---
title: "ICML 2021 — accepted papers — Elamur Research"
description: "ICML 2021 — accepted papers: 2 papers in the Elamur Research library, with our summaries, ranked by citations."
canonical: "https://research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2021/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2021/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [ICML](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/) / 2021

# ICML 2021 — accepted papers

ICML 2021 is the 2021 edition of the International Conference on Machine Learning (ICML). OpenAlex lists 196 papers of it; our library holds 2 with our summaries. Below: the most cited papers, every accepted paper, and ours with their topics, authors and institutions.

[**196** papers in the proceedings](#all) · [**2** works in our library](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2021/#works) · [**1,737** citations of these works](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2021/#works)

## Most cited papers

By their OpenAlex citations; a paper with our summary links to its page here, the others to the original.

1. **[SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks ↗](http://proceedings.mlr.press/v139/yang21o/yang21o.pdf)**Lingxiao Yang, Ru‐Yuan Zhang, Lida Li et al.*638 citations*
2. **[HAWQ-V3: Dyadic Neural Network Quantization ↗](http://proceedings.mlr.press/v139/yao21a/yao21a.pdf)**Zhewei Yao, Zhen Dong, Zhangcheng Zheng et al.*37 citations*
3. **[LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs ↗](http://proceedings.mlr.press/v139/ren21a/ren21a.pdf)**Hongyu Ren, Hanjun Dai, Bo Dai et al.*31 citations*
4. **[Representation Subspace Distance for Domain Adaptation Regression ↗](http://proceedings.mlr.press/v139/chen21u/chen21u.pdf)**Xinyang Chen, Sinan Wang, Jianmin Wang et al.*29 citations*
5. **[Ditto: Fair and Robust Federated Learning Through Personalization ↗](http://proceedings.mlr.press/v139/li21h/li21h.pdf)**Tian Li, Shengyuan Hu, Ahmad Beirami et al.*22 citations*
6. **[Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations ↗](http://proceedings.mlr.press/v139/kim21h/kim21h.pdf)**Timothy Kim, Thomas Zhihao Luo, Jonathan W. Pillow et al.*19 citations*
7. **[Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies ↗](http://proceedings.mlr.press/v139/yang21i/yang21i.pdf)**Jimmy Jimmy, Justinian P. Rosca, Karthik Narasimhan et al.*18 citations*
8. **[RAD-TTS: Parallel Flow-Based TTS with Robust Alignment Learning and Diverse Synthesis ↗](https://openreview.net/pdf?id=0NQwnnwAORi)**Kevin J. Shih, Rafael Valle, Rohan Badlani et al.*18 citations*
9. **[Synthesizer: Rethinking Self-Attention for Transformer Models ↗](http://proceedings.mlr.press/v139/tay21a/tay21a.pdf)**Yi Tay, Dara Bahri, Donald Metzler et al.*17 citations*
10. **[Dissecting Supervised Constrastive Learning ↗](http://proceedings.mlr.press/v139/graf21a/graf21a.pdf)**Florian Gräf, Christoph D. Hofer, Marc Niethammer et al.*15 citations*

## All accepted papers (196)

The most cited first; 2 with our summary link to their page here, the others to the original.

