🧑‍🔬 Chengqi Zhang

🏛️ Affiliations

🎓University of Technology SydneySydney · Australia2002–2025 · 503 papersEmployment🎓Guangxi Normal UniversityGuilin · China2002–2013 · 35 papers🎓Hong Kong Polytechnic UniversityHong Kong · China2024–2026 · 32 papersEmployment since 2024 · Director of HK PolyU Shenzhen Research Institute and Chair Professor of AI, Data Science and Artificial Intelligence🎓Deakin UniversityBurwood · Australia1999–2004 · 32 papersEducation 2002 · Doctor of Science (Higher Doctorate), Computer Science🎓University of New EnglandArmidale · Australia1992–2005 · 21 papers🎓University of New EnglandBiddeford · United States1996–1998 · 7 papers🎓Jilin UniversityChangchun · China1982–2025 · 4 papersEducation 1982–1984 · Master of Science, Computer Science🎓Zhejiang Normal UniversityJinhua · China2009–2011 · 4 papers🎓Chinese University of Hong KongHong Kong · China1999–2005 · 4 papers🎓Beihang UniversityBeijing · China2006–2007 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 12 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

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

📅 Works by year

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. A Comprehensive Survey on Graph Neural Networks (2019 · 10,312 citations)
   Deep learning works well on grid-like data such as images and text sequences. Many real datasets are graphs instead: nodes have varying numbers of unordered neighbours, and instances depend on each other. This survey reviews deep learning methods for graph data and sorts them into four families. Recurrent GNNs…
2. DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding (2017 · 854 citations)
   Sentence encoders in NLP usually rely on RNNs for long-range context or on CNNs for local patterns. Both have drawbacks: RNNs process tokens sequentially, and standard attention ignores word order. The authors propose DiSAN, a lightweight sentence-encoding network that uses only attention. It has two new components.…

All works

5 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. A Comprehensive Survey on Graph Neural NetworksarXiv:1901.00596Zonghan Wu, Shirui Pan, Fengwen Chen, et al.2019 · 10,312 citations
2. Graph WaveNet for Deep Spatial-Temporal Graph Modeling ↗International Joint Conference on Artificial Intelligence · no summary yetZonghan Wu et al.2019 · 2,968 citations
3. DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language UnderstandingProceedings of the AAAI Conference on Artificial IntelligenceTao Shen, Tianyi Zhou, Guodong Long, et al.2017 · 854 citations
4. FedProto: Federated Prototype Learning across Heterogeneous Clients ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetYue Tan et al.2022 · 766 citations
5. Attributed Graph Clustering: A Deep Attentional Embedding Approach ↗International Joint Conference on Artificial Intelligence · no summary yetChun Wang et al.2019 · 582 citations

🤝 Co-authors here

6 co-authors with a page, the most papers together first.

• Guodong Long ×2
• Shirui Pan ×2
• Jing Jiang
• Philip S. Yu
• Tao Shen
• Tianyi Zhou

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Proceedings of the AAAI Conference on Artificial Intelligence ×2: Proceedings of the AAAI Conference on Artificial Intelligence 2017
• International Joint Conference on Artificial Intelligence ×2

🔗 Cited by

Papers of our library cite their works 345 times (of the 149,439 papers whose bibliographies we read); 30 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/chengqi-zhang/