Graph-LDA: Graph Structure Priors to Improve the Accuracy in Few-Shot Classification

TL;DR

This paper introduces Graph-LDA, a model leveraging graph structure priors to enhance classification accuracy in few-shot learning scenarios with limited labeled data.

Contribution

It proposes a novel classification method that incorporates known graph structures and a single tunable parameter, improving generalization in scarce data conditions.

Findings

Outperforms popular alternatives on real datasets

Effectively incorporates graph priors for better accuracy

Suitable for scenarios with very limited labeled data

Abstract

It is very common to face classification problems where the number of available labeled samples is small compared to their dimension. These conditions are likely to cause underdetermined settings, with high risk of overfitting. To improve the generalization ability of trained classifiers, common solutions include using priors about the data distribution. Among many options, data structure priors, often represented through graphs, are increasingly popular in the field. In this paper, we introduce a generic model where observed class signals are supposed to be deteriorated with two sources of noise, one independent of the underlying graph structure and isotropic, and the other colored by a known graph operator. Under this model, we derive an optimal methodology to classify such signals. Interestingly, this methodology includes a single parameter, making it particularly suitable for cases where available data is scarce. Using various real datasets, we showcase the ability of the proposed model to be implemented in real world scenarios, resulting in increased generalization accuracy compared to popular alternatives.