Jonathan Frankle
Impact in
- Software top 10%
- Software Testing and Debugging Techniques
- Artificial Intelligence top 10%
- Domain Adaptation and Few-Shot Learning
- Logic, programming, and type systems
- Adversarial Robustness in Machine Learning
- Privacy-Preserving Technologies in Data
Papers in
-
- Adversarial Robustness in Machine Learning 4
- Domain Adaptation and Few-Shot Learning 2
- Logic, programming, and type systems 2
- Software 2
- Software Testing and Debugging Techniques 2
- Co-authors
- Michael Carbin (4 shared papers)Steve Zdancewic (2 shared papers)David P. Walker (2 shared papers)Peter-Michael Osera (2 shared papers)Shiyu Chang (1 shared paper)Yang Zhang (1 shared paper)Zhangyang Wang (1 shared paper)Tianlong Chen (1 shared paper)
- Journals
- ACM SIGPLAN Notices (1 paper)USENIX Security Symposium (1 paper)arXiv (Cornell University) (1 paper)
- Partner nations
- United States
In The Last Decade
Jonathan Frankle
10 papers receiving 238 citations
Peers
Comparison fields: 5 of 53
- Software 38
- Artificial Intelligence 166
- Computer Vision and Pattern Recognition 88
- Signal Processing 23
- Information Systems 46
Countries citing papers authored by Jonathan Frankle
This map shows the geographic impact of Jonathan Frankle's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Jonathan Frankle with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Jonathan Frankle more than expected).
Fields of papers citing papers by Jonathan Frankle
This network shows the impact of papers produced by Jonathan Frankle. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Jonathan Frankle. The network helps show where Jonathan Frankle may publish in the future.
Co-authors
The 25 scholars most cited alongside Jonathan Frankle, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
| # | Work | ||
|---|---|---|---|
| 1 | The Lottery Ticket Hypothesis: Training Pruned Neural Networks. | 2018 | 58 |
| 2 | 2021 | 53 | |
| 3 | 2016 | 53 | |
| 4 | The Lottery Ticket Hypothesis at Scale | 2019 | 28 |
| 5 | 2016 | 17 | |
| 6 | Practical Accountability of Secret Processes | 2018 | 16 |
| 7 | 2022 | 7 | |
| 8 | 2024 | 5 | |
| 9 | 2024 | 2 | |
| 10 | 2022 | 1 | |
| 11 | 2023 | 0 |
About Jonathan Frankle
Jonathan Frankle is a scholar working on Artificial Intelligence, Software, Computer Vision and Pattern Recognition, Information Systems and Safety Research, having authored 11 papers that have together received 240 indexed citations. Recurring topics across this work include Adversarial Robustness in Machine Learning (4 papers), Advanced Neural Network Applications (3 papers), Software Engineering Research (2 papers), Domain Adaptation and Few-Shot Learning (2 papers), Logic, programming, and type systems (2 papers), Software Testing and Debugging Techniques (2 papers), Generative Adversarial Networks and Image Synthesis (1 paper) and Video Analysis and Summarization (1 paper). The work is most often cited by research in Software (38 citations), Artificial Intelligence (166 citations), Computer Vision and Pattern Recognition (88 citations), Signal Processing (23 citations) and Information Systems (46 citations). Jonathan Frankle has collaborated with scholars based in United States. Frequent co-authors include Michael Carbin, Steve Zdancewic, David P. Walker, Peter-Michael Osera, Shiyu Chang, Yang Zhang, Zhangyang Wang, Tianlong Chen, Sijia Liu and Gintare Karolina Dziugaite. Their work appears in journals such as ACM SIGPLAN Notices, USENIX Security Symposium and arXiv (Cornell University).
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.