Graph Matching with Bi-level Noisy Correspondence

• URL: http://arxiv.org/abs/2212.04085v3
• Date: Sat, 5 Aug 2023 08:07:07 GMT
• Title: Graph Matching with Bi-level Noisy Correspondence
• Authors: Yijie Lin, Mouxing Yang, Jun Yu, Peng Hu, Changqing Zhang, Xi Peng
• Abstract summary: Bi-level Noisy Correspondence (BNC) refers to node-level noisy correspondence (NNC) and edge-level noisy correspondence (ENC)
• Score: 43.071988798418886
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we study a novel and widely existing problem in graph matching (GM), namely, Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence (NNC) and edge-level noisy correspondence (ENC). In brief, on the one hand, due to the poor recognizability and viewpoint differences between images, it is inevitable to inaccurately annotate some keypoints with offset and confusion, leading to the mismatch between two associated nodes, i.e., NNC. On the other hand, the noisy node-to-node correspondence will further contaminate the edge-to-edge correspondence, thus leading to ENC. For the BNC challenge, we propose a novel method termed Contrastive Matching with Momentum Distillation. Specifically, the proposed method is with a robust quadratic contrastive loss which enjoys the following merits: i) better exploring the node-to-node and edge-to-edge correlations through a GM customized quadratic contrastive learning paradigm; ii) adaptively penalizing the noisy assignments based on the confidence estimated by the momentum teacher. Extensive experiments on three real-world datasets show the robustness of our model compared with 12 competitive baselines. The code is available at https://github.com/XLearning-SCU/2023-ICCV-COMMON.

Related papers

• DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noise [53.55187452152358]
  This paper proposes a novel method, Dual-Standard Semantic Homogeneity with Dynamic Optimization (DREAM) for reliable, relation-informed optimization on graphs with label noise.<n>Specifically, we design a relation-informed dynamic optimization framework that iteratively reevaluates the reliability of each labeled node in the graph.
  arXiv  Detail & Related papers  (2026-01-24T12:54:18Z)
• EDN: A Novel Edge-Dependent Noise Model for Graph Data [0.2812395851874055]
  Edge-Dependent Noise (EDN) addresses the limitation of node label noise models.<n>EDN posits that in real-world scenarios, label noise may be influenced by the connections between nodes.<n>We show that 2 variants of EDN lead to greater performance degradation in both Graph Neural Networks (GNNs) and existing noise-robust algorithms.
  arXiv  Detail & Related papers  (2025-06-13T00:05:00Z)
• Bilateral Unsymmetrical Graph Contrastive Learning for Recommendation [12.945782054710113]
  We propose a novel framework for recommendation tasks called Bilateral Unsymmetrical Graph Contrastive Learning (BusGCL) BusGCL considers the bilateral unsymmetry on user-item node relation density for sliced user and item graph reasoning better with bilateral slicing contrastive training. Comprehensive experiments on two public datasets have proved the superiority of BusGCL in comparison to various recommendation methods.
  arXiv  Detail & Related papers  (2024-03-22T09:58:33Z)
• CSGNN: Conquering Noisy Node labels via Dynamic Class-wise Selection [45.83801634434111]
  We introduce a novel Class-wise Selection for Graph Neural Networks, dubbed CSGNN. To tackle the class imbalance issue, we introduce a dynamic class-wise selection mechanism, leveraging the clustering technique to identify clean nodes. To alleviate the problem of noisy labels, built on the concept of the memorization effect, CSGNN prioritizes learning from clean nodes before noisy ones.
  arXiv  Detail & Related papers  (2023-11-20T00:57:30Z)
• Noisy-Correspondence Learning for Text-to-Image Person Re-identification [50.07634676709067]
  We propose a novel Robust Dual Embedding method (RDE) to learn robust visual-semantic associations even with noisy correspondences. Our method achieves state-of-the-art results both with and without synthetic noisy correspondences on three datasets.
  arXiv  Detail & Related papers  (2023-08-19T05:34:13Z)
• Commonsense Knowledge Graph Completion Via Contrastive Pretraining and Node Clustering [14.854971279160933]
  We propose a new CSKG completion framework based on Contrastive Pretraining and Node Clustering. We evaluate our CPNC approach on two CSKG completion benchmarks (CN-100K and ATOMIC), where CPNC outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-26T15:24:32Z)
• Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classification [1.3190581566723918]
  Graph Neural Networks (GNNs) have proven to be powerful in many graph-based applications. However, they fail to generalize well under heterophilic setups.
  arXiv  Detail & Related papers  (2023-02-20T04:23:34Z)
• Interpolation-based Correlation Reduction Network for Semi-Supervised Graph Learning [49.94816548023729]
  We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN) In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries. By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
  arXiv  Detail & Related papers  (2022-06-06T14:26:34Z)
• Deep Probabilistic Graph Matching [72.6690550634166]
  We propose a deep learning-based graph matching framework that works for the original QAP without compromising on the matching constraints. The proposed method is evaluated on three popularly tested benchmarks (Pascal VOC, Willow Object and SPair-71k) and it outperforms all previous state-of-the-arts on all benchmarks.
  arXiv  Detail & Related papers  (2022-01-05T13:37:27Z)
• Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions [123.07967420310796]
  This paper bridges the gap by proposing a pairwise framework for noisy node classification on graphs. PI-GNN relies on the PI as a primary learning proxy in addition to the pointwise learning from the noisy node class labels. Our proposed framework PI-GNN contributes two novel components: (1) a confidence-aware PI estimation model that adaptively estimates the PI labels, and (2) a decoupled training approach that leverages the estimated PI labels.
  arXiv  Detail & Related papers  (2021-06-14T14:23:08Z)
• Sequential Graph Convolutional Network for Active Learning [53.99104862192055]
  We propose a novel pool-based Active Learning framework constructed on a sequential Graph Convolution Network (GCN) With a small number of randomly sampled images as seed labelled examples, we learn the parameters of the graph to distinguish labelled vs unlabelled nodes. We exploit these characteristics of GCN to select the unlabelled examples which are sufficiently different from labelled ones.
  arXiv  Detail & Related papers  (2020-06-18T00:55:10Z)

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.