Back to papers
ANN Softmax: Acceleration of Extreme Classification Training
Summary: ANN Softmax: GPU-optimized sampling-based softmax for extreme classification with millions of classes, using an inverted-file index and binary quantization to boost recall. GPU kernels plus sample-grouping preserve full-softmax accuracy with 1/10 sampling, achieving 4.3x speedup and enabling 300M-class training on large GPU clusters.
(summarized by gpt-5-nano on Feb 09 2026)
- Paper ID
- 12614
- Venue
- VLDB
- Year
- 2022
- Pagerank
- 4.4584416e-05
- Overall Rank
- 8,709 | 39.48%
- DOI
-
10.14778/3485450.3485451
Incoming Non-self Citations Over Time
Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
Outgoing Citations (Sorted by Pagerank)
Showing 13 of 13 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank |
Cited Paper |
Year |
Venue |
Pagerank |
| 34 |
Similarity Search in High Dimensions via Hashing |
1999 |
VLDB |
0.00076824554 |
| 210 |
Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph |
2019 |
VLDB |
0.00034086264 |
| 399 |
Multi-Probe LSH: Efficient Indexing for High-Dimensional Similarity Search |
2007 |
VLDB |
0.00024359304 |
| 411 |
PyTorch Distributed: Experiences on Accelerating Data Parallel Training |
2020 |
VLDB |
0.00023881138 |
| 514 |
TURL: Table Understanding through Representation Learning |
2021 |
VLDB |
0.00021280726 |
| 1,013 |
HD-Index: Pushing the Scalability-Accuracy Boundary for Approximate kNN Search in High-Dimensional Spaces |
2018 |
VLDB |
0.00014632051 |
| 1,252 |
Cache locality is not enough: High-Performance Nearest Neighbor Search with Product Quantization Fast Scan |
2016 |
VLDB |
0.00013023834 |
| 1,713 |
Chimera: Large-Scale Classification using Machine Learning, Rules, and Crowdsourcing |
2014 |
VLDB |
0.00010785323 |
| 3,019 |
DSH: Data Sensitive Hashing for High-Dimensional k-NN Search |
2014 |
SIGMOD |
7.699097e-05 |
| 3,212 |
Panorama: A Data System for Unbounded Vocabulary Querying over Video |
2020 |
VLDB |
7.3772955e-05 |
| 3,372 |
CROSSBOW: Scaling Deep Learning with Small Batch Sizes on Multi-GPU Servers |
2019 |
VLDB |
7.1633912e-05 |
| 4,749 |
ODIN: Automated Drift Detection and Recovery in Video Analytics |
2020 |
VLDB |
5.9428569e-05 |
| 8,829 |
A Distributed System for Large-scale n-gram Language Models at Tencent |
2019 |
VLDB |
4.4364351e-05 |
Semantically Similar Papers
| Overall Rank |
Paper |
Year |
Venue |
Pagerank |
| 2,690 |
Accelerating Recommendation System Training by Leveraging Popular Choices |
2022 |
VLDB |
8.2911466e-05 |
| 9,596 |
Scalable Graph Convolutional Network Training on Distributed-Memory Systems |
2023 |
VLDB |
4.3150788e-05 |
| 8,373 |
Fast Neural Ranking on Bipartite Graph Indices |
2022 |
VLDB |
4.5282739e-05 |
| 8,807 |
FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement |
2023 |
SIGMOD |
4.4413307e-05 |
| 10,537 |
Two Birds with One Stone: Efficient Deep Learning over Mislabeled Data through Subset Selection |
2025 |
SIGMOD |
4.1905499e-05 |
| 7,568 |
ADGNN: Towards Scalable GNN Training with Aggregation-Difference Aware Sampling |
2023 |
SIGMOD |
4.7044808e-05 |
| 10,042 |
Accelerating High-Dimensional ANN Search via Skipping Redundant Distance Computations |
2026 |
SIGMOD |
4.1905499e-05 |
| 3,291 |
Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics |
2021 |
VLDB |
7.2607192e-05 |
| 5,744 |
Efficient Algorithms for Crowd-Aided Categorization |
2020 |
VLDB |
5.343155e-05 |
| 10,167 |
FlashANNS: GPU-Driven Asynchronous I/O Pipelining for Eliminating Storage-Compute Bottlenecks in Billion-Scale Similarity Search |
2026 |
SIGMOD |
4.1905499e-05 |