Combining LLM Semantic Reasoning with GNN Structural Modeling for Multi-view Multi-Label Feature Selection

2025-11-11

AI Summary

This paper addresses the multi-view multi-label feature selection problem by proposing the first dual-layer heterogeneous graph modeling framework that integrates large language models (LLMs) and graph neural networks (GNNs). Methodologically, it constructs two complementary layers: a semantic layer—a label-feature semantic graph driven by an LLM—and a statistical layer—a heterogeneous graph capturing multi-view co-occurrence patterns. A lightweight graph attention network jointly learns node embeddings across both layers to produce feature saliency scores. The key contribution lies in the novel integration of LLMs into this task, enabling synergistic optimization of semantic reasoning and structural modeling. Extensive experiments on multiple benchmark datasets demonstrate significant improvements over state-of-the-art methods, particularly under few-shot settings, where the approach exhibits strong robustness and superior generalization performance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Computer Vision: Multi-modal Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Multi-view multi-label feature selection aims to identify informative features from heterogeneous views, where each sample is associated with multiple interdependent labels. This problem is particularly important in machine learning involving high-dimensional, multimodal data such as social media, bioinformatics or recommendation systems. Existing Multi-View Multi-Label Feature Selection (MVMLFS) methods mainly focus on analyzing statistical information of data, but seldom consider semantic information. In this paper, we aim to use these two types of information jointly and propose a method that combines Large Language Models (LLMs) semantic reasoning with Graph Neural Networks (GNNs) structural modeling for MVMLFS. Specifically, the method consists of three main components. (1) LLM is first used as an evaluation agent to assess the latent semantic relevance among feature, view, and label descriptions. (2) A semantic-aware heterogeneous graph with two levels is designed to represent relations among features, views and labels: one is a semantic graph representing semantic relations, and the other is a statistical graph. (3) A lightweight Graph Attention Network (GAT) is applied to learn node embedding in the heterogeneous graph as feature saliency scores for ranking and selection. Experimental results on multiple benchmark datasets demonstrate the superiority of our method over state-of-the-art baselines, and it is still effective when applied to small-scale datasets, showcasing its robustness, flexibility, and generalization ability.

Problem

• Selecting informative features from multi-view multi-label heterogeneous data
• Integrating semantic reasoning with structural modeling for feature selection
• Addressing limitations of statistical-only approaches in high-dimensional multimodal data

Innovation

• LLM evaluates semantic relevance among features, views, labels
• Semantic-aware heterogeneous graph models statistical and semantic relations
• Lightweight GAT learns embeddings for feature ranking and selection