Sequential Graph Convolutional Network for Active Learning

Abstract

We propose a novel pool-based Active Learning framework constructed on a sequential Graph Convolution Network (GCN). Each image's feature from a pool of data represents a node in the graph and the edges encode their similarities. 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 by minimising the binary cross-entropy loss. GCN performs message-passing operations between the nodes, and hence, induces similar representations of the strongly associated nodes. We exploit these characteristics of GCN to select the unlabelled examples which are sufficiently different from labelled ones. To this end, we utilise the graph node embeddings and their confidence scores and adapt sampling techniques such as CoreSet and uncertainty-based methods to query the nodes. We flip the label of newly queried nodes from unlabelled to labelled, re-train the learner to optimise the downstream task and the graph to minimise its modified objective. We continue this process within a fixed budget. We evaluate our method on 6 different benchmarks:4 real image classification, 1 depth-based hand pose estimation and 1 synthetic RGB image classification datasets. Our method outperforms several competitive baselines such as VAAL, Learning Loss, CoreSet and attains the new state-of-the-art performance on multiple applications The implementations can be found here: https://github.com/razvancaramalau/Sequential-GCN-for-Active-Learning

arXiv commentAccepted as Poster at CVPR 2021

References in corpus (18)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Inductive Representation Learning on Large Graphs
• Geometric deep learning: going beyond Euclidean data
• Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
• Bayesian Active Learning for Classification and Preference Learning
• Few-Shot Learning with Graph Neural Networks
• Variational Autoencoder for Deep Learning of Images, Labels and Captions
• Hands Deep in Deep Learning for Hand Pose Estimation
• BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
• PairNorm: Tackling Oversmoothing in GNNs
• Bayesian Batch Active Learning as Sparse Subset Approximation
• Active Learning for Graph Embedding
• Sampling Strategies for GAN Synthetic Data
• Active Learning for Graph Neural Networks via Node Feature Propagation
• Semantic Redundancies in Image-Classification Datasets: The 10% You Don't Need
• Active Nearest-Neighbor Learning in Metric Spaces
• Regional based query in graph active learning