BU, Fanchen 卜凡辰

😊 Hi, I am Fanchen (/fantʂʰən/)! You can also call me Vezen (/vezən/).

I am a PhD student in the Data Mining Lab at KAIST, under Prof. Shin, Kijung.

My research interests lie in graph mining, graph algorithms, and combinatorial optimization.

Besides research, I like music 🎼, math 📐, thinking 🤔, and exercise 🏋️‍♀️!

過則勿憚改。 When you make a mistake, don't be afraid to correct yourself.——《論語·學而》


Contact

✉️ Email: boqvezen97@kaist.ac.kr

👾 GitHub

💼 LinkedIn

Education

Ph.D. Student

2022.03 – Present | Korea Advanced Institute of Science and Technology (KAIST)

  • Electrical Engineering

M.S.

2019.09 - 2021.08 | Korea Advanced Institute of Science and Technology (KAIST)

  • Electrical Engineering, GPA: 4.21/4.3
  • Thesis: A Novel Optimization Algorithm with Orthogonality for Deep Neural Networks Inspired by Feedback Integrators

B.Eng.

2015.09 - 2019.08 | University of Chinese Academy of Sciences (UCAS)

  • Computer Science and Technology, GPA: 3.71/4

Research Experience

Visiting Researcher

2026.09 - 2026.11 | KTH Royal Institute of Technology

Visiting Researcher

2025.03 - 2025.06 | CENTAI Institute (now Intesa Sanpaolo AI Research)

Research Assistant

2021.09 - 2022.02 | Korea Advanced Institute of Science and Technology (KAIST)

Publications

You can also check them on Google Scholar or Semantic Scholar
Conference / Journal / Preprint / Workshop / Software
*: equal contribution

[P2] Do Higher-Order Models Win for Higher-Order Reasons? Rethinking Performance Gains in Hypergraph Learning

  • Fanchen Bu, Fan Li, Geon Lee, Sunwoo Kim, Xiaoyang Wang, Renaud Lambiotte, and Kijung Shin

[P1] Causal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Science

  • Soo Yong Lee*, Jongha Lee*, Jaewan Chun, Hyunjin Hwang, Fanchen Bu, Dongyeong Hwang, Ziv Ben-Zion, Taekwan Kim, Denny Borsboom, Jaemin Yoo, and Kijung Shin

[J6] A Survey on Centrality and Importance Measures in Hypergraphs: Categorization and Empirical Insights

  • Jaewan Chun*, Fanchen Bu*, Yeongho Kim, Atsushi Miyauchi, Francesco Bonchi, and Kijung Shin

[J5] Revisiting LightGCN: Unexpected Inflexibility, Inconsistency, and A Remedy Towards Improved Recommendation

  • Geon Lee, Kyungho Kim, Fanchen Bu, Langzhang Liang, and Kijung Shin
  • ACM Transactions on Recommender Systems 2026 [ paper | code | bib ]

[C21] Toward a Science of AI Agent Societies

  • Geon Lee*, Fanchen Bu*, Soo Yong Lee*, Sunwoo Kim, and Kijung Shin
  • KDD 2026 (Blue Sky Ideas Track) [ paper | bib ]

[C20] Edge Probability Graph Models Beyond Edge Independency: Concepts, Analyses, and Algorithms

  • Fanchen Bu, Ruochen Yang, Paul Bogdan, and Kijung Shin

[C19] Identifying Group Anchors in Real-World Group Interactions Under Label Scarcity

  • Fanchen Bu, Geon Lee, Minyoung Choe, and Kijung Shin

[C18] HyperSearch: Prediction of New Hyperedges through Unconstrained yet Efficient Search

  • Hyunjin Choo, Fanchen Bu, Hyunjin Hwang, Young-Gyu Yoon, and Kijung Shin

[W1] On Training-Test (Mis)alignment in Unsupervised Combinatorial Optimization: Observation, Empirical Exploration, and Analysis

  • Fanchen Bu and Kijung Shin
  • (Workshop on Test-Time Adaptation)

[C17] PyTorch-based Geometric Learning with Non-CUDA Processing Units: Experiences from Intel Gaudi-v2 HPUs

  • Fanchen Bu and Kijung Shin

[C16] RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark

  • Federico Berto*, Chuanbo Hua*, Junyoung Park*, Laurin Luttmann*, Yining Ma, Fanchen Bu, Jiarui Wang, Haoran Ye,
  • (Datasets and Benchmarks Track)

[C15] Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification

  • Langzhang Liang, Fanchen Bu, Zixing Song, Zenglin Xu, Shirui Pan, and Kijung Shin

[C14] TiGer: Self-Supervised Purification for Time-evolving Graphs

  • Hyeonsoo Jo, Jongha Lee, Fanchen Bu, and Kijung Shin

[J4] A Survey on Hypergraph Mining: Patterns, Tools, and Generators

  • Geon Lee*, Fanchen Bu*, Tina Eliassi-Rad, and Kijung Shin
  • ACM Computing Surveys 2025 [ paper | bib ]

[J3] Estimating Simplet Counts via Sampling

  • Hyunju Kim*, Heechan Moon*, Fanchen Bu, Jihoon Ko, and Kijung Shin
  • (Journal Extension of [C3])

[C13] DiffIM: Differentiable Influence Minimization with Surrogate Modeling and Continuous Relaxation

  • Junghun Lee, Hyunju Kim, Fanchen Bu, Jihoon Ko, Kijung Shin

[C12] On Measuring Unnoticeability of Graph Adversarial Attacks: Observations, New Measure, and Applications

