Noisy Node Classification by Bi-level Optimization based Multi-teacher Distillation

• URL: http://arxiv.org/abs/2404.17875v2
• Date: Wed, 8 May 2024 06:56:53 GMT
• Title: Noisy Node Classification by Bi-level Optimization based Multi-teacher Distillation
• Authors: Yujing Liu, Zongqian Wu, Zhengyu Lu, Ci Nie, Guoqiu Wen, Ping Hu, Xiaofeng Zhu,
• Abstract summary: We propose a new multi-teacher distillation method based on bi-level optimization (namely BO-NNC) to conduct noisy node classification on the graph data. Specifically, we first employ multiple self-supervised learning methods to train diverse teacher models, and then aggregate their predictions through a teacher weight matrix. Furthermore, we design a new bi-level optimization strategy to dynamically adjust the teacher weight matrix based on the training progress of the student model.
• Score: 17.50773984154023
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Previous graph neural networks (GNNs) usually assume that the graph data is with clean labels for representation learning, but it is not true in real applications. In this paper, we propose a new multi-teacher distillation method based on bi-level optimization (namely BO-NNC), to conduct noisy node classification on the graph data. Specifically, we first employ multiple self-supervised learning methods to train diverse teacher models, and then aggregate their predictions through a teacher weight matrix. Furthermore, we design a new bi-level optimization strategy to dynamically adjust the teacher weight matrix based on the training progress of the student model. Finally, we design a label improvement module to improve the label quality. Extensive experimental results on real datasets show that our method achieves the best results compared to state-of-the-art methods.

Related papers

• Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification [49.09505771145326]
  We propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
  arXiv  Detail & Related papers  (2024-04-26T06:00:27Z)
• MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning [17.70842402755857]
  We develop the first meta-learning approach for evaluation-free graph learning model selection, called MetaGL. To quantify similarities across a wide variety of graphs, we introduce specialized meta-graph features. Then we design G-M network, which represents the relations among graphs and models, and develop a graph-based meta-learner.
  arXiv  Detail & Related papers  (2022-06-18T20:43:38Z)
• 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)
• SLADE: A Self-Training Framework For Distance Metric Learning [75.54078592084217]
  We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional unlabeled data. We first train a teacher model on the labeled data and use it to generate pseudo labels for the unlabeled data. We then train a student model on both labels and pseudo labels to generate final feature embeddings.
  arXiv  Detail & Related papers  (2020-11-20T08:26:10Z)
• MetAL: Active Semi-Supervised Learning on Graphs via Meta Learning [2.903711704663904]
  We propose MetAL, an AL approach that selects unlabeled instances that directly improve the future performance of a classification model. We demonstrate that MetAL efficiently outperforms existing state-of-the-art AL algorithms.
  arXiv  Detail & Related papers  (2020-07-22T06:59:49Z)
• Active Learning on Attributed Graphs via Graph Cognizant Logistic Regression and Preemptive Query Generation [37.742218733235084]
  We propose a novel graph-based active learning algorithm for the task of node classification in attributed graphs. Our algorithm uses graph cognizant logistic regression, equivalent to a linearized graph convolutional neural network (GCN) for the prediction phase and maximizes the expected error reduction in the query phase. We conduct experiments on five public benchmark datasets, demonstrating a significant improvement over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-07-09T18:00:53Z)
• Heuristic Semi-Supervised Learning for Graph Generation Inspired by Electoral College [80.67842220664231]
  We propose a novel pre-processing technique, namely ELectoral COllege (ELCO), which automatically expands new nodes and edges to refine the label similarity within a dense subgraph. In all setups tested, our method boosts the average score of base models by a large margin of 4.7 points, as well as consistently outperforms the state-of-the-art.
  arXiv  Detail & Related papers  (2020-06-10T14:48:48Z)
• COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization [60.07531696857743]
  Co-Learns DNNs and soft labels through Alternating Minimization of two objectives. We propose COLAM framework that Co-Learns DNNs and soft labels through Alternating Minimization of two objectives.
  arXiv  Detail & Related papers  (2020-04-26T17:50:20Z)
• Distilling Knowledge from Graph Convolutional Networks [146.71503336770886]
  Existing knowledge distillation methods focus on convolutional neural networks (CNNs) We propose the first dedicated approach to distilling knowledge from a pre-trained graph convolutional network (GCN) model. We show that our method achieves the state-of-the-art knowledge distillation performance for GCN models.
  arXiv  Detail & Related papers  (2020-03-23T18:23:11Z)

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.