XLDA: Linear Discriminant Analysis for Scaling Continual Learning to Extreme Classification at the Edge

TL;DR

This paper introduces XLDA, a scalable Linear Discriminant Analysis framework optimized for extreme classification at the edge, enabling efficient training and inference on datasets with tens of thousands of classes.

Contribution

XLDA extends LDA-based class-incremental learning to extreme classification scenarios and provides optimizations for edge deployment with limited compute resources.

Findings

Achieved up to 42x training speedup with batched approach

Realized up to 5x inference speedup using nearest neighbor search

Successfully applied to datasets with over 80,000 classes

Abstract

Streaming Linear Discriminant Analysis (LDA) while proven in Class-incremental Learning deployments at the edge with limited classes (upto 1000), has not been proven for deployment in extreme classification scenarios. In this paper, we present: (a) XLDA, a framework for Class-IL in edge deployment where LDA classifier is proven to be equivalent to FC layer including in extreme classification scenarios, and (b) optimizations to enable XLDA-based training and inference for edge deployment where there is a constraint on available compute resources. We show up to 42x speed up using a batched training approach and up to 5x inference speedup with nearest neighbor search on extreme datasets like AliProducts (50k classes) and Google Landmarks V2 (81k classes)