Robust Recommendation with Implicit Feedback via Eliminating the Effects of Unexpected Behaviors

TL;DR

This paper introduces a Multi-Preferences Model (MPM) that effectively filters out the influence of unexpected behaviors in implicit feedback data, leading to more accurate recommendations by focusing on genuine user preferences.

Contribution

The paper presents a novel MPM that detects and eliminates the effects of unexpected behaviors, improving recommendation accuracy over existing methods.

Findings

Significant improvements in HR@10 and NDCG@10 metrics.

Massive relative increase of 3.643% and 4.107% in performance metrics.

Demonstrated effectiveness on movie and e-retailing datasets.

Abstract

In the implicit feedback recommendation, incorporating short-term preference into recommender systems has attracted increasing attention in recent years. However, unexpected behaviors in historical interactions like clicking some items by accident don't well reflect users' inherent preferences. Existing studies fail to model the effects of unexpected behaviors, thus achieve inferior recommendation performance. In this paper, we propose a Multi-Preferences Model (MPM) to eliminate the effects of unexpected behaviors. MPM first extracts the users' instant preferences from their recent historical interactions by a fine-grained preference module. Then an unexpected-behaviors detector is trained to judge whether these instant preferences are biased by unexpected behaviors. We also integrate user's general preference in MPM. Finally, an output module is performed to eliminate the effects of unexpected behaviors and integrates all the information to make a final recommendation. We conduct extensive experiments on two datasets of a movie and an e-retailing, demonstrating significant improvements in our model over the state-of-the-art methods. The experimental results show that MPM gets a massive improvement in HR@10 and NDCG@10, which relatively increased by 3.643% and 4.107% compare with AttRec model on average. We publish our code at https://github.com/chenjie04/MPM/.