MLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing

• URL: http://arxiv.org/abs/2605.13126v2
• Date: Thu, 14 May 2026 10:59:42 GMT
• Title: MLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing
• Abstract summary: Graph Neural Networks (GNNs) suffer from over-squashing in deep message passing, where information from exponentially growing neighborhoods is compressed into fixed-dimensional representations.<n>We show that this issue becomes a distinct failure mode in multi-label graphs, causing predictive signals to be diluted by noisy label information.<n>We propose the Multi-Label Graph Information Bottleneck (MLGIB), which formulates multi-label message passing as constrained information transmission under irrelevant label noise.
• Score: 12.034223244199902
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph Neural Networks (GNNs) suffer from over-squashing in deep message passing, where information from exponentially growing neighborhoods is compressed into fixed-dimensional representations. We show that this issue becomes a distinct failure mode in multi-label graphs: neighboring nodes often share only limited labels while differing across many irrelevant ones, causing predictive signals to be diluted by noisy label information. To address this challenge, we propose the Multi-Label Graph Information Bottleneck (MLGIB), which formulates multi-label message passing as constrained information transmission under irrelevant label noise. MLGIB balances expressiveness and robustness by preserving predictive label signals while suppressing irrelevant noise. Specifically, it constructs a Markovian dependence space and derives tractable variational bounds, where the lower bound maximizes mutual information with target labels and the upper bound constrains redundant source information. These bounds lead to an end-to-end label-aware message-passing architecture. Extensive experiments on multiple benchmarks demonstrate consistent improvements over existing methods, validating the effectiveness and generality of the proposed framework.

Related papers

• Multi-Label Node Classification with Label Influence Propagation [79.38415948442751]
  Tackling multi-label node classification (MLNC) on graphs has led to the development of various approaches.<n>Some methods leverage graph neural networks (GNNs) to exploit label co-occurrence correlations, while others incorporate label embeddings to capture label proximity.<n>We decompose the message passing process in GNNs into two operations: propagation and transformation.<n>We then conduct a comprehensive analysis and quantification of the influence correlations between labels in each operation.
  arXiv  Detail & Related papers  (2026-07-01T09:17:28Z)
• Identifying and Correcting Label Noise for Robust GNNs via Influence Contradiction [25.627750818623884]
  Graph Neural Networks (GNNs) have shown remarkable capabilities in learning from graph-structured data.<n>The presence of label noise in real scenarios poses a significant challenge in learning robust GNNs.<n>We propose a novel approach called ICGNN that harnesses the structure information of the graph to effectively alleviate the challenges posed by noisy labels.
  arXiv  Detail & Related papers  (2026-01-24T14:07:07Z)
• Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning [70.73716819236627]
  Heterogeneous Graph Neural Networks (HGNNs) are widely used for deep learning on heterogeneous graphs.<n>HGNNs require repetitive message passing during training, limiting efficiency for large-scale real-world graphs.<n>We propose pre-computation-based HGNNs that only perform message passing once during preprocessing.
  arXiv  Detail & Related papers  (2025-11-14T08:53:39Z)
• Correlation-Aware Graph Convolutional Networks for Multi-Label Node Classification [32.4968073593255]
  We propose a Correlation-aware Graph Convolutional Network (CorGCN) for multi-label node classification.<n>By introducing a novel Correlation-Aware Graph Decomposition module, CorGCN can learn a graph that contains rich label-correlated information for each label.
  arXiv  Detail & Related papers  (2024-11-26T11:52:47Z)
• ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance [53.73316938815873]
  We propose a method called ERASE (Error-Resilient representation learning on graphs for lAbel noiSe tolerancE) to learn representations with error tolerance. ERASE combines prototype pseudo-labels with propagated denoised labels and updates representations with error resilience. Our method can outperform multiple baselines with clear margins in broad noise levels and enjoy great scalability.
  arXiv  Detail & Related papers  (2023-12-13T17:59:07Z)
• ALEX: Towards Effective Graph Transfer Learning with Noisy Labels [11.115297917940829]
  We introduce a novel technique termed Balance Alignment and Information-aware Examination (ALEX) to address the problem of graph transfer learning. ALEX first employs singular value decomposition to generate different views with crucial structural semantics, which help provide robust node representations. Building on this foundation, an adversarial domain discriminator is incorporated for the implicit domain alignment of complex multi-modal distributions.
  arXiv  Detail & Related papers  (2023-09-26T04:59:49Z)
• Learning on Graphs under Label Noise [5.909452203428086]
  We develop a novel approach dubbed Consistent Graph Neural Network (CGNN) to solve the problem of learning on graphs with label noise. Specifically, we employ graph contrastive learning as a regularization term, which promotes two views of augmented nodes to have consistent representations. To detect noisy labels on the graph, we present a sample selection technique based on the homophily assumption.
  arXiv  Detail & Related papers  (2023-06-14T01:38:01Z)
• Label Noise-Resistant Mean Teaching for Weakly Supervised Fake News Detection [93.6222609806278]
  We propose a novel label noise-resistant mean teaching approach (LNMT) for weakly supervised fake news detection. LNMT leverages unlabeled news and feedback comments of users to enlarge the amount of training data. LNMT establishes a mean teacher framework equipped with label propagation and label reliability estimation.
  arXiv  Detail & Related papers  (2022-06-10T16:01:58Z)
• Informative Pseudo-Labeling for Graph Neural Networks with Few Labels [12.83841767562179]
  Graph Neural Networks (GNNs) have achieved state-of-the-art results for semi-supervised node classification on graphs. The challenge of how to effectively learn GNNs with very few labels is still under-explored. We propose a novel informative pseudo-labeling framework, called InfoGNN, to facilitate learning of GNNs with extremely few labels.
  arXiv  Detail & Related papers  (2022-01-20T01:49:30Z)
• 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)
• Learn to Propagate Reliably on Noisy Affinity Graphs [69.97364913330989]
  Recent works have shown that exploiting unlabeled data through label propagation can substantially reduce the labeling cost. How to propagate labels reliably, especially on a dataset with unknown outliers, remains an open question. We propose a new framework that allows labels to be propagated reliably on large-scale real-world data.
  arXiv  Detail & Related papers  (2020-07-17T07:55:59Z)

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.