Papers › NISER: Normalized Item and Session Representations to Handle Popularity Bias

NISER: Normalized Item and Session Representations to Handle Popularity Bias

10 Sep 2019arXiv:1909.04276archive 2025-07-28

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

The goal of session-based recommendation (SR) models is to utilize the information from past actions (e.g. item/product clicks) in a session to recommend items that a user is likely to click next. Recently it has been shown that the sequence of item interactions in a session can be modeled as graph-structured data to better account for complex item transitions. Graph neural networks (GNNs) can learn useful representations for such session-graphs, and have been shown to improve over sequential models such as recurrent neural networks [14]. However, we note that these GNN-based recommendation models suffer from popularity bias: the models are biased towards recommending popular items, and fail to recommend relevant long-tail items (less popular or less frequent items). Therefore, these models perform poorly for the less popular new items arriving daily in a practical online setting. We demonstrate that this issue is, in part, related to the magnitude or norm of the learned item and session-graph representations (embedding vectors). We propose a training procedure that mitigates this issue by using normalized representations. The models using normalized item and session-graph representations perform significantly better: i. for the less popular long-tail items in the offline setting, and ii. for the less popular newly introduced items in the online setting. Furthermore, our approach significantly improves upon existing state-of-the-art on three benchmark datasets.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

GhostAnderson/NISER mentioned on GitHubpytorchSyntology: not harvested report
johnny12150/NISER pytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Session-Based Recommendations

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Session-Based Recommendations Diginetica NISER+ Hit@20 53.39 #3 of 13 Archive leaderboard report
Session-Based Recommendations Diginetica NISER+ MRR@20 18.72 #3 of 13 Archive leaderboard report
Session-Based Recommendations Last.FM NISER+ HR@20 24.76 #2 of 3 Archive leaderboard report
Session-Based Recommendations Last.FM NISER+ MRR@20 9.02 #2 of 3 Archive leaderboard report
Session-Based Recommendations yoochoose1/4 NISER+ HR@20 72.90 #3 of 4 Archive leaderboard report
Session-Based Recommendations yoochoose1/4 NISER+ MRR@20 32.04 #3 of 4 Archive leaderboard report
Session-Based Recommendations yoochoose1/64 NISER+ HR@20 71.27 #4 of 11 Archive leaderboard report
Session-Based Recommendations yoochoose1/64 NISER+ MRR@20 31.61 #4 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections