PeopleofSuperintelligence

Researcher

Bohang Zhang

Also known as 张博航

Bohang Zhang is a machine-learning researcher whose papers study how graph neural networks represent graph structure. He earned a computer-science B.S. at Xi’an Jiaotong University and completed doctoral study at Peking University. His papers examined certified robustness for Lipschitz networks, graph biconnectivity, quantitative GNN expressiveness, and spectral-invariant graph networks. ICLR gave his biconnectivity paper a 2023 Outstanding Paper Award and named his 2024 GNN framework an Honorable Mention. As of October 2026, his research focuses on the foundations of machine learning.

Works
9
Citations
44
h-index
3

Publication numbers from OpenAlex, as of 19 October 2026.

Timeline

  1. 2013–2019

    Studying computer science

    He earns a B.S. in computer science at Xi’an Jiaotong University’s School of the Gifted Young in 2019.

  2. 2019–2024

    A Ph.D. at Peking

    He pursues doctoral study in Peking University’s School of Electronic Engineering and Computer Science from 2019 to 2024 and is a Ph.D. graduate at the university.

  3. 2022

    Certified robustness for neural nets

    He coauthors a NeurIPS 2022 paper that studies certified ℓ∞ robustness through Boolean-function representations.

  4. 2023

    A GNN paper on biconnectivity

    He coauthors “Rethinking the Expressive Power of GNNs via Graph Biconnectivity,” which introduces Generalized Distance Weisfeiler-Lehman as a method for biconnectivity metrics. ICLR gives the paper an Outstanding Paper Award in 2023.

  5. 2024

    Quantifying GNN expressiveness

    He coauthors “Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness,” which uses homomorphism expressivity to measure how GNNs count graphs. ICLR names the paper an Honorable Mention in its 2024 Outstanding Paper awards.

  6. 2025

    Spectral invariant graph networks

    He coauthors “Homomorphism Expressivity of Spectral Invariant Graph Neural Networks,” showing that spectral-invariant GNNs can count a class of tree-like graphs. The work appears at ICLR 2025.

  7. As of October 2026

    Machine-learning foundations

    As of October 2026, his main research area is the foundations of machine learning.

Career

Education

  1. 2024Peking UniversityPhD
  2. 2019Xi'an Jiaotong UniversityB.S.

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. Rethinking the Expressive Power of GNNs via Graph Biconnectivity2023 · 23 citations
  2. Can Graph Learning Improve Planning in LLM-based Agents?2024 · neural information processing systems · 11 citations
  3. A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests2023 · 5 citations
  4. Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness2024 · 3 citations
  5. How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension2024 · 1 citationsWith Jiliang Tang

From OpenAlex, as of 19 October 2026.

  1. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Peking University. Our estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.
  2. The company share of AI researchers’ top papers rose from 2% to 32%Includes Peking University. We estimate where leading AI researchers worked when their most-cited papers appeared. The company share rose from 2% in 1975–1979 to 32% in 2020–2024.
  3. Google has the highest combined h-index among AI organizationsIncludes Peking University. Our estimates of combined and median h-index at AI organizations, using current affiliations and OpenAlex records.
  4. Stanford University trained or employed 26 of the 108 AI major-prize winners, more than any other universityIncludes Peking University. Stanford University trained or employed 26 of the 108 AI major-prize winners, more than any other university. We compare doctorate and employment links for major-prize and best-paper winners.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Bohang Zhang yet. Send us a free-licensed photo.

  1. CV - Bohang Zhang’s Homepage (张博航) zbh2047.github.io. Checked 18 October 2026.
  2. About Me - Bohang Zhang’s Homepage (张博航) zbh2047.github.io. Checked 18 October 2026.
  3. Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective proceedings.neurips.cc. Checked 18 October 2026.
  4. Rethinking the Expressive Power of GNNs via Graph Biconnectivity arxiv.org. Checked 18 October 2026.
  5. About Me - Di He (贺笛) dihe-pku.github.io. Checked 18 October 2026.
  6. Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness proceedings.iclr.cc. Checked 18 October 2026.
  7. Jingchu Gai gaijingchu.github.io. Checked 18 October 2026.
  8. Homomorphism Expressivity of Spectral Invariant Graph Neural Networks proceedings.iclr.cc. Checked 18 October 2026.