1. **[SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks ↗](http://proceedings.mlr.press/v139/yang21o/yang21o.pdf)**Lingxiao Yang, Ru‐Yuan Zhang, Lida Li et al.*638 citations*
2. **[HAWQ-V3: Dyadic Neural Network Quantization ↗](http://proceedings.mlr.press/v139/yao21a/yao21a.pdf)**Zhewei Yao, Zhen Dong, Zhangcheng Zheng et al.*37 citations*
3. **[LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs ↗](http://proceedings.mlr.press/v139/ren21a/ren21a.pdf)**Hongyu Ren, Hanjun Dai, Bo Dai et al.*31 citations*
4. **[Representation Subspace Distance for Domain Adaptation Regression ↗](http://proceedings.mlr.press/v139/chen21u/chen21u.pdf)**Xinyang Chen, Sinan Wang, Jianmin Wang et al.*29 citations*
5. **[Ditto: Fair and Robust Federated Learning Through Personalization ↗](http://proceedings.mlr.press/v139/li21h/li21h.pdf)**Tian Li, Shengyuan Hu, Ahmad Beirami et al.*22 citations*
6. **[Inferring Latent Dynamics Underlying Neural Population Activity via Neural Differential Equations ↗](http://proceedings.mlr.press/v139/kim21h/kim21h.pdf)**Timothy Kim, Thomas Zhihao Luo, Jonathan W. Pillow et al.*19 citations*
7. **[Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies ↗](http://proceedings.mlr.press/v139/yang21i/yang21i.pdf)**Jimmy Jimmy, Justinian P. Rosca, Karthik Narasimhan et al.*18 citations*
8. **[RAD-TTS: Parallel Flow-Based TTS with Robust Alignment Learning and Diverse Synthesis ↗](https://openreview.net/pdf?id=0NQwnnwAORi)**Kevin J. Shih, Rafael Valle, Rohan Badlani et al.*18 citations*
9. **[Synthesizer: Rethinking Self-Attention for Transformer Models ↗](http://proceedings.mlr.press/v139/tay21a/tay21a.pdf)**Yi Tay, Dara Bahri, Donald Metzler et al.*17 citations*
10. **[Dissecting Supervised Constrastive Learning ↗](http://proceedings.mlr.press/v139/graf21a/graf21a.pdf)**Florian Gräf, Christoph D. Hofer, Marc Niethammer et al.*15 citations*
11. **[How Does Loss Function Affect Generalization Performance of Deep Learning? Application to Human Age Estimation ↗](http://proceedings.mlr.press/v139/akbari21a/akbari21a.pdf)**Ali Akbari, Muhammad Awais, Manijeh Bashar et al.*14 citations*
12. **[When Does Data Augmentation Help With Membership Inference Attacks ↗](http://proceedings.mlr.press/v139/kaya21a/kaya21a.pdf)**Yiğitcan Kaya, Tudor Dumitraş*14 citations*
13. **[Modelling Behavioural Diversity for Learning in Open-Ended Games ↗](http://proceedings.mlr.press/v139/perez-nieves21a/perez-nieves21a.pdf)**Nicolas Perez-Nieves, Yaodong Yang, Oliver Slumbers et al.*13 citations*
14. **[One Pass Late Fusion Multi-view Clustering ↗](http://proceedings.mlr.press/v139/liu21l/liu21l.pdf)**Xinwang Liu, Li Liu, Qing Liao et al.*13 citations*
15. **[SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels ↗](http://proceedings.mlr.press/v139/dahiya21a/dahiya21a.pdf)**Kunal Dahiya, Ananye Agarwal, Deepak Saini et al.*13 citations*
16. **[AutoAttend: Automated Attention Representation Search ↗](http://proceedings.mlr.press/v139/guan21a/guan21a.pdf)**Chaoyu Guan, Xin Wang, Wenwu Zhu*11 citations*
17. **[Federated Learning under Arbitrary Communication Patterns ↗](http://proceedings.mlr.press/v139/avdiukhin21a/avdiukhin21a.pdf)**Dmitrii Avdiukhin, Shiva Prasad Kasiviswanathan*11 citations*
18. **[Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off ↗](https://openreview.net/pdf?id=BuD2LmNaU3a)**Rahul Rade, Seyed-Mohsen Moosavi-Dezfooli*11 citations*
19. **[PipeTransformer: Automated Elastic Pipelining for Distributed Training of Large-scale Models ↗](http://proceedings.mlr.press/v139/he21a/he21a.pdf)**Chaoyang He, Li Shen, Mahdi Soltanolkotabi et al.*11 citations*
20. **[Revisiting Rainbow: Promoting more insightful and inclusive deep reinforcement learning research ↗](http://proceedings.mlr.press/v139/ceron21a/ceron21a.pdf)**Johan Obando-Ceron, Pablo Samuel Castro*11 citations*
21. **[Improved OOD Generalization via Adversarial Training and Pretraing ↗](http://proceedings.mlr.press/v139/yi21a/yi21a.pdf)**Mingyang Yi, Lu Hou, Jiacheng Sun et al.*10 citations*
22. **[Sharper Generalization Bounds for Clustering ↗](http://proceedings.mlr.press/v139/li21k/li21k.pdf)**Shaojie Li, Yong Liu*10 citations*
23. **[Understanding and Mitigating Accuracy Disparity in Regression ↗](http://proceedings.mlr.press/v139/chi21a/chi21a.pdf)**Jianfeng Chi, Han Zhao, Geoff Gordon et al.*10 citations*
24. **[Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference ↗](http://proceedings.mlr.press/v139/fu21c/fu21c.pdf)**Yonggan Fu, Qixuan Yu, Meng Li et al.*9 citations*
25. **[Improving Gradient Regularization using Complex-Valued Neural Networks ↗](http://proceedings.mlr.press/v139/yeats21a/yeats21a.pdf)**Eric Yeats, Yiran Chen, Hai Helen Li*9 citations*

