Relational Generalized Few-Shot Learning

Abstract

Transferring learned models to novel tasks is a challenging problem, particularly if only very few labeled examples are available. Although this few-shot learning setup has received a lot of attention recently, most proposed methods focus on discriminating novel classes only. Instead, we consider the extended setup of generalized few-shot learning (GFSL), where the model is required to perform classification on the joint label space consisting of both previously seen and novel classes. We propose a graph-based framework that explicitly models relationships between all seen and novel classes in the joint label space. Our model Graph-convolutional Global Prototypical Networks (GcGPN) incorporates these inter-class relations using graph-convolution in order to embed novel class representations into the existing space of previously seen classes in a globally consistent manner. Our approach ensures both fast adaptation and global discrimination, which is the major challenge in GFSL. We demonstrate the benefits of our model on two challenging benchmark datasets.

References in corpus (17)

• Distributed Representations of Words and Phrases and their Compositionality
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Graph Convolutional Matrix Completion
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Label-Embedding for Image Classification
• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• A simple neural network module for relational reasoning
• Few-Shot Learning with Graph Neural Networks
• Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly
• Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
• An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
• A Semantic Loss Function for Deep Learning with Symbolic Knowledge
• Discriminative k-shot learning using probabilistic models
• Edge-labeling Graph Neural Network for Few-shot Learning
• Few-Shot Learning with Global Class Representations

Cited by in corpus (4)

• Graph signal processing for machine learning: A review and new perspectives
• CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection
• Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction
• End-to-end One-shot Human Parsing