Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
Heterogeneous Network Embedding via Deep Architectures
2015378 citationsShiyu Chang, Guo-Jun Qi et al.profile →
Learning Locally-Adaptive Decision Functions for Person Verification
2013357 citationsShiyu Chang, Thomas S. Huang et al.profile →
Peers — A (Enhanced Table)
Peers by citation overlap · career bar shows stage (early→late)
cites ·
hero ref
This map shows the geographic impact of Shiyu Chang'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 Shiyu Chang with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Shiyu Chang more than expected).
This network shows the impact of papers produced by Shiyu Chang. 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 Shiyu Chang. The network helps show where Shiyu Chang may publish in the future.
Co-authorship network of co-authors of Shiyu Chang
This figure shows the co-authorship network connecting the top 25 collaborators of Shiyu Chang.
A scholar is included among the top collaborators of Shiyu Chang 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 Shiyu Chang. Shiyu Chang is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Chuang, Yung-Sung, Hongyin Luo, Yang Zhang, et al.. (2022). DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4207–4218.90 indexed citations
5.
Jiang, Yifan, Shiyu Chang, & Zhangyang Wang. (2021). TransGAN: Two Transformers Can Make One Strong GAN. arXiv (Cornell University).84 indexed citations
6.
Bao, Yujia, Menghua Wu, Shiyu Chang, & Regina Barzilay. (2020). Few-shot Text Classification with Distributional Signatures. International Conference on Learning Representations.23 indexed citations
7.
Qian, Kaizhi, Shuicheng Yan, Shiyu Chang, Xuesong Yang, & Mark Hasegawa‐Johnson. (2019). Zero-Shot Voice Style Transfer with Only Autoencoder Loss.. arXiv (Cornell University).11 indexed citations
8.
Lee, Guang-He, et al.. (2019). A Stratified Approach to Robustness for Randomly Smoothed Classifiers.. arXiv (Cornell University).1 indexed citations
9.
Qian, Kaizhi, Shuicheng Yan, Shiyu Chang, Xuesong Yang, & Mark Hasegawa‐Johnson. (2019). AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss. International Conference on Machine Learning. 5210–5219.39 indexed citations
Yan, Shuicheng, Shuicheng Yan, Shiyu Chang, Qing Ling, & Thomas S. Huang. (2016). Learning a deep l ∞ encoder for hashing. International Joint Conference on Artificial Intelligence. 2174–2180.14 indexed citations
17.
Wang, Qi, Pinghua Gong, Shiyu Chang, Thomas S. Huang, & Jiayu Zhou. (2016). Robust Convex Clustering Analysis. 1263–1268.6 indexed citations
Yan, Shuicheng, Shuicheng Yan, Shiyu Chang, et al.. (2015). A joint optimization framework of sparse coding and discriminative clustering. International Conference on Artificial Intelligence. 3932–3938.16 indexed citations
20.
Liu, Xianming, Yue Gao, Rongrong Ji, Shiyu Chang, & Thomas S. Huang. (2013). Localizing web videos from heterogeneous images. National Conference on Artificial Intelligence. 71–73.1 indexed citations
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.