NISER: Normalized Item and Session Representations to Handle Popularity Bias

10 Sep 2019  ·  Priyanka Gupta, Diksha Garg, Pankaj Malhotra, Lovekesh Vig, Gautam Shroff ·

The goal of session-based recommendation (SR) models is to utilize the information from past actions (e.g. item/product clicks) in a session to recommend items that a user is likely to click next. Recently it has been shown that the sequence of item interactions in a session can be modeled as graph-structured data to better account for complex item transitions. Graph neural networks (GNNs) can learn useful representations for such session-graphs, and have been shown to improve over sequential models such as recurrent neural networks [14]. However, we note that these GNN-based recommendation models suffer from popularity bias: the models are biased towards recommending popular items, and fail to recommend relevant long-tail items (less popular or less frequent items). Therefore, these models perform poorly for the less popular new items arriving daily in a practical online setting. We demonstrate that this issue is, in part, related to the magnitude or norm of the learned item and session-graph representations (embedding vectors). We propose a training procedure that mitigates this issue by using normalized representations. The models using normalized item and session-graph representations perform significantly better: i. for the less popular long-tail items in the offline setting, and ii. for the less popular newly introduced items in the online setting. Furthermore, our approach significantly improves upon existing state-of-the-art on three benchmark datasets.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Session-Based Recommendations Diginetica NISER+ MRR@20 18.72 # 3
Hit@20 53.39 # 4
Session-Based Recommendations Last.FM NISER+ HR@20 24.76 # 2
MRR@20 9.02 # 2
Session-Based Recommendations yoochoose1/4 NISER+ MRR@20 32.04 # 3
HR@20 72.90 # 1
Session-Based Recommendations yoochoose1/64 NISER+ MRR@20 31.61 # 4
HR@20 71.27 # 5

Methods


No methods listed for this paper. Add relevant methods here