EMK-KEN: A High-Performance Approach for Assessing Knowledge Value in Citation Network

TL;DR

EMK-KEN is a novel method that efficiently evaluates the knowledge value of academic papers by combining semantic and structural features, outperforming existing approaches in robustness and effectiveness.

Contribution

The paper introduces EMK-KEN, a new approach that integrates semantic and structural analysis for citation networks, improving evaluation efficiency and robustness across fields.

Findings

Outperforms state-of-the-art methods in effectiveness.

Demonstrates robustness across ten benchmark datasets.

Efficiently captures semantic and structural features.

Abstract

With the explosive growth of academic literature, effectively evaluating the knowledge value of literature has become quite essential. However, most of the existing methods focus on modeling the entire citation network, which is structurally complex and often suffers from long sequence dependencies when dealing with text embeddings. Thus, they might have low efficiency and poor robustness in different fields. To address these issues, a novel knowledge evaluation method is proposed, called EMK-KEN. The model consists of two modules. Specifically, the first module utilizes MetaFP and Mamba to capture semantic features of node metadata and text embeddings to learn contextual representations of each paper. The second module utilizes KAN to further capture the structural information of citation networks in order to learn the differences in different fields of networks. Extensive experiments based on ten benchmark datasets show that our method outperforms the state-of-the-art competitors in effectiveness and robustness.