Robust Graph Structure Learning via Multiple Statistical Tests
Not on the map. Why?
Abstract (arXiv)
Graph structure learning aims to learn connectivity in a graph from data. It is particularly important for many computer vision related tasks since no explicit graph structure is available for images for most cases. A natural way to construct a graph among images is to treat each image as a node and assign pairwise image similarities as weights to corresponding edges. It is well known that pairwise similarities between images are sensitive to the noise in feature representations, leading to unreliable graph structures. We address this problem from the viewpoint of statistical tests. By viewing the feature vector of each node as an independent sample, the decision of whether creating an edge between two nodes based on their similarity in feature representation can be thought as a it single statistical test. To improve the robustness in the decision of creating an edge, multiple samples are drawn and integrated by it multiple statistical tests to generate a more reliable similarity measure, consequentially more reliable graph structure. The corresponding elegant matrix form named B-Attention is designed for efficiency. The effectiveness of multiple tests for graph structure learning is verified both theoretically and empirically on multiple clustering and ReID benchmark datasets. Source codes are available at https://github.com/Thomas-wyh/B-Attention.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 37 of its 84 references that are in the map. First posted on arXiv 8 Oct 2022.
Builds on
37 of 84 references.
References · 37
- 2017Attention Is All You Needcited by 60,361
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
- 2016Optimization Methods for Large-Scale Machine Learningcited by 1,150
- 2019Heterogeneous Graph Attention Networkcited by 734
- 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 624
- 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
- 2020Heterogeneous Graph Transformercited by 582
- 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 549
25 more
- 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
- 2021TransReID: Transformer-based Object Re-Identificationcited by 435
- 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
- 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 262
- 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
- 2019Learning Discrete Structures for Graph Neural Networkscited by 231
- 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 214
- 2018Adaptive Graph Convolutional Neural Networkscited by 155
- 2020Retrieval-Augmented Generation for Code Summarization via Hybrid GNNcited by 89
- 2019Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformercited by 88
- 2020Differentiable Graph Module (DGM) for Graph Convolutional Networkscited by 86
- 2020Location-aware Graph Convolutional Networks for Video Question Answeringcited by 80
- 2017A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Rankingcited by 74
- 2019Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generationcited by 57
- 2019Linkage Based Face Clustering via Graph Convolution Networkcited by 55
- 2019Learning to Cluster Faces on an Affinity Graphcited by 50
- 2020Learning to Cluster Faces via Confidence and Connectivity Estimationcited by 42
- 2019GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehensioncited by 41
- 2018Spectral Feature Transformation for Person Re-identificationcited by 39
- 2019A Flexible Generative Framework for Graph-based Semi-supervised Learningcited by 24
- 2021Structure-Aware Face Clustering on a Large-Scale Graph with bf107 Nodescited by 21
- 2022Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Spacecited by 16
- 2017Face Clustering: Representation and Pairwise Constraintscited by 14
- 2020Learning Graph Structure With A Finite-State Automaton Layercited by 10
- 2020Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video Datacited by 3
Built on by
Citing papers per year: 2024: 1; 2025: 1; 2026: 1.
3 papers.