Alleviating neighbor bias: augmenting graph self-supervise learning with
structural equivalent positive samples
- URL: http://arxiv.org/abs/2212.04365v1
- Date: Thu, 8 Dec 2022 16:04:06 GMT
- Title: Alleviating neighbor bias: augmenting graph self-supervise learning with
structural equivalent positive samples
- Authors: Jiawei Zhu, Mei Hong, Ronghua Du, Haifeng Li
- Abstract summary: We propose a signal-driven self-supervised method for graph representation learning.
It uses a topological information-guided structural equivalence sampling strategy.
The results show that the model performance can be effectively improved.
- Score: 1.0507062889290775
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In recent years, using a self-supervised learning framework to learn the
general characteristics of graphs has been considered a promising paradigm for
graph representation learning. The core of self-supervised learning strategies
for graph neural networks lies in constructing suitable positive sample
selection strategies. However, existing GNNs typically aggregate information
from neighboring nodes to update node representations, leading to an
over-reliance on neighboring positive samples, i.e., homophilous samples; while
ignoring long-range positive samples, i.e., positive samples that are far apart
on the graph but structurally equivalent samples, a problem we call "neighbor
bias." This neighbor bias can reduce the generalization performance of GNNs. In
this paper, we argue that the generalization properties of GNNs should be
determined by combining homogeneous samples and structurally equivalent
samples, which we call the "GC combination hypothesis." Therefore, we propose a
topological signal-driven self-supervised method. It uses a topological
information-guided structural equivalence sampling strategy. First, we extract
multiscale topological features using persistent homology. Then we compute the
structural equivalence of node pairs based on their topological features. In
particular, we design a topological loss function to pull in non-neighboring
node pairs with high structural equivalence in the representation space to
alleviate neighbor bias. Finally, we use the joint training mechanism to adjust
the effect of structural equivalence on the model to fit datasets with
different characteristics. We conducted experiments on the node classification
task across seven graph datasets. The results show that the model performance
can be effectively improved using a strategy of topological signal enhancement.
Related papers
- Neural Gaussian Similarity Modeling for Differential Graph Structure
Learning [24.582257964387402]
We construct a differential graph structure learning model by replacing the non-differentiable nearest neighbor sampling with a differentiable sampling.
To alleviate this issue, the bell-shaped Gaussian Similarity (GauSim) modeling is proposed to sample non-nearest neighbors.
We develop a scalable method by transferring the large-scale graph to the transition graph to significantly reduce the complexity.
arXiv Detail & Related papers (2023-12-15T02:45:33Z) - A GAN Approach for Node Embedding in Heterogeneous Graphs Using Subgraph Sampling [33.50085646298074]
We propose a novel framework that combines Graph Neural Network (GNN) and Generative Adrial Network (GAN) to enhance classification for underrepresented node classes.
The framework incorporates an advanced edge generation and selection module, enabling the simultaneous creation of synthetic nodes and edges.
arXiv Detail & Related papers (2023-12-11T16:52:20Z) - Optimality of Message-Passing Architectures for Sparse Graphs [13.96547777184641]
We study the node classification problem on feature-decorated graphs in the sparse setting, i.e., when the expected degree of a node is $O(1)$ in the number of nodes.
We introduce a notion of Bayes optimality for node classification tasks, called local Bayes optimality.
We show that the optimal message-passing architecture interpolates between a standard in the regime of low graph signal and a typical in the regime of high graph signal.
arXiv Detail & Related papers (2023-05-17T17:31:20Z) - Optimal Propagation for Graph Neural Networks [51.08426265813481]
We propose a bi-level optimization approach for learning the optimal graph structure.
We also explore a low-rank approximation model for further reducing the time complexity.
arXiv Detail & Related papers (2022-05-06T03:37:00Z) - Heterogeneous Graph Neural Networks using Self-supervised Reciprocally
Contrastive Learning [102.9138736545956]
Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs.
We develop for the first time a novel and robust heterogeneous graph contrastive learning approach, namely HGCL, which introduces two views on respective guidance of node attributes and graph topologies.
In this new approach, we adopt distinct but most suitable attribute and topology fusion mechanisms in the two views, which are conducive to mining relevant information in attributes and topologies separately.
arXiv Detail & Related papers (2022-04-30T12:57:02Z) - Curvature Graph Generative Adversarial Networks [31.763904668737304]
Generative adversarial network (GAN) is widely used for generalized and robust learning on graph data.
Existing GAN-based graph representation methods generate negative samples by random walk or traverse in discrete space.
CurvGAN consistently and significantly outperforms the state-of-the-art methods across multiple tasks.
arXiv Detail & Related papers (2022-03-03T10:00:32Z) - Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised
Node Classification [59.06717774425588]
We propose the Explicit Pairwise Factorized Graph Neural Network (EPFGNN), which models the whole graph as a partially observed Markov Random Field.
It contains explicit pairwise factors to model output-output relations and uses a GNN backbone to model input-output relations.
We conduct experiments on various datasets, which shows that our model can effectively improve the performance for semi-supervised node classification on graphs.
arXiv Detail & Related papers (2021-07-27T19:47:53Z) - Topological Regularization for Graph Neural Networks Augmentation [12.190045459064413]
We propose a feature augmentation method for graph nodes based on topological regularization.
We have carried out extensive experiments on a large number of datasets to prove the effectiveness of our model.
arXiv Detail & Related papers (2021-04-03T01:37:44Z) - Node Similarity Preserving Graph Convolutional Networks [51.520749924844054]
Graph Neural Networks (GNNs) explore the graph structure and node features by aggregating and transforming information within node neighborhoods.
We propose SimP-GCN that can effectively and efficiently preserve node similarity while exploiting graph structure.
We validate the effectiveness of SimP-GCN on seven benchmark datasets including three assortative and four disassorative graphs.
arXiv Detail & Related papers (2020-11-19T04:18:01Z) - CatGCN: Graph Convolutional Networks with Categorical Node Features [99.555850712725]
CatGCN is tailored for graph learning when the node features are categorical.
We train CatGCN in an end-to-end fashion and demonstrate it on semi-supervised node classification.
arXiv Detail & Related papers (2020-09-11T09:25:17Z) - Graph Inference Learning for Semi-supervised Classification [50.55765399527556]
We propose a Graph Inference Learning framework to boost the performance of semi-supervised node classification.
For learning the inference process, we introduce meta-optimization on structure relations from training nodes to validation nodes.
Comprehensive evaluations on four benchmark datasets demonstrate the superiority of our proposed GIL when compared against state-of-the-art methods.
arXiv Detail & Related papers (2020-01-17T02:52:30Z)
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.