Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Translation-based Recommendation

About

Modeling the complex interactions between users and items as well as amongst items themselves is at the core of designing successful recommender systems. One classical setting is predicting users' personalized sequential behavior (or `next-item' recommendation), where the challenges mainly lie in modeling `third-order' interactions between a user, her previously visited item(s), and the next item to consume. Existing methods typically decompose these higher-order interactions into a combination of pairwise relationships, by way of which user preferences (user-item interactions) and sequential patterns (item-item interactions) are captured by separate components. In this paper, we propose a unified method, TransRec, to model such third-order relationships for large-scale sequential prediction. Methodologically, we embed items into a `transition space' where users are modeled as translation vectors operating on item sequences. Empirically, this approach outperforms the state-of-the-art on a wide spectrum of real-world datasets. Data and code are available at https://sites.google.com/a/eng.ucsd.edu/ruining-he/.

Ruining He, Wang-Cheng Kang, Julian McAuley• 2017

Related benchmarks

TaskDatasetResultRank
Sequential RecommendationAmazon Beauty (test)
NDCG@1030.2
107
Sequential RecommendationAmazon Games (test)
Hit@1068.38
23
Sequential RecommendationMovieLens 1M (test)
Hit@1064.13
22
Sequential RecommendationSteam (test)
Hit@1076.24
18
Sequential RecommendationFashion
Recall14.64
14
Sequential RecommendationGames
Recall0.0101
14
Sequential Recommendationmusic
Recall0.05
14
Sequential RecommendationMovies
Recall2.11
14
Top-10 RecommendationAmazon CDs and Vinyl
NDCG3.372
8
Top-10 RecommendationAmazon Clothing
NDCG1.245
8
Showing 10 of 12 rows

Other info

Follow for update