  • Hyeonsoo Jo*, Hyunjin Hwang*, Fanchen Bu, Soo Yong Lee, Chanyoung Park, and Kijung Shin

[C11] Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy

  • Sunwoo Kim, Soo Yong Lee, Fanchen Bu, Shinhwan Kang, Kyungho Kim, Jaemin Yoo, and Kijung Shin

[C10] Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More

  • Fanchen Bu, Hyeonsoo Jo, Soo Yong Lee, Sungsoo Ahn, and Kijung Shin

[C9] Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective

  • Soo Yong Lee, Sunwoo Kim, Fanchen Bu, Jaemin Yoo, Jiliang Tang, and Kijung Shin

[C8] HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs

  • Sunwoo Kim, Shinhwan Kang, Fanchen Bu, Soo Yong Lee, Jaemin Yoo, and Kijung Shin

[C7] Robust Graph Clustering via Meta Weighting for Noisy Graphs

  • Hyeonsoo Jo, Fanchen Bu, and Kijung Shin

[C6] On Improving the Cohesiveness of Graphs by Merging Nodes: Formulation, Analysis, and Algorithms

  • Fanchen Bu and Kijung Shin

[C5] How Transitive Are Real-World Group Interactions? - Measurement and Reproduction

  • Sunwoo Kim, Fanchen Bu, Minyoung Choe, Jaemin Yoo, and Kijung Shin

[J2] Interplay between Topology and Edge Weights in Real-World Graphs: Concepts, Patterns, and an Algorithm

  • Fanchen Bu, Shinhwan Kang, and Kijung Shin
  • (ECML PKDD 2023 Journal Track)

[J1] Hypercore Decomposition for Non-Fragile Hyperedges: Concepts, Algorithms, Observations, and Applications

  • Fanchen Bu, Geon Lee, and Kijung Shin
  • (ECML PKDD 2023 Journal Track)

[C4] Towards Deep Attention in Graph Neural Networks: Problems and Remedies

  • Soo Yong Lee, Fanchen Bu, Jaemin Yoo, and Kijung Shin

[C3] Characterization of Simplicial Complexes by Counting Simplets Beyond Four Nodes

  • Hyunju Kim, Jihoon Ko, Fanchen Bu, and Kijung Shin

[C2] Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs

  • Fanchen Bu and Dong Eui Chang

[C1] Double Prioritized State Recycled Experience Replay

  • Fanchen Bu and Dong Eui Chang

Languages

Chinese

Native

English

Advanced

  • IELTS 7.5
  • GRE 333

Korean

Intermediate

Italian

Elementary

Academic Services

[C11] International Conference on Learning Representations (ICLR)

  • Reviewer: 2026 - 2027
  • Note: Selected as one of the top reviewers (top 200) in ICLR 2026

[C10] AAAI Conference on Artificial Intelligence (AAAI)

  • Reviewer: 2026 - 2027

[C9] ACM International Conference on Information and Knowledge Management (CIKM)

  • Reviewer: 2025 - 2026
  • Session Chair: 2025

[C8] Conference on Neural Information Processing Systems (NeurIPS)

  • Reviewer: 2025 - 2026

[C7] International Conference on Machine Learning (ICML)

  • Reviewer: 2025 - 2026
  • Note: Selected as a Gold reviewer (top 25%) in ICML 2026

[C6] Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)

  • Workshop Organizer: 2025 (GLFM)

[C5] ACM Web Conference (TheWebConf/WWW)

  • Reviewer: 2025 - 2027

[C4] Learning on Graphs Conference (LoG)

  • Reviewer: 2024, 2026
  • Note: Selected as one of the top reviewers (top 32) in LoG 2024

[C3] European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

  • Reviewer: 2024

[C2] Asian Conference on Machine Learning (ACML)

  • Reviewer: 2024 - 2026

[C1] ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

  • Reviewer: 2024 - 2027
  • Note: Selected as one of the best reviewers (top 407) in KDD 2026 (both August and February Cycles)
  • Note: Selected as one of the outstanding reviewers (top 10%) in KDD 2025 (both August and February Cycles)

[J16] Progress in Artificial Intelligence

  • Reviewer: 2026

[J15] Transactions on Machine Learning Research (TMLR)

  • Reviewer: 2026

[J14] Data Mining and Knowledge Discovery (DAMI)

  • Reviewer: 2026

[J13] Machine Learning

  • Reviewer: 2026

[J12] IEEE Transactions on Knowledge and Data Engineering (TKDE)

  • Reviewer: 2026

[J11] Journal of Network and Systems Management

  • Reviewer: 2026

[J10] PLoS One

  • Reviewer: 2026

[J9] Neural Processing Letters

  • Reviewer: 2025

[J8] VLDB Journal

  • Reviewer: 2025 - 2026

[J7] Computational and Mathematical Organization Theory

  • Reviewer: 2025

[J6] Scientific Reports

  • Reviewer: 2025

[J5] IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

  • Reviewer: 2025

[J4] International Journal of Machine Learning and Cybernetics (IJMLC)

  • Reviewer: 2024

[J3] IEEE Transactions on Network Science and Engineering (TNSE)

  • Reviewer: 2024, 2026

[J2] Journal of Supercomputing

  • Reviewer: 2024 - 2025

[J1] Big Data Research

  • Reviewer: 2024

Favorite Music

The links are on Youtube Music

Useful Tools and Websites

Miscellanea