Takuya Akiba
- Artificial Intelligence top 1%
- Computer Vision and Pattern Recognition top 2%
- Electrical and Electronic Engineering top 10%
- Computer Networks and Communications top 5%
- Statistical and Nonlinear Physics top 2%
- Co-authors
- Shotaro SanoToshihiko YanaseMasanori KoyamaYuichi YoshidaYoichi IwataKen‐ichi KawarabayashiNaoto OhsakaTakanori Hayashi
- Topics
- Complex Network Analysis Techniques (12 papers)Data Management and Algorithms (9 papers)Graph Theory and Algorithms (8 papers)
- Partner nations
- JapanUnited States
In The Last Decade
Takuya Akiba
25 papers receiving 4.0k citations
Hit Papers
Peers
Comparison fields: 5 of 205
- Artificial Intelligence 1.2k
- Computer Vision and Pattern Recognition 603
- Electrical and Electronic Engineering 439
- Computer Networks and Communications 401
- Statistical and Nonlinear Physics 385
Countries citing papers authored by Takuya Akiba
This map shows the geographic impact of Takuya Akiba'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 Takuya Akiba with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Takuya Akiba more than expected).
Fields of papers citing papers by Takuya Akiba
This network shows the impact of papers produced by Takuya Akiba. 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 Takuya Akiba. The network helps show where Takuya Akiba may publish in the future.
Co-authorship network of co-authors of Takuya Akiba
This figure shows the co-authorship network connecting the top 25 collaborators of Takuya Akiba. A scholar is included among the top collaborators of Takuya Akiba based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Takuya Akiba. Takuya Akiba is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation | 1 |
| 2 | 68 | |
| 3 | Optunabreakdown → | 3383 |
| 4 | 87 | |
| 5 | Variance-based Gradient Compression for Efficient Distributed Deep Learning | 2 |
| 6 | Efficient algorithms for spanning tree centrality | 11 |
| 7 | 3 | |
| 8 | 57 | |
| 9 | 5 | |
| 10 | 6 | |
| 11 | 58 | |
| 12 | 19 | |
| 13 | 131 | |
| 14 | 1 | |
| 15 | 46 | |
| 16 | 60 | |
| 17 | 1 | |
| 18 | 36 | |
| 19 | 45 | |
| 20 | 47 |
About Takuya Akiba
Takuya Akiba is a scholar working on Statistical and Nonlinear Physics, Signal Processing and Computer Vision and Pattern Recognition, having authored 25 papers that have together received 4.1k indexed citations. Recurring topics across this work include Complex Network Analysis Techniques (12 papers), Data Management and Algorithms (9 papers) and Graph Theory and Algorithms (8 papers). The work is most often cited by research in Artificial Intelligence (1.2k citations), Signal Processing (372 citations) and Statistical and Nonlinear Physics (385 citations). Takuya Akiba has collaborated with scholars based in Japan and United States. Frequent co-authors include Shotaro Sano, Toshihiko Yanase, Masanori Koyama, Yuichi Yoshida, Yoichi Iwata, Ken‐ichi Kawarabayashi, Naoto Ohsaka, Takanori Hayashi, Yoshihiro Yamada and Masakazu Iwamura. Their work appears in journals such as IEEE Access, Proceedings of the VLDB Endowment and Theoretical Computer Science.
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.