Laplacian Regularized Few-Shot Learning
We propose a transductive Laplacian-regularized inference for few-shot tasks. Given any feature embedding learned from the base classes, we minimize a quadratic binary-assignment function containing two terms: (1) a unary term assign- ing query samples to the nearest class prototype, and (2) a pairwise Laplacian term encouraging nearby query samples to have consistent label as- signments. Our transductive inference does not re-train the base model, and can be viewed as a graph clustering of the query set, subject to super- vision constraints from the support set. We derive a computationally efficient bound optimizer of a relaxation of our function, which computes inde- pendent (parallel) updates for each query sample, while guaranteeing convergence. Following a sim- ple cross-entropy training on the base classes, and without complex meta-learning strategies, we con- ducted comprehensive experiments over five few- shot learning benchmarks. Our LaplacianShot consistently outperforms state-of-the-art methods by significant margins across different models, settings, and data sets. Furthermore, our trans- ductive inference is very fast, with computational times that are close to inductive inference, and can be used for large-scale few-shot tasks.
Code (2)
Tasks
ClusteringFew-Shot Image ClassificationFew-Shot LearningGraph ClusteringMeta-LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Laplacian Regularized Few-Shot Learning
We propose a transductive Laplacian-regularized inference for few-shot tasks. Given any feature embedding learned from the base classes, we minimize a quadratic binary-assignment function containing two terms: (1) a unar…
ClusteringFew-Shot Image ClassificationFew-Shot LearningGraph Clustering+1Semi-supervised Learning with Regularized Laplacian
We study a semi-supervised learning method based on the similarity graph and RegularizedLaplacian. We give convenient optimization formulation of the Regularized Laplacian method and establishits various properties. In p…
General ClassificationRegularized Laplacian Estimation and Fast Eigenvector Approximation
Recently, Mahoney and Orecchia demonstrated that popular diffusion-based procedures to compute a quick approximation to the first nontrivial eigenvector of a data graph Laplacian exactly solve certain regularized Semi-De…
regressionDual regularized Laplacian spectral clustering methods on community detection
Spectral clustering methods are widely used for detecting clusters in networks for community detection, while a small change on the graph Laplacian matrix could bring a dramatic improvement. In this paper, we propose a d…
ClusteringCommunity DetectionStochastic Block ModelDifference-of-Convex Regularization for Graph Learning by Differentiable Programming
Laplacian-regularized minimization is fundamental in signal processing and machine learning, but is limited by the dense and ill-conditioned nature of the graph Laplacian pseudoinverse. While the Laplacian itself is spar…
Graph Learning