CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking

TL;DR

This paper introduces CODE, a zero-shot expert linking method combining contrastive pre-training and adversarial fine-tuning, improving linking accuracy across external sources without extensive labeled data.

Contribution

The paper proposes a novel zero-shot expert linking framework using contrastive learning and adversarial fine-tuning, enhancing transferability and performance without requiring large labeled datasets.

Findings

Contrastive pre-training captures expert representation and matching patterns effectively.

Adversarial fine-tuning improves transferability to external sources.

CODE outperforms baseline methods in expert linking tasks.

Abstract

Expert finding, a popular service provided by many online websites such as Expertise Finder, LinkedIn, and AMiner, is beneficial to seeking candidate qualifications, consultants, and collaborators. However, its quality is suffered from lack of ample sources of expert information. This paper employs AMiner as the basis with an aim at linking any external experts to the counterparts on AMiner. As it is infeasible to acquire sufficient linkages from arbitrary external sources, we explore the problem of zero-shot expert linking. In this paper, we propose CODE, which first pre-trains an expert linking model by contrastive learning on AMiner such that it can capture the representation and matching patterns of experts without supervised signals, then it is fine-tuned between AMiner and external sources to enhance the models transferability in an adversarial manner. For evaluation, we first design two intrinsic tasks, author identification and paper clustering, to validate the representation and matching capability endowed by contrastive learning. Then the final external expert linking performance on two genres of external sources also implies the superiority of the adversarial fine-tuning method. Additionally, we show the online deployment of CODE, and continuously improve its online performance via active learning.