Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification

• URL: http://arxiv.org/abs/2001.09849v4
• Date: Thu, 28 Jan 2021 07:56:12 GMT
• Title: Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification
• Authors: Yuqing Hu, Vincent Gripon, St\'ephane Pateux
• Abstract summary: In few-shot classification, the aim is to learn models able to discriminate classes using only a small number of labeled examples. We propose a new method that relies on graphs only to interpolate feature vectors instead, resulting in a transductive learning setting.
• Score: 2.922007656878633
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In few-shot classification, the aim is to learn models able to discriminate classes using only a small number of labeled examples. In this context, works have proposed to introduce Graph Neural Networks (GNNs) aiming at exploiting the information contained in other samples treated concurrently, what is commonly referred to as the transductive setting in the literature. These GNNs are trained all together with a backbone feature extractor. In this paper, we propose a new method that relies on graphs only to interpolate feature vectors instead, resulting in a transductive learning setting with no additional parameters to train. Our proposed method thus exploits two levels of information: a) transfer features obtained on generic datasets, b) transductive information obtained from other samples to be classified. Using standard few-shot vision classification datasets, we demonstrate its ability to bring significant gains compared to other works.

Related papers

• Transductive Linear Probing: A Novel Framework for Few-Shot Node Classification [56.17097897754628]
  We show that transductive linear probing with self-supervised graph contrastive pretraining can outperform the state-of-the-art fully supervised meta-learning based methods under the same protocol. We hope this work can shed new light on few-shot node classification problems and foster future research on learning from scarcely labeled instances on graphs.
  arXiv  Detail & Related papers  (2022-12-11T21:10:34Z)
• Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems [9.660129425150926]
  Cross entropy loss can easily lead us to find models which demonstrate severe overfitting behavior. In this paper, we prove that the existing cross entropy loss minimization for training DNN classifiers essentially learns the conditional entropy of the underlying data distribution. We propose a mutual information learning framework where we train DNN classifiers via learning the mutual information between the label and input.
  arXiv  Detail & Related papers  (2022-10-03T15:09:19Z)
• A Simple Yet Effective Pretraining Strategy for Graph Few-shot Learning [38.66690010054665]
  We propose a simple transductive fine-tuning based framework as a new paradigm for graph few-shot learning. For pretraining, we propose a supervised contrastive learning framework with data augmentation strategies specific for few-shot node classification.
  arXiv  Detail & Related papers  (2022-03-29T22:30:00Z)
• Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
  Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. We present a novel Graph Matching based GNN Pre-Training framework, called GMPT. The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
  arXiv  Detail & Related papers  (2022-03-03T09:53:53Z)
• Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach [80.8446673089281]
  We propose a new learning paradigm with graph representation and learning. Our framework contains two modules: 1) a backbone network (e.g., feedforward neural nets) as a lower model takes features as input and outputs predicted labels; 2) a graph neural network as an upper model learns to extrapolate embeddings for new features via message passing over a feature-data graph built from observed data.
  arXiv  Detail & Related papers  (2021-10-09T09:02:45Z)
• From Canonical Correlation Analysis to Self-supervised Graph Neural Networks [99.44881722969046]
  We introduce a conceptually simple yet effective model for self-supervised representation learning with graph data. We optimize an innovative feature-level objective inspired by classical Canonical Correlation Analysis. Our method performs competitively on seven public graph datasets.
  arXiv  Detail & Related papers  (2021-06-23T15:55:47Z)
• ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning [53.09923823663554]
  Class-level knowledge can be easily learned by humans from just a handful of samples. We propose an Explicit Class Knowledge Propagation Network (ECKPN) to address this problem. We conduct extensive experiments on four few-shot classification benchmarks, and the experimental results show that the proposed ECKPN significantly outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-16T02:29:43Z)
• Few-Shot Object Detection via Knowledge Transfer [21.3564383157159]
  Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes. In this paper, we introduce a few-shot object detection via knowledge transfer, which aims to detect objects from a few training examples.
  arXiv  Detail & Related papers  (2020-08-28T06:35:27Z)
• Geometric graphs from data to aid classification tasks with graph convolutional networks [0.0]
  We show that, even if additional relational information is not available in the data set, one can improve classification by constructing geometric graphs from the features themselves. The improvement in classification accuracy is maximized by graphs that capture sample similarity with relatively low edge density.
  arXiv  Detail & Related papers  (2020-05-08T15:00:45Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

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.