Di He
- Artificial Intelligence top 5%
- Topic Modeling 11
- Natural Language Processing Techniques 9
- Speech Recognition and Synthesis 2
- Text and Document Classification Technologies 1
-
- Multimodal Machine Learning Applications 5
-
- Auction Theory and Applications 3
- Advanced Bandit Algorithms Research 2
-
- Consumer Market Behavior and Pricing 3
- Journals
- Advanced Science (1 paper)Decision Support Systems (1 paper)International journal of greenhouse gas control (1 paper)
- Partner nations
- ChinaUnited StatesUnited Kingdom
In The Last Decade
Di He
25 papers receiving 478 citations
Peers
Comparison fields: 5 of 75
- Artificial Intelligence 354
- Computer Vision and Pattern Recognition 185
- Health Informatics 5
- Management Science and Operations Research 40
- Marketing 24
Countries citing papers authored by Di He
This map shows the geographic impact of Di He'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 Di He with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Di He more than expected).
Fields of papers citing papers by Di He
This network shows the impact of papers produced by Di He. 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 Di He. The network helps show where Di He may publish in the future.
Co-authorship network
The 25 scholars most cited alongside Di He, 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 | 2025 | 9 | |
| 2 | 2024 | 0 | |
| 3 | 2023 | 1 | |
| 4 | 2023 | 1 | |
| 5 | 2022 | 29 | |
| 6 | 2022 | 1 | |
| 7 | 2020 | 3 | |
| 8 | Efficient Training of BERT by Progressively Stacking | 2019 | 39 |
| 9 | Fast Structured Decoding for Sequence Models | 2019 | 21 |
| 10 | Towards a Deep and Unified Understanding of Deep Neural Models in NLP | 2019 | 43 |
| 11 | Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View | 2019 | 3 |
| 12 | 2019 | 29 | |
| 13 | 2019 | 78 | |
| 14 | FRAGE: Frequency-Agnostic Word Representation | 2018 | 26 |
| 15 | Towards Binary-Valued Gates for Robust LSTM Training | 2018 | 2 |
| 16 | 2018 | 18 | |
| 17 | 2017 | 8 | |
| 18 | 2014 | 9 | |
| 19 | A Theoretical Analysis of NDCG Type Ranking Measures | 2013 | 61 |
| 20 | A game- heoretic machine learning approach for revenue maximization in sponsored search | 2013 | 20 |
About Di He
Di He is a scholar working on Artificial Intelligence, Marketing and Computer Vision and Pattern Recognition, having authored 26 papers that have together received 508 indexed citations. Recurring topics across this work include Topic Modeling (11 papers), Natural Language Processing Techniques (9 papers), Multimodal Machine Learning Applications (5 papers), Consumer Market Behavior and Pricing (3 papers), Auction Theory and Applications (3 papers), Speech Recognition and Synthesis (2 papers), Advanced Bandit Algorithms Research (2 papers) and Text and Document Classification Technologies (1 paper). The work is most often cited by research in Artificial Intelligence (354 citations), Computer Vision and Pattern Recognition (185 citations) and Health Informatics (5 citations). Di He has collaborated with scholars based in China, United States and United Kingdom. Frequent co-authors include Tao Qin, Tie‐Yan Liu, Tie‐Yan Liu, Fei Tian, Xu Tan, Liwei Wang, Zhuohan Li, Yiren Wang, ChengXiang Zhai and Yuanzhi Li. Their work appears in journals such as Advanced Science, Decision Support Systems and International journal of greenhouse gas control.
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.