Microsoft Academic Graph Information Retrieval for Research Recommendation and Assistance

TL;DR

This paper introduces an Attention-Based Subgraph Retriever that leverages Graph Neural Networks and attention mechanisms to efficiently filter and process large-scale scientific publication data for improved research recommendation and assistance.

Contribution

It presents a novel GNN-based retrieval model that uses attention-based pruning to enhance knowledge reasoning in large language models.

Findings

Effective subgraph extraction improves retrieval accuracy

Enhanced reasoning capabilities with combined GNN and language models

Potential for better research recommendation systems

Abstract

In today's information-driven world, access to scientific publications has become increasingly easy. At the same time, filtering through the massive volume of available research has become more challenging than ever. Graph Neural Networks (GNNs) and graph attention mechanisms have shown strong effectiveness in searching large-scale information databases, particularly when combined with modern large language models. In this paper, we propose an Attention-Based Subgraph Retriever, a GNN-as-retriever model that applies attention-based pruning to extract a refined subgraph, which is then passed to a large language model for advanced knowledge reasoning.