Streaming Session-based Recommendation

Guo, Lei; Yin, Hongzhi; Wang, Qinyong; Chen, Tong; Zhou, Alexander; Nguyen, Quoc Viet Hung

doi:10.1145/3292500.3330839

Cited by 161 publications

(89 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A major challenge in rapidly iterating on sequential recommendation systems is a reliable o ine evaluation methodology. Sequential recommendations are becoming increasingly relevant due to richer interactions between users and recommenders [9,17,27,29]. In such scenarios, the user's action (or reward) on a recommended item depends on the recent recommendations or user's previous actions.…”

Section: Introductionmentioning

confidence: 99%

Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions

McInerney

Brost

Chandar

et al. 2020

Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Users of music streaming, video streaming, news recommendation, and e-commerce services often engage with content in a sequential manner. Providing and evaluating good sequences of recommendations is therefore a central problem for these services. Prior reweighting-based counterfactual evaluation methods either suffer from high variance or make strong independence assumptions about rewards. We propose a new counterfactual estimator that allows for sequential interactions in the rewards with lower variance in an asymptotically unbiased manner. Our method uses graphical assumptions about the causal relationships of the slate to reweight the rewards in the logging policy in a way that approximates the expected sum of rewards under the target policy. Extensive experiments in simulation and on a live recommender system show that our approach outperforms existing methods in terms of bias and data e ciency for the sequential track recommendations problem.

show abstract

Section: Introductionmentioning

confidence: 99%

Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions

McInerney

Brost

Chandar

et al. 2020

Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

show abstract

“…SR-GNN [38] applies a gated graph network [18] as the item feature encoder and a self-attention layer to aggregate the item features together as the session feature. SSRM [5] considers a specific user's history sessions and applies the attention mechanism to combine them. Though the attention mechanism can proactively ignore the bias introduced by the time order of interaction, it considers a session as a totally random set.…”

Section: Session-based Recommender Systemmentioning

confidence: 99%

Rethinking the Item Order in Session-based Recommendation with Graph Neural Networks

Qiu

Huang

et al. 2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

Self Cite

310

185

View full text Add to dashboard Cite

Predicting a user's preference in a short anonymous interaction session instead of long-term history is a challenging problem in the real-life session-based recommendation, e.g., e-commerce and media stream. Recent research of the session-based recommender system mainly focuses on sequential patterns by utilizing the attention mechanism, which is straightforward for the session's natural sequence sorted by time. However, the user's preference is much more complicated than a solely consecutive time pattern in the transition of item choices. In this paper, therefore, we study the item transition pattern by constructing a session graph and propose a novel model which collaboratively considers the sequence order and the latent order in the session graph for a session-based recommender system. We formulate the next item recommendation within the session as a graph classification problem. Specifically, we propose a weighted attention graph layer and a Readout function to learn embeddings of items and sessions for the next item recommendation. Extensive experiments have been conducted on two benchmark E-commerce datasets, Yoochoose and Diginetica, and the experimental results show that our model outperforms other state-of-the-art methods. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

“…FlowRec implements several evaluation metrics, two of which are commonly used for next-item prediction [6,7,13,19], namely recall (a.k.a. hitrate) and mean reciprocal rank (MRR).…”

Section: Metricsmentioning

confidence: 99%

“…To better approximate realworld scenarios with severe cold-start and concept drifts, streaming recommender systems [3,18,20] have been designed for incremental online learning from continuous data streams in the context of limited memory/runtime, and anytime prediction [17]. However, most of them address the conventional rather than session-based recommendation problem [6]. Bridging the gap between sessionbased and streaming recommender systems has been recently attempted [6,9], marking an emerging research direction of a high practical value.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

FlowRec: Prototyping Session-Based Recommender Systems in Streaming Mode

Paraschakis

Nilsson

2020

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Despite the increasing interest towards session-based and streaming recommender systems, there is still a lack of publicly available evaluation frameworks supporting both these paradigms. To address the gap, we propose FlowRec -an extension of the streaming framework Scikit-Multiflow, which opens plentiful possibilities for prototyping recommender systems operating on sessionized data streams, thanks to the underlying collection of incremental learners and support for realtime performance tracking. We describe the extended functionalities of the adapted prequential evaluation protocol, and develop a competitive recommendation algorithm on top of Scikit-Multiflow's implementation of a Hoeffding Tree. We compare our algorithm to other known baselines for the next-item prediction task across three different domains.

show abstract

Streaming Session-based Recommendation

Cited by 161 publications

References 27 publications

Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions

Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions

Rethinking the Item Order in Session-based Recommendation with Graph Neural Networks

FlowRec: Prototyping Session-Based Recommender Systems in Streaming Mode

Contact Info

Product

Resources

About