[See all 196 papers in ICML 2021 — accepted papers →](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2021/papers/)

## Papers with our summary in our library (2)

The most cited first (OpenAlex citations plus our library's).

1. **[Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://md.research.elamur.ai/free/en/papers/jia-2021-scaling-up-visual-vision-language/) [International Conference on Machine Learning (ICML)](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/)**Chao Jia, Yinfei Yang, Ye Xia, et al.*2021 · 1,615 citations*
2. **[I-BERT: Integer-only BERT Quantization](https://md.research.elamur.ai/free/en/papers/kim-2021-i-bert-integer-only-bert/) [International Conference on Machine Learning (ICML)](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/)**Sehoon Kim, Amir Gholami, Zhewei Yao, et al.*2021 · 122 citations*

## Top topics

Topics of its works in our library, with the number of works on each.

[Vision & language (1)](https://md.research.elamur.ai/free/en/topics/multimodal/) · [Efficient models & compression (1)](https://md.research.elamur.ai/free/en/topics/efficient-models/)

## Fields

[Computer Science (2)](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities (1)](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/)

## Top authors

Authors with a page who published here most often: their works here, and the citations of those works.

[🧑‍🔬**Hieu Pham**1 work here · 1,615 citations](https://md.research.elamur.ai/free/en/authors/hieu-pham/) · [🧑‍🔬**Quoc Viet Le**1 work here · 1,615 citations](https://md.research.elamur.ai/free/en/authors/quoc-viet-le/) · [🧑‍🔬**Yinfei Yang**1 work here · 1,615 citations](https://md.research.elamur.ai/free/en/authors/yinfei-yang/) · [🧑‍🔬**Zhen Li**1 work here · 1,615 citations](https://md.research.elamur.ai/free/en/authors/zhen-li/) · [🧑‍🔬**Amir Gholami**1 work here · 122 citations](https://md.research.elamur.ai/free/en/authors/amir-gholami/) · [🧑‍🔬**Kurt Keutzer**1 work here · 122 citations](https://md.research.elamur.ai/free/en/authors/kurt-keutzer/) · [🧑‍🔬**Michael W. Mahoney**1 work here · 122 citations](https://md.research.elamur.ai/free/en/authors/michael-w-mahoney/) · [🧑‍🔬**Sehoon Kim**1 work here · 122 citations](https://md.research.elamur.ai/free/en/authors/sehoon-kim/) · [🧑‍🔬**Zhewei Yao**1 work here · 122 citations](https://md.research.elamur.ai/free/en/authors/zhewei-yao/)

## Top institutions

Institutions on the bylines of its works here, by the number of works.

[🏢**Google** Mountain View · United States 1 work here](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**University of California, Berkeley** Berkeley · United States 1 work here](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/)

works and citations from OpenAlex and our library.

- [← previous ICML 2019](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2019/)
- [next → ICML 2023](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/2023/)
- [↑ back to ICML](https://md.research.elamur.ai/free/en/venues/international-conference-on-machine-learning/)