Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
- URL: http://arxiv.org/abs/2405.19919v2
- Date: Sat, 1 Jun 2024 10:28:20 GMT
- Title: Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
- Authors: Yuhao Wu, Jiangchao Yao, Bo Han, Lina Yao, Tongliang Liu,
- Abstract summary: Positive-Unlabeled (PU) learning is vital in many real-world scenarios, but its application to graph data remains under-explored.
We unveil that a critical challenge for PU learning on graph lies on the edge heterophily, which directly violates the irreducibility assumption for Class-Prior Estimation.
In response to this challenge, we introduce a new method, named Graph PU Learning with Label Propagation Loss (GPL)
- Score: 71.9954600831939
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: While Positive-Unlabeled (PU) learning is vital in many real-world scenarios, its application to graph data still remains under-explored. We unveil that a critical challenge for PU learning on graph lies on the edge heterophily, which directly violates the irreducibility assumption for Class-Prior Estimation (class prior is essential for building PU learning algorithms) and degenerates the latent label inference on unlabeled nodes during classifier training. In response to this challenge, we introduce a new method, named Graph PU Learning with Label Propagation Loss (GPL). Specifically, GPL considers learning from PU nodes along with an intermediate heterophily reduction, which helps mitigate the negative impact of the heterophilic structure. We formulate this procedure as a bilevel optimization that reduces heterophily in the inner loop and efficiently learns a classifier in the outer loop. Extensive experiments across a variety of datasets have shown that GPL significantly outperforms baseline methods, confirming its effectiveness and superiority.
Related papers
- When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning [6.2167203720326025]
Unsupervised heterogeneous graph representation learning (UHGRL) has gained increasing attention due to its significance in handling practical graphs without labels.
We define semantic heterophily and propose an innovative framework called Latent Graphs Guided Unsupervised Representation Learning (LatGRL) to handle this problem.
arXiv Detail & Related papers (2024-09-01T10:25:06Z) - 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) - Class Prior-Free Positive-Unlabeled Learning with Taylor Variational
Loss for Hyperspectral Remote Sensing Imagery [12.54504113062557]
Positive-unlabeled learning (PU learning) in hyperspectral remote sensing imagery (HSI) is aimed at learning a binary classifier from positive and unlabeled data.
In this paper, a Taylor variational loss is proposed for HSI PU learning, which reduces the weight of the gradient of the unlabeled data.
Experiments on 7 benchmark datasets (21 tasks in total) validate the effectiveness of the proposed method.
arXiv Detail & Related papers (2023-08-29T07:29:30Z) - All Points Matter: Entropy-Regularized Distribution Alignment for
Weakly-supervised 3D Segmentation [67.30502812804271]
Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning.
We propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions.
arXiv Detail & Related papers (2023-05-25T08:19:31Z) - Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data.
We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
arXiv Detail & Related papers (2023-03-06T14:49:59Z) - Dist-PU: Positive-Unlabeled Learning from a Label Distribution
Perspective [89.5370481649529]
We propose a label distribution perspective for PU learning in this paper.
Motivated by this, we propose to pursue the label distribution consistency between predicted and ground-truth label distributions.
Experiments on three benchmark datasets validate the effectiveness of the proposed method.
arXiv Detail & Related papers (2022-12-06T07:38:29Z) - Learning from Label Proportions by Learning with Label Noise [30.7933303912474]
Learning from label proportions (LLP) is a weakly supervised classification problem where data points are grouped into bags.
We provide a theoretically grounded approach to LLP based on a reduction to learning with label noise.
Our approach demonstrates improved empirical performance in deep learning scenarios across multiple datasets and architectures.
arXiv Detail & Related papers (2022-03-04T18:52:21Z) - Cyclic Label Propagation for Graph Semi-supervised Learning [52.102251202186025]
We introduce a novel framework for graph semi-supervised learning called CycProp.
CycProp integrates GNNs into the process of label propagation in a cyclic and mutually reinforcing manner.
In particular, our proposed CycProp updates the node embeddings learned by GNN module with the augmented information by label propagation.
arXiv Detail & Related papers (2020-11-24T02:55:40Z)
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.