Time-Aware-Recommender-Systems Paper List

A summary of must-read papers for Time-aware Recommender Systems.

• Contributed by Hengchang Hu

Please follow this link to view papers in chronological order.

Content

1. Survey
2. Models
2.1 Basic Models	2.2 CNN-based Models
2.3 RNN-based Models	2.4 GNN-based Models
2.5 Reinforcement Learning	2.6 Contrastive Learning
2.5 Adversarial Learning	2.6 Meta Learning
2. Tasks
2.1 Collaborative Filtering	2.2 Sequential/Session-based Recommendations
2.3 CTR/CVR Prediction	2.4 Knowledge-aware Recommendations
2.5 Conversational Recommender System	2.6 POI Recommendation
2.7 News Recommendation	2.8 Explainable Recommendation
2.9 Privacy & Security	2.10 Debias & Fairness
3. Temporal Aspects in User Modeling
3.1 Temporal Popularity	3.2 Temporal Periodicality
3.3 Recency	3.4 Time-Point Sensitivity
3.5 Temporal Features
4. Resources

Survey papers

1. Sequence-aware recommender systems. ACM Computing Surveys (CSUR), 2018.

2. Considering Temporal Aspects in Recommender Systems: A Survey. UMUAI, 2022. paper

   Veronika Bogina, Tsvi Kuflik, Dietmar Jannach, Maria Bielikova, Michal Kompan, Christoph Trattner

3. Review of the Temporal Recommendation System with Matrix Factorization. ICIC, 2017. paper

   IAAQ Al-Hadi, NM Sharef, MN Sulaiman, N Mustapha

4. A Survey on Session-based Recommender System. arxiv, 2021. paper

Models

Basic Models

Basic models including two-tower models, and classical machine learning approaches.

1. Time Weight Collaborative Filtering. CIKM, 2005. paper

   Yi Ding, Xue Li

2. Temporal collaborative filtering with bayesian probabilistic tensor factorization. SIAM, 2010. paper

   Liang Xiong, Xi Chen, Tzu-Kuo Huang, Jeff Schneider, Jaime G. Carbonell

   ​

CNN-based Models

RNN-based Models

1. Learn from Past, Evolve for Future: Search-based Time-aware Recommendation with Sequential Behavior Data. WWW 2022. paper

   Jiarui Jin, Xianyu Chen, Weinan Zhang, Junjie Huang, Ziming Feng, Yong Yu

Transformer-based Models

1. RESETBERT4Rec: A Pre-training Model Integrating Time And User Historical Behavior for Sequential Recommendation. SIGIR 2022. paper

   Qihang Zhao

GNN-based Models

1. Spatiotemporal-aware Session-based Recommendation with Graph Neural Networks. CIKM 2022. paper

   Yinfeng Li, Chen Gao, Xiaoyi Du, Huazhou Wei, Hengliang Luo, Depeng Jin, Yong Li

Tasks

Sequential/Session-based Recommendations

1. Time Lag Aware Sequential Recommendation. CIKM 2022. paper

   Lihua Chen, Ning Yang, Philip S Yu

2. RESETBERT4Rec: A Pre-training Model Integrating Time And User Historical Behavior for Sequential Recommendation. SIGIR 2022. paper

   Qihang Zhao

3. Learn from Past, Evolve for Future: Search-based Time-aware Recommendation with Sequential Behavior Data. WWW 2022. paper

   Jiarui Jin, Xianyu Chen, Weinan Zhang, Junjie Huang, Ziming Feng, Yong Yu

4. Temporal Contrastive Pre-Training for Sequential Recommendation. CIKM 2022. paper

   Changxin Tian, Zihan Lin, Shuqing Bian, Jinpeng Wang, Wayne Xin Zhao

POI Recommendations

1. Spatiotemporal-aware Session-based Recommendation with Graph Neural Networks. CIKM 2022. paper

   Yinfeng Li, Chen Gao, Xiaoyi Du, Huazhou Wei, Hengliang Luo, Depeng Jin, Yong Li

2. Recommendation in Offline Stores: A Gamification Approach for Learning the Spatiotemporal Representation of Indoor Shopping. KDD 2022. paper

   Jongkyung Shin, Changhun Lee, Chiehyeon Lim, Yunmo Shin, Junseok Lim

Temporal-Aspect

Temporal Popularity & Trendiness

1. Personalized News Recommendation with Context Trees. RecSys, 2013. paper

   Florent Garcin, Christos Dimitrakakis, Boi Faltings

2. Learning item temporal dynamics for predicting buying sessions. IUI, 2016. paper

   Veronika Bogina, Tsvi Kuflik, Osnat Mokryn

3. Collaborative Filtering with Temporal Dynamics. KDD, 2009. paper

   Yehuda Koren

4. Incorporating context and trends in news recommender systems. WI, 2017. paper

A Lommatzsch, B Kille, S Albayrak

5. Session-based item recommendation in e-commerce: on short-term intents, reminders, trends and discounts. User Model. User-Adapt. Interact., 2017. paper

