Skip to content
Conference Open access

Disentangled Graph-Enhanced Large Language Models for Fair Learning

Sep 2026 · Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence · pp. 844-852 · 5 citations · 44 references

TL;DR

FairGEnt, a disentangled graph-enhanced large language model for fair graph learning, separates sensitive-related and sensitive-invariant factors in both graph and textual representations to mitigate bias while preserving task-relevant information, and further aligns the two modalities through a fairness-aware integration module.

Abstract

Large Language Models (LLMs) achieve strong performance in many applications but remain limited in handling graph-structured data due to their reliance on textual context. Recent approaches integrate Graph Neural Networks (GNNs) to enhance structural modeling, yet they largely overlook fairness, leaving models vulnerable to bias amplification across graph and text modalities. To address this issue, we propose FairGEnt, a disentangled graph-enhanced large language model for fair graph learning. FairGEnt separates sensitive-related and sensitive-invariant factors in both graph and textual representations to mitigate bias while preserving task-relevant information, and further aligns the two modalities through a fairness-aware integration module. In addition, FairGEnt incorporates fair graph-enhanced instruction tuning to improve LLM understanding of complex graph structures. Experiments on multiple benchmark datasets demonstrate that FairGEnt consistently outperforms existing methods in both fairness and predictive performance.

Read PDF

Similar papers

Open access Oct 2026

Fair synthetic tabular data generation via disentangled semantic encoding and large language models

Synthetic tabular data generation plays a key role in alleviating data scarcity and privacy limitations in machine learning, especially in regulated domains such as finance and healthcare. While many existing methods focus on producing realistic and predictive tabular data, fairness is often not explicitly considered,...

Huyen Giang Thi Thu, Thang Doan Viet, Trung Nguyen-Thanh et al. · 0 citations

IMoKGNN: Dual-Stream Fusion of Generic and Task-Specific Language Model Features for Graph Neural Networks

A dual-channel knowledge fusion framework, named MoKGNN, to simultaneously leverage the generic semantic knowledge from LLMs and the task adaptation capability of TLM, and a Knowledge Alignment Network to align the LLM embeddings with the TLM representations.

Hao Yan, Chao-Zhuo Li, Jun Yin et al. · 0 citations
Preprint Aug 2026

Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds

GRAPHSU is proposed, a graph-guided controller that expands the deletion scope beyond forget seeds by constructing a weighted support-route graph, propagating deletion pressure through it, and applying graded forgetting strengths to high-risk neighbors, demonstrating that effective enterprise unlearning requires contro...

Waqas Khan, Tabinda Sarwar, Jing-Yue Cong et al. · 0 citations
#graph neural networks Open access Oct 2026

GraphLLM4CTR: Large Language Model-enhanced Graph Neural Networks for Click-through Rate Prediction in Recommender Systems

Click-through rate (CTR) prediction is a crucial task to estimate the probability that users will click on items in online platforms. Recently, researchers have incorporated semantics derived from large language models (LLMs) into representations of users and items in a graph neural network (GNN) framework to facilitat...

Shan Gao, Yan-Wu Yang · 0 citations

Message Passing Does More with Less for In-Context Learning on Graphs

Achieving strong performance with graph neural networks (GNNs) typically requires training and hyperparameter tuning for each dataset, incurring repeated costs and effort. Graph in-context learning (ICL) avoids this by using a single pretrained model to predict unknown node labels directly from labeled context nodes. E...

Dooho Lee, Jin-Mo Lee, Minho Jeong et al. · 0 citations
Preprint Aug 2026

Auditing Privacy Risks in LLM-Enhanced Graph Neural Networks

Large language models (LLMs) have recently advanced graph neural networks (GNNs) by enriching node representations with semantic information, giving rise to LLM-enhanced GNNs that achieve substantial performance gains. However, how such semantic enhancement affects privacy risks remains largely underexplored. To bridge...

Long-Zhu He, Ze-Kun Wen, Chao-Zhuo Li et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.