Papers › Collaborative Similarity Embedding for Recommender Systems

Collaborative Similarity Embedding for Recommender Systems

17 Feb 2019arXiv:1902.06188archive 2025-07-28

Chih-Ming Chen, Chuan-Ju Wang, Ming-Feng Tsai, Yi-Hsuan Yang

We present collaborative similarity embedding (CSE), a unified framework that exploits comprehensive collaborative relations available in a user-item bipartite graph for representation learning and recommendation. In the proposed framework, we differentiate two types of proximity relations: direct proximity and k-th order neighborhood proximity. While learning from the former exploits direct user-item associations observable from the graph, learning from the latter makes use of implicit associations such as user-user similarities and item-item similarities, which can provide valuable information especially when the graph is sparse. Moreover, for improving scalability and flexibility, we propose a sampling technique that is specifically designed to capture the two types of proximity relations. Extensive experiments on eight benchmark datasets show that CSE yields significantly better performance than state-of-the-art recommendation methods.

PaperPDFCode

Code

bdnf/SBX-Recommendation-Engine mentioned on GitHubpytorch report
cnclabs/smore mentioned on GitHub 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

Graph LearningRecommendation SystemsRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Recommendation Systems CiteULike RATE-CSE Recall@10 0.2362 #1 of 1 Archive leaderboard report
Recommendation Systems CiteULike RATE-CSE mAP@10 0.1452 #1 of 1 Archive leaderboard report
Recommendation Systems Echonest RANK-CSE Recall@10 0.1358 #1 of 1 Archive leaderboard report
Recommendation Systems Echonest RANK-CSE mAP@10 0.0679 #1 of 1 Archive leaderboard report
Recommendation Systems Epinions-Extend RANK-CSE Recall@10 0.1767 #1 of 1 Archive leaderboard report
Recommendation Systems Epinions-Extend RANK-CSE mAP@10 0.0921 #1 of 1 Archive leaderboard report
Recommendation Systems Frappe RATE-CSE Recall@10 33.47 #2 of 2 Archive leaderboard report
Recommendation Systems Frappe RATE-CSE mAP@10 0.2047 #2 of 2 Archive leaderboard report
Recommendation Systems Last.FM-360k RANK-CSE Recall@10 0.1762 #1 of 1 Archive leaderboard report
Recommendation Systems Last.FM-360k RANK-CSE mAP@10 0.097 #1 of 1 Archive leaderboard report
Recommendation Systems MovieLens-Latest RATE-CSE Recall@10 0.3225 #1 of 1 Archive leaderboard report
Recommendation Systems MovieLens-Latest RATE-CSE mAP@10 0.199 #1 of 1 Archive leaderboard report
Recommendation Systems Netflix RATE-CSE Recall@10 0.2014 #10 of 10 Archive leaderboard report
Recommendation Systems Netflix RATE-CSE mAP@10 0.1039 #10 of 10 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