Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Collaborative Distillation for Top-N Recommendation

About

Knowledge distillation (KD) is a well-known method to reduce inference latency by compressing a cumbersome teacher model to a small student model. Despite the success of KD in the classification task, applying KD to recommender models is challenging due to the sparsity of positive feedback, the ambiguity of missing feedback, and the ranking problem associated with the top-N recommendation. To address the issues, we propose a new KD model for the collaborative filtering approach, namely collaborative distillation (CD). Specifically, (1) we reformulate a loss function to deal with the ambiguity of missing feedback. (2) We exploit probabilistic rank-aware sampling for the top-N recommendation. (3) To train the proposed model effectively, we develop two training strategies for the student model, called the teacher- and the student-guided training methods, selecting the most useful feedback from the teacher model. Via experimental results, we demonstrate that the proposed model outperforms the state-of-the-art method by 2.7-33.2% and 2.7-29.1% in hit rate (HR) and normalized discounted cumulative gain (NDCG), respectively. Moreover, the proposed model achieves the performance comparable to the teacher model.

Jae-woong Lee, Minjin Choi, Jongwuk Lee, Hyunjung Shim• 2019

Related benchmarks

TaskDatasetResultRank
RecommendationGowalla (test)
Recall@200.1592
177
Sequential RecommendationYelp
Recall@100.0153
120
RecommendationYelp (test)
NDCG@203.7
82
Sequential RecommendationGowalla
NDCG@100.025
45
Sequential RecommendationCiteULike
Recall@101.02
40
RecommendationCiteULike (test)
Recall@104.28
40
Showing 6 of 6 rows

Other info

Follow for update