{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/niser-normalized-item-and-session","title":"NISER: Normalized Item and Session Representations to Handle Popularity Bias","arxiv_id":"1909.04276","date":"2019-09-10","proceeding":null,"authors":["Priyanka Gupta","Diksha Garg","Pankaj Malhotra","Lovekesh Vig","Gautam Shroff"],"abstract":"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.","url_abs":"https://arxiv.org/abs/1909.04276v4","url_pdf":"https://arxiv.org/pdf/1909.04276v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"niser-normalized-item-and-session","repo_url":"https://github.com/GhostAnderson/NISER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"niser-normalized-item-and-session","repo_url":"https://github.com/johnny12150/NISER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"session-based-recommendations","task_name":"Session-Based Recommendations"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/session-based-recommendations-on-diginetica","task":"Session-Based Recommendations","dataset":"Diginetica","model":"NISER+","rank_in_archive_order":3,"of":13,"metrics":{"Hit@20":"53.39","MRR@20":"18.72"},"uses_additional_data":false},{"leaderboard":"/sota/session-based-recommendations-on-last-fm","task":"Session-Based Recommendations","dataset":"Last.FM","model":"NISER+","rank_in_archive_order":2,"of":3,"metrics":{"HR@20":"24.76","MRR@20":"9.02"},"uses_additional_data":false},{"leaderboard":"/sota/session-based-recommendations-on-yoochoose1-4","task":"Session-Based Recommendations","dataset":"yoochoose1/4","model":"NISER+","rank_in_archive_order":3,"of":4,"metrics":{"HR@20":"72.90","MRR@20":"32.04"},"uses_additional_data":false},{"leaderboard":"/sota/session-based-recommendations-on-yoochoose1-1","task":"Session-Based Recommendations","dataset":"yoochoose1/64","model":"NISER+","rank_in_archive_order":4,"of":11,"metrics":{"HR@20":"71.27","MRR@20":"31.61"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.04276","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}