{"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/an-attentive-inductive-bias-for-sequential","title":"An Attentive Inductive Bias for Sequential Recommendation beyond the Self-Attention","arxiv_id":"2312.10325","date":"2023-12-16","proceeding":null,"authors":["Yehjin Shin","Jeongwhan Choi","Hyowon Wi","Noseong Park"],"abstract":"Sequential recommendation (SR) models based on Transformers have achieved remarkable successes. The self-attention mechanism of Transformers for computer vision and natural language processing suffers from the oversmoothing problem, i.e., hidden representations becoming similar to tokens. In the SR domain, we, for the first time, show that the same problem occurs. We present pioneering investigations that reveal the low-pass filtering nature of self-attention in the SR, which causes oversmoothing. To this end, we propose a novel method called $\\textbf{B}$eyond $\\textbf{S}$elf-$\\textbf{A}$ttention for Sequential $\\textbf{Rec}$ommendation (BSARec), which leverages the Fourier transform to i) inject an inductive bias by considering fine-grained sequential patterns and ii) integrate low and high-frequency information to mitigate oversmoothing. Our discovery shows significant advancements in the SR domain and is expected to bridge the gap for existing Transformer-based SR models. We test our proposed approach through extensive experiments on 6 benchmark datasets. The experimental results demonstrate that our model outperforms 7 baseline methods in terms of recommendation performance. Our code is available at https://github.com/yehjin-shin/BSARec.","url_abs":"https://arxiv.org/abs/2312.10325v2","url_pdf":"https://arxiv.org/pdf/2312.10325v2.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":"an-attentive-inductive-bias-for-sequential","repo_url":"https://github.com/jeongwhanchoi/BSARec","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"an-attentive-inductive-bias-for-sequential","repo_url":"https://github.com/yehjin-shin/bsarec","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"sequential-recommendation","task_name":"Sequential Recommendation"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sequential-recommendation-on-amazon-beauty","task":"Sequential Recommendation","dataset":"Amazon-Beauty","model":"BSARec","rank_in_archive_order":1,"of":3,"metrics":{"HR@10":"0.1008","HR@20":"0.1373","HR@5":"0.0736","NDCG@20":"0.0703","NDCG@5":"0.0523","nDCG@10":"0.0611"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-recommendation-on-amazon-sports","task":"Sequential Recommendation","dataset":"Amazon-Sports","model":"BSARec","rank_in_archive_order":2,"of":3,"metrics":{"HR@10":"0.0612","HR@20":"0.0858","HR@5":"0.0426"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-recommendation-on-amazon-toys","task":"Sequential Recommendation","dataset":"Amazon-Toys","model":"BSARec","rank_in_archive_order":1,"of":1,"metrics":{"HR@5":"0.0805"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-recommendation-on-lastfm","task":"Sequential Recommendation","dataset":"LastFM","model":"BSARec","rank_in_archive_order":1,"of":1,"metrics":{"HR@10":"0.0807","HR@10 (99 Neg. Samples)":"0.5028","HR@20":"0.1174","HR@5":"0.0523","HR@5 (99 Neg. Samples)":"0.3752","MRR (99 Neg. Samples)":"0.2636","NDCG@10":"0.0435","NDCG@10 (99 Neg. Samples)":"0.3045","NDCG@20":"0.0526","NDCG@5":"0.0344","NDCG@5 (99 Neg. Samples)":"0.2634"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-recommendation-on-movielens-1m","task":"Sequential Recommendation","dataset":"MovieLens 1M","model":"BSARec","rank_in_archive_order":2,"of":4,"metrics":{"HR@10":"0.2757","HR@10 (99 Neg. Samples)":"0.7978","HR@20":"0.3884","HR@5":"0.1944","HR@5 (99 Neg. Samples)":"0.7023","MRR (99 Neg. Samples)":"0.5406","NDCG@10":"0.1568","NDCG@10 (99 Neg. Samples)":"0.5955","NDCG@20":"0.1851","NDCG@5":"0.1306","NDCG@5 (99 Neg. Samples)":"0.5646"},"uses_additional_data":false},{"leaderboard":"/sota/sequential-recommendation-on-yelp","task":"Sequential Recommendation","dataset":"Yelp","model":"BSARec","rank_in_archive_order":1,"of":1,"metrics":{"HR@10":"0.0465","HR@10 (99 Neg. Samples)":"0.7848","HR@20":"0.0746","HR@5":"0.0275","HR@5 (99 Neg. Samples)":"0.6447","MRR (99 Neg. Samples)":"0.4587","NDCG@10":"0.0231","NDCG@10 (99 Neg. Samples)":"0.5280","NDCG@20":"0.0302","NDCG@5":"0.0170","NDCG@5 (99 Neg. Samples)":"0.4824"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.10325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10325"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jeongwhanchoi/BSARec","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yehjin-shin/bsarec","reach":{"status":"ok"}}],"summary":{"ran":6,"ran_honours":1},"by_repo_kind":{"official":{"samples":7,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"141fb484e5c9fe9a","entry":"generate_rating_matrix_test","repo":"jeongwhanchoi/BSARec","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/jeongwhanchoi/BSARec/blob/HEAD/src/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"141fb484e5c9fe9a"}},{"code_sha256_prefix":"b63caa42213cd69d","entry":"generate_rating_matrix_valid","repo":"jeongwhanchoi/BSARec","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/jeongwhanchoi/BSARec/blob/HEAD/src/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b63caa42213cd69d"}},{"code_sha256_prefix":"20b7c6470df6e0be","entry":"idcg_k","repo":"jeongwhanchoi/BSARec","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/jeongwhanchoi/BSARec/blob/HEAD/src/metrics.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"20b7c6470df6e0be"}},{"code_sha256_prefix":"4c416e834dc4dc77","entry":"ndcg_k","repo":"jeongwhanchoi/BSARec","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/jeongwhanchoi/BSARec/blob/HEAD/src/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4c416e834dc4dc77"}},{"code_sha256_prefix":"ff0f6a85cdaf16a5","entry":"neg_sample","repo":"jeongwhanchoi/BSARec","repo_kind":"official","path":"src/dataset.py","file_url":"https://github.com/jeongwhanchoi/BSARec/blob/HEAD/src/dataset.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff0f6a85cdaf16a5"}},{"code_sha256_prefix":"9c210c31b61b3c93","entry":"recall_at_k","repo":"jeongwhanchoi/BSARec","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/jeongwhanchoi/BSARec/blob/HEAD/src/metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9c210c31b61b3c93"}},{"code_sha256_prefix":"6dfdc5d998ebb49f","entry":"set_logger","repo":"jeongwhanchoi/BSARec","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/jeongwhanchoi/BSARec/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6dfdc5d998ebb49f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}