential recommendation","authors":"Wang Zhikai, Shen Yanyan","year":"2022","venue":"SDM","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhikai and Yanyan, 2023] Wang Zhikai and Shen Yanyan. Incremental learning for multi-interest sequential recom- mendation. In ICDE, 2023.","title":"Incremental learning for multi-interest sequential recommendation","authors":"Wang Zhikai, Shen Yanyan","year":"2023","venue":"ICDE","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhou et al., 2018] Guorui Zhou, Na Mou, Ying Fan, Qi Pi, Weijie Bian, Chang Zhou, Xiaoqiang Zhu, and Kun Gai. Deep Interest Evolution Network for Click-Through Rate Prediction. In AAAI, pages 5941-5948, 2018.","title":"Deep Interest Evolution Network for Click-Through Rate Prediction","authors":"Guorui Zhou, Na Mou, Ying Fan, Qi Pi, Weijie Bian, Chang Zhou, Xiaoqiang Zhu, Kun Gai","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhu et al., 2019] Wenwu Zhu, Dacheng Tao, Xueqi Cheng, Peng Cui, Elke Rundensteiner, David Carmel, Qi He, Jef- frey Xu Yu, Zekun Li, Zeyu Cui, Shu Wu, Xiaoyu Zhang, and Liang Wang. Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction. Proceed- ings of the 28th ACM International Conference on Infor- mation and Knowledge Management, pages 539-548, 11 2019.","title":"Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction","authors":"Wenwu Zhu, Dacheng Tao, Xueqi Cheng, Peng Cui, Elke Rundensteiner, David Carmel, Qi He, Jeffrey Xu Yu, Zekun Li, Zeyu Cui, Shu Wu, Xiaoyu Zhang, Liang Wang","year":"2019","venue":"Proceedings of the 28th ACM International Conference on Information and Knowledge Management","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}