Multi-Task Learning for Recommendation Over Heterogeneous Information Network

doi:10.1109/TKDE.2020.2983409

Multi-Task Learning for Recommendation Over Heterogeneous Information Network

2022-02-01

38

PRE

AI

DOI：10.1109/TKDE.2020.2983409

Original

Original request for help

Save

Abstract

En 中文

Traditional recommender systems (RS) only consider homogeneous data and cannot fully model heterogeneous information of complex objects and relations. Recent advances in the study of Heterogeneous Information Network (HIN) have shed some light on how to leverage heterogeneous information in RS. However, existing HIN-based recommendation models assume HIN is invariable and merely use HIN as a data source for assisting recommendation, which limits their performance. In this paper, we propose a multi-task learning framework, called MTRec, for recommendation over HIN. MTRec relies on self-attention mechanism to learn the semantics of meta-paths in HIN and jointly optimizes the tasks of both recommendation and link prediction. Using a Bayesian task weight learner, MTRec is able to achieve the balance of two tasks during optimization automatically. Moreover, MTRec provides good interpretabilities of recommendation through a translation mechanism which is used to model the three-way interactions among users, items and the meta-paths connecting them. Experimental results demonstrate the superiority of MTRec over state-of-the-art HIN-based recommendation models, and the case studies we provide illustrate that MTRec enhances the explainability of RS.

Keywords:

Task analysis

Predictive models

Data models

Recommender systems

Semantics

Bayes methods

Optimization

Recommender systems

heterogeneous information network

multi-task learning

Multi-Task Learning for Recommendation Over Heterogeneous Information Network

Abstract

AI Summary

Journal

Organization