# Accelerated Training for Massive Classification via Dynamic Class Selection

arXiv: https://arxiv.org/abs/1801.01687 · HTML: https://mlsanity.com/paper/1801.01687/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jan 2018.

## Built on by (most cited first, 16 of 16)

- [Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC](https://mlsanity.com/paper/2203.15565/) (2022)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [Dynamic Class Queue for Large Scale Face Recognition In the Wild](https://mlsanity.com/paper/2105.11113/) (2021)
- [An Efficient Training Approach for Very Large Scale Face Recognition](https://mlsanity.com/paper/2105.10375/) (2021)
- [Massively Scaling Heteroscedastic Classifiers](https://mlsanity.com/paper/2301.12860/) (2023)
- [Large-Scale Training System for 100-Million Classification at Alibaba](https://mlsanity.com/paper/2102.06025/) (2021)
- [Learn to Cluster Faces via Pairwise Classification](https://mlsanity.com/paper/2205.13117/) (2022)
- [Prototype Memory for Large-scale Face Representation Learning](https://mlsanity.com/paper/2105.02103/) (2021)
- [Inter-class Discrepancy Alignment for Face Recognition](https://mlsanity.com/paper/2103.01559/) (2021)
- [EXACT: How to Train Your Accuracy](https://mlsanity.com/paper/2205.09615/) (2022)
- [SPT: Fine-Tuning Transformer-based Language Models Efficiently with Sparsification](https://mlsanity.com/paper/2312.10365/) (2023)
- [GIF: Generative Inspiration for Face Recognition at Scale](https://mlsanity.com/paper/2505.03012/) (2025)
- [EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence](https://mlsanity.com/paper/2511.10834/) (2025)
- [CARLS: Cross-platform Asynchronous Representation Learning System](https://mlsanity.com/paper/2105.12849/) (2021)
- [Multi-Head Encoding for Extreme Label Classification](https://mlsanity.com/paper/2412.10182/) (2024)
- [Adaptive Sparse Softmax: An Effective and Efficient Softmax Variant](https://mlsanity.com/paper/2508.03175/) (2025)

## Abstract (arXiv)

Massive classification, a classification task defined over a vast number of classes (hundreds of thousands or even millions), has become an essential part of many real-world systems, such as face recognition. Existing methods, including the deep networks that achieved remarkable success in recent years, were mostly devised for problems with a moderate number of classes. They would meet with substantial difficulties, e.g. excessive memory demand and computational cost, when applied to massive problems. We present a new method to tackle this problem. This method can efficiently and accurately identify a small number of "active classes" for each mini-batch, based on a set of dynamic class hierarchies constructed on the fly. We also develop an adaptive allocation scheme thereon, which leads to a better tradeoff between performance and cost. On several large-scale benchmarks, our method significantly reduces the training cost and memory demand, while maintaining competitive performance.