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

• URL: http://arxiv.org/abs/2511.08008v2
• Date: Wed, 19 Nov 2025 07:57:22 GMT
• Title: Combining LLM Semantic Reasoning with GNN Structural Modeling for Multi-View Multi-Label Feature Selection
• Authors: Zhiqi Chen, Yuzhou Liu, Jiarui Liu, Wanfu Gao,
• Abstract summary: Multi-view multi-label feature selection aims to identify informative features from heterogeneous views.<n>Existing Multi-View Multi-Label Feature Selection (MVMLFS) methods mainly focus on analyzing statistical information of data.<n>We propose a method that combines Large Language Models (LLMs) semantic reasoning with Graph Neural Networks (GNNs) structural modeling for MVMLFS.
• Score: 13.731528637960828
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Cross-Contrastive Clustering for Multimodal Attributed Graphs with Dual Graph Filtering [22.795819970801475]
  MultimodalAttributed Graphs (MMAGs) are an expressive data model for representing the complex interconnections among entities.<n>We propose the Dual Graph Filtering scheme, which incorporates a feature-wise denoising component into node representation learning.<n>Our experiments show that DGF is able to outperform a wide range of state-of-the-art baselines consistently and significantly in terms of clustering quality measured against ground-truth labels.
  arXiv  Detail & Related papers  (2025-11-25T07:56:40Z)
• UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs [34.48393396390799]
  We propose a novel cross-domain graph foundation model that enables general representation learning on multimodal graphs.<n>UniGraph2 employs modality-specific encoders alongside a graph neural network (GNN) to learn a unified low-dimensional embedding space.<n>We show that UniGraph2 significantly outperforms state-of-the-art models in tasks such as representation learning, transfer learning, and multimodal generative tasks.
  arXiv  Detail & Related papers  (2025-02-02T14:04:53Z)
• Incomplete Multi-view Multi-label Classification via a Dual-level Contrastive Learning Framework [3.9108639455354592]
  In this paper, we propose our dual-level contrastive learning framework to solve the issue of double missing multi-view multi-label classification.<n>Experiments on several widely used benchmark datasets demonstrate that the proposed method has more stable and superior classification performance.
  arXiv  Detail & Related papers  (2024-11-27T12:04:04Z)
• Visual Commonsense based Heterogeneous Graph Contrastive Learning [79.22206720896664]
  We propose a heterogeneous graph contrastive learning method to better finish the visual reasoning task. Our method is designed as a plug-and-play way, so that it can be quickly and easily combined with a wide range of representative methods.
  arXiv  Detail & Related papers  (2023-11-11T12:01:18Z)
• KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification [75.95647590619929]
  Zero-Shot Node Classification (ZNC) has been an emerging and crucial task in graph data analysis. We propose a Knowledge-Aware Multi-Faceted framework (KMF) that enhances the richness of label semantics. A novel geometric constraint is developed to alleviate the problem of prototype drift caused by node information aggregation.
  arXiv  Detail & Related papers  (2023-08-15T02:38:08Z)
• Multi-label Node Classification On Graph-Structured Data [7.892731722253387]
  Graph Neural Networks (GNNs) have shown state-of-the-art improvements in node classification tasks on graphs. A more general and realistic scenario in which each node could have multiple labels has so far received little attention. We collect and release three real-world biological datasets and develop a multi-label graph generator.
  arXiv  Detail & Related papers  (2023-04-20T15:34:20Z)
• r-GAT: Relational Graph Attention Network for Multi-Relational Graphs [8.529080554172692]
  Graph Attention Network (GAT) focuses on modelling simple undirected and single relational graph data only. We propose r-GAT, a relational graph attention network to learn multi-channel entity representations. Experiments on link prediction and entity classification tasks show that our r-GAT can model multi-relational graphs effectively.
  arXiv  Detail & Related papers  (2021-09-13T12:43:00Z)
• Auto-weighted Multi-view Feature Selection with Graph Optimization [90.26124046530319]
  We propose a novel unsupervised multi-view feature selection model based on graph learning. The contributions are threefold: (1) during the feature selection procedure, the consensus similarity graph shared by different views is learned. Experiments on various datasets demonstrate the superiority of the proposed method compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-04-11T03:25:25Z)
• Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer [140.72439827136085]
  We propose a graph reasoning and transfer learning framework named "Graphonomy" It incorporates human knowledge and label taxonomy into the intermediate graph representation learning beyond local convolutions. It learns the global and structured semantic coherency in multiple domains via semantic-aware graph reasoning and transfer.
  arXiv  Detail & Related papers  (2021-01-26T08:19:03Z)
• Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition [75.44233392355711]
  KGGR framework exploits prior knowledge of statistical label correlations with deep neural networks. It first builds a structured knowledge graph to correlate different labels based on statistical label co-occurrence. Then, it introduces the label semantics to guide learning semantic-specific features. It exploits a graph propagation network to explore graph node interactions.
  arXiv  Detail & Related papers  (2020-09-20T15:05:29Z)
• Instance-Aware Graph Convolutional Network for Multi-Label Classification [55.131166957803345]
  Graph convolutional neural network (GCN) has effectively boosted the multi-label image recognition task. We propose an instance-aware graph convolutional neural network (IA-GCN) framework for multi-label classification.
  arXiv  Detail & Related papers  (2020-08-19T12:49:28Z)
• Multi-Label Text Classification using Attention-based Graph Neural Network [0.0]
  A graph attention network-based model is proposed to capture the attentive dependency structure among the labels. The proposed model achieves similar or better performance compared to the previous state-of-the-art models.
  arXiv  Detail & Related papers  (2020-03-22T17:12:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.