Code Recommendation for Open Source Software Developers

Apr 30, 2023·
Yiqiao Jin
Yiqiao Jin
,
Yunsheng Bai
,
Yanqiao Zhu
,
Yizhou Sun
,
Wei Wang
· 1 min read
Abstract
Open Source Software (OSS) developers contribute to a large and rapidly growing ecosystem, but matching developers to relevant code is challenging. We introduce CODER, a graph-based code recommendation framework that leverages multi-modal signals from OSS contribution and engagement networks. CODER models heterogeneous graphs over repositories, users, issues, and pull requests, and learns representations that improve code recommendation across realistic OSS workloads. WWW 2023 acceptance rate: 19.2%.
Type
Publication
The Web Conference (WWW) 2023, Oral Presentation

Abstract

Open Source Software (OSS) developers contribute to a large and rapidly growing ecosystem, but matching developers to relevant code is challenging. We introduce CODER, a graph-based code recommendation framework that leverages multi-modal signals from OSS contribution and engagement networks.

Recommender Systems Graph Neural Networks Open Source Software Code Recommendation
Yiqiao Jin
Authors
Yiqiao Jin
Ph.D. Candidate in Computer Science
My research sits at the intersection of multimodal foundation models, intelligent agents, and spatial/physical intelligence. I build general-purpose models that perceive, reason, learn, and act in interactive virtual and physical environments.