Papers › Deep Models of Interactions Across Sets

Deep Models of Interactions Across Sets

7 Mar 2018ICML 2018 7arXiv:1803.02879archive 2025-07-28

Jason Hartford, Devon R Graham, Kevin Leyton-Brown, Siamak Ravanbakhsh

We use deep learning to model interactions across two or more sets of objects, such as user-movie ratings, protein-drug bindings, or ternary user-item-tag interactions. The canonical representation of such interactions is a matrix (or a higher-dimensional tensor) with an exchangeability property: the encoding's meaning is not changed by permuting rows or columns. We argue that models should hence be Permutation Equivariant (PE): constrained to make the same predictions across such permutations. We present a parameter-sharing scheme and prove that it could not be made any more expressive without violating PE. This scheme yields three benefits. First, we demonstrate state-of-the-art performance on multiple matrix completion benchmarks. Second, our models require a number of parameters independent of the numbers of objects, and thus scale well to large datasets. Third, models can be queried about new objects that were not available at training time, but for which interactions have since been observed. In experiments, our models achieved surprisingly good generalization performance on this matrix extrapolation task, both within domains (e.g., new users and new movies drawn from the same distribution used for training) and even across domains (e.g., predicting music ratings after training on movies).

PaperPDFConference PDFCode

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

Code

mravanba/deep_exchangeable_tensors officialmentioned in papermentioned on GitHubtf 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

Collaborative FilteringMatrix CompletionRecommendation SystemsTAG

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Recommendation Systems Douban Monti Factorized EAE RMSE 0.738 #6 of 8 Archive leaderboard report
Recommendation Systems Flixster Monti Factorized EAE RMSE 0.908 #4 of 7 Archive leaderboard report
Recommendation Systems MovieLens 100K Self-Supervised Exchangeable Model RMSE (u1 Splits) 0.91 #10 of 18 Archive leaderboard report
Recommendation Systems MovieLens 100K Factorized EAE RMSE (u1 Splits) 0.920 #12 of 18 Archive leaderboard report
Recommendation Systems MovieLens 1M Factorized EAE RMSE 0.860 #15 of 31 Archive leaderboard report
Recommendation Systems YahooMusic Monti Factorized EAE RMSE 20.0 #3 of 6 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