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

Karan Shah, Vishruth Veerendranath, Anushka Hebbar, Raghavendra Bhat
7/21/2023
cs.LGcs.AIcs.CV

No confident code implementation found for this paper.

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)

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Lightweight Edge Learning via Dataset Pruning

78% match1 repo12026

From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices

78% match2025

A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques

78% match2023

ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing

77% match2026

Continual Learning at the Edge: An Agnostic IIoT Architecture

77% match2025

LODAP: On-Device Incremental Learning Via Lightweight Operations and Data Pruning

77% match1 repo32025

Cite this paper

@article{shah2023xlda,
  title  = {XLDA: Linear Discriminant Analysis for Scaling Continual Learning to Extreme Classification at the Edge},
  author = {Karan Shah and Vishruth Veerendranath and Anushka Hebbar and Raghavendra Bhat},
  year   = {2023},
  eprint = {2307.11317},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.11317v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.11317.svg)](https://codeofpaper.com/paper/2307.11317)

Discussion