An Adjustable Heat Conduction based KNN Approach for Session-based Recommendation

TL;DR

This paper introduces an adjustable heat conduction inspired KNN method for session-based recommendation that considers both recent and historical co-occurrence information, improving recommendation accuracy.

Contribution

It proposes a novel diffusion-based similarity and candidate selection method to enhance KNN for session-based recommendation, addressing limitations of existing approaches.

Findings

Outperforms state-of-the-art KNN methods on benchmark datasets

Effectively captures historical and recent co-occurrence information

Demonstrates robustness and efficiency in recommendations

Abstract

The KNN approach, which is widely used in recommender systems because of its efficiency, robustness and interpretability, is proposed for session-based recommendation recently and outperforms recurrent neural network models. It captures the most recent co-occurrence information of items by considering the interaction time. However, it neglects the co-occurrence information of items in the historical behavior which is interacted earlier and cannot discriminate the impact of items and sessions with different popularity. Due to these observations, this paper presents a new contextual KNN approach to address these issues for session-based recommendation. Specifically, a diffusion-based similarity method is proposed for considering the popularity of vertices in session-item bipartite network, and a candidate selection method is proposed to capture the items that are co-occurred with different historical clicked items in the same session efficiently. Comprehensive experiments are conducted to demonstrate the effectiveness of our KNN approach over the state-of-the-art KNN approach for session-based recommendation on three benchmark datasets.