Topology Distillation for Recommender System

TL;DR

This paper introduces Hierarchical Topology Distillation, a novel method for compressing recommender systems by transferring topological structures from teacher to student models, significantly improving recommendation quality.

Contribution

It proposes a hierarchical topology distillation approach that effectively transfers relational knowledge, overcoming capacity limitations of compact student models in recommender systems.

Findings

HTD outperforms state-of-the-art methods on real-world datasets.

Distilling topological structures enhances recommendation accuracy.

Hierarchical approach effectively manages capacity gaps.

Abstract

Recommender Systems (RS) have employed knowledge distillation which is a model compression technique training a compact student model with the knowledge transferred from a pre-trained large teacher model. Recent work has shown that transferring knowledge from the teacher's intermediate layer significantly improves the recommendation quality of the student. However, they transfer the knowledge of individual representation point-wise and thus have a limitation in that primary information of RS lies in the relations in the representation space. This paper proposes a new topology distillation approach that guides the student by transferring the topological structure built upon the relations in the teacher space. We first observe that simply making the student learn the whole topological structure is not always effective and even degrades the student's performance. We demonstrate that because the capacity of the student is highly limited compared to that of the teacher, learning the whole topological structure is daunting for the student. To address this issue, we propose a novel method named Hierarchical Topology Distillation (HTD) which distills the topology hierarchically to cope with the large capacity gap. Our extensive experiments on real-world datasets show that the proposed method significantly outperforms the state-of-the-art competitors. We also provide in-depth analyses to ascertain the benefit of distilling the topology for RS.