Unified Pretraining for Recommendation via Task Hypergraphs

TL;DR

This paper introduces a unified multitask pretraining framework using task hypergraphs for recommendation systems, effectively handling diverse pretext tasks and improving performance across multiple datasets.

Contribution

It proposes a novel task hypergraph-based pretraining framework with a transitional attention layer to generalize pretext tasks for recommendation.

Findings

Outperforms existing methods on three benchmark datasets.

Effectively generalizes diverse pretext tasks.

Demonstrates robustness and effectiveness through detailed experiments.

Abstract

Although pretraining has garnered significant attention and popularity in recent years, its application in graph-based recommender systems is relatively limited. It is challenging to exploit prior knowledge by pretraining in widely used ID-dependent datasets. On one hand, user-item interaction history in one dataset can hardly be transferred to other datasets through pretraining, where IDs are different. On the other hand, pretraining and finetuning on the same dataset leads to a high risk of overfitting. In this paper, we propose a novel multitask pretraining framework named Unified Pretraining for Recommendation via Task Hypergraphs. For a unified learning pattern to handle diverse requirements and nuances of various pretext tasks, we design task hypergraphs to generalize pretext tasks to hyperedge prediction. A novel transitional attention layer is devised to discriminatively learn the relevance between each pretext task and recommendation. Experimental results on three benchmark datasets verify the superiority of UPRTH. Additional detailed investigations are conducted to demonstrate the effectiveness of the proposed framework.