   Dietmar Jannach, Malte Ludewig & Lukas Lerche

Temporal Periodicality

这里面包括repetely consumption，which关注于用户重复地做某项事情，buy the same things repeatedly

区别于temporal frequency，这里指的是关注于有规律的重复， people have regular habits， 比如we eat at the same restaurants regularly

1. Itinerary recommender system with semantic trajectory pattern mining from geo-tagged photos. Expert Syst. Appl., 2017. paper

   Guochen Cai, Kyungmi Lee, Ickjai Lee

2. News session-based recommendations using deep neural networks. DLRS, 2018. paper

   Gabriel de Souza Pereira, Felipe Ferreira, Adilson Marques da Cunha

3. The Intricacies of Time in News Recommendation. UMAP, 2016. paper

   Jon Atle Gulla, Arne Dag Fidjestøl, Jon Espen Ingvaldsen, Cristina Marco, Xiaomeng Su, Özlem Özgöbek

4. Ctrec: a longshort demands evolution model for continuous-time recommendation. SIGIR, 2019. paper

   Ting Bai, Lixin Zou, Wayne Xin Zhao, Pan DuWeidong Liu, Jian-Yun Nie, Ji-Rong Wen

5. Modeling user consumption sequences. WWW, 2016. paper

   Austin R. Benson, Ravi Kumar, Andrew Tomkins

6. RepeatNet: A Repeat Aware Neural Recommendation Machine for Session-based Recommendation. AAAI, 2019. paper

   Pengjie Ren, Zhumin Chen, Jing Li, Zhaochun Ren, Jun Ma, Maarten de Rijk

7. Modeling Personalized Item Frequency Information for Next-basket Recommendation. SIGIR, 2020. paper

   Haoji Hu, Xiangnan He, Jinyang Gao, Zhi-Li Zhang

Temporal Recency

The recency of tags has a positive effect on their recurrence probability. (To Replace)

1. Models of user engagement. UMAP, 2012. paper

   Janette Lehmann, Mounia Lalmas, Elad Yom-Tov, Georges Dupret

2. Sequence and time aware neighborhood for session-based recommendations: Stan. SIGIR, 2019. paper

   Diksha Garg, Priyanka Gupta, Pankaj Malhotra, Lovekesh Vig, Gautam Shroff

3. Time Interval Aware Self-Attention for Sequential Recommendation. WSDM, 2020. paper

   Jiacheng Li, Yujie Wang, Julian McAuley

4. On the Decaying Utility of News Recommendation Models. RecTemp@ RecSys, 2017. paper

   Benjamin Kille, Sahin Albayrak

5. Recency Aware Collaborative Filtering for Next Basket Recommendation. UMAP, 2020. paper

   *Guglielmo Faggioli, Mirko Polato, Fabio Aioll

6. Time Lag Aware Sequential Recommendation. CIKM 2022. paper

   Lihua Chen, Ning Yang, Philip S Yu

Time-Point Sensitivity

A specific time point making the difference to user selection, such as purchasing festaval, promptions, Olympics, when a new item is released, or when an item is available at a specific point.

1. A recommender system for heterogeneous and time sensitive environment. RecSys, 2019. paper

   Meng Wu, Ying Zhu, Qilian Yu, Bhargav Rajendra, Yunqi Zhao, Navid Aghdaie, and Kazi A. Zaman

2. Discovering temporal purchase patterns with different responses to promotions. CIKM, 2016. paper

   Ling Luo, Bin Li, Irena Koprinska, Shlomo Berkovsky, Fang Chen

3. Visualizing program genres’ temporal-based similarity in linear TV recommendations. AVI, 2020. paper

   Veronika Bogina, Julia Sheidin, Tsvi Kuflik, Shlomo Berkovsky

   ​

Temporal Features

Time transformed features, such as weeks, seasons, years.

1. Enhanced product recommendations based on seasonality and demography in ecommerce. ICACCCN, 2020. paper

   Keerthika K, Saravanan T

2. Context of Seasonality in Web Search. ECIR, 2014. paper

   Tomáš Kramá, Mária Bieliková

3. Temporal collaborative filtering with bayesian probabilistic tensor factorization. SIAM, 2010. paper

   Liang Xiong, Xi Chen, Tzu-Kuo Huang, Jeff Schneider, Jaime G. Carbonell

4. Seasonality-adjusted conceptualrelevancy-aware recommender system in online groceries. BigData, 2019. paper

   Luyi Ma, Jason H.D. Cho, Sushant Kumar, Kannan Achan

5. Mining frequent seasonal gradual patterns. DaWaK, 2020. paper

   Jerry Lonlac, Arnaud Doniec, Marin Lujak, Stephane Lecoeuche

6. The contextual turn: from context-aware to context-driven recommender systems. RecSys, 2016. paper

   Roberto Pagano, Martha Larson, Balázs Hidasi, Alexandros Karatzoglou

7. Investigating and predicting online food recipe upload behavior. IPM, 2019. paper

   Christoph Trattnerb, Tomasz Kusmierczyka, Kjetil Nørvåga

   ​

Resources

https://github.com/caserec/Datasets-for-Recommender-Systems