mlsanityData to 14 Oct 2026

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

arXiv 2307.11317 ↗First posted 21 Jul 2023cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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)

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 21 Jul 2023.

Builds on

17 of 29 references.

References · 17

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  4. 2016Learning without Forgettingcited by 2,496
  5. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  6. 2017Gradient Episodic Memory for Continual Learningcited by 1,898
  7. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  8. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 309
  9. 2018Task-Free Continual Learningcited by 221
  10. 2019Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysiscited by 92
  11. 2020PECOS: Prediction for Enormous and Correlated Output Spacescited by 50
  12. 2022The Met Dataset: Instance-level Recognition for Artworkscited by 40
5 more
  1. 2021DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documentscited by 37
  2. 2022NGAME: Negative Mining-aware Mini-batching for Extreme Classificationcited by 32
  3. 2020Weakly Supervised Learning with Side Information for Noisy Labeled Imagescited by 30
  4. 2020Two-stage Discriminative Re-ranking for Large-scale Landmark Retrievalcited by 18
  5. 2021Large-Scale Training System for 100-Million Classification at Alibabacited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Post-Training Quantization of Generative and Discriminative LSTM Text Classifiers: A Study of Calibration, Class Balance, and Robustness
  2. 2026ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing
  3. 2024Advancing Cross-domain Discriminability in Continual Learning of Vision-Language Models
  4. 2023Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform
  5. 2025No Forgetting Learning: Buffer-free Continual Learning Classification
  6. 2024Class incremental learning with probability dampening and cascaded gated classifier
  7. 2026CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning
  8. 2022On Generalizing Beyond Domains in Cross-Domain Continual Learning