Research Interests

The ongoing research projects of the team consist of the current funded projects and some new research themes. 

The research of our group lies at the intersection of computational methods and machine learning, with a particular focus on graph- and network-structured data. I am interested in both the theoretical foundations of learning and computation on graphs and their application to critical real-world challenges in science and engineering. My work aims to bridge fundamental theory with impactful solutions in diverse domains. 

The ongoing projects are in the following four research themes:

Theme I: Foundations of Graph and Geometric Machine Learning

This theme explores the core theoretical and computational challenges in Graph and Geometric Machine Learning. 

• The expressive power of graph neural networks: Investigating the limits of what GNNs can represent and how their architectures can be optimized for better expressiveness across different tasks such as molecular dynamic simulation and material property prediction.

  1. Polynomial Width is Sufficient for Set Representation with High-dimensional Features, ICLR 2024

  2. Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning, NeurIPS 2021

  3. "Nested Graph Neural Networks," NeurIPS 2021. (code)

  4. Distance Encoding -- Design Provably More Powerful GNNs for Structural Representation Learning, NeurIPS 2020. (codes)(slides)

• The stability and generalization of Graph and Geometric Machine Learning models: Examining the ability of these models to generalize beyond their training data, particularly in cases where the underlying graphs vary in size and structure, and the geometry gets shifted.

  1. On the Stability of Expressive Positional Encodings for Graphs, ICLR 2024 (codes)

  2. Pairwise Alignment Improves Graph Domain Adaptation, ICML 2024 (codes, spotlight)

  3. Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks, ICLR 2022. (code)

  4.  Structural Re-weighting Improves Graph Domain Adaptation, ICML 2023.  (codes) 

  5. Graph Information Bottleneck, NeurIPS 2020. (codes) (slides)

• Efficient computation of Graph and Geometric Machine Learning models: Developing novel algorithms and optimization techniques to accelerate the computational efficiency of machine learning models to process graph and geometric data. This includes reducing the time and space complexity of training large-scale models, enabling their application to high-dimensional graph data in real-world scenarios.

  1. Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics, ICML 2024 (codes, oral)

  2. Equivariant Hypergraph Diffusion Neural Operators,"  ICLR 2023. (codes)

  3. Neighborhood-aware Scalable Temporal Network Representation Learning, LoG 2022 (best paper award!) (codes) (talks) 

  4. Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning, VLDB 2022 (codes)

  5. "Submodular Hypergraph: p-Laplacian, Cheeger Inequalities and Spectral Clustering," ICML 2018

Theme II: Trustworthy Machine Learning (Large Language Models Interact with Graph Data)

This theme focuses on enhancing the trustworthiness of machine learning systems that integrate graph data and LLMs, with special emphasis on privacy and knowledge representation.

• Privacy-preserving machine learning with graph data: Utilizing advanced techniques such as differential privacy and certified unlearning to ensure the security and confidentiality of sensitive graph-structured data that is used by graph models or large language models. This work aims to protect data integrity in domains like social networks, healthcare, and financial systems, where privacy is critical.

  1. Differentially Private Graph Diffusion with Applications in Personalized PageRanks, NeurIPS 2024

  2. Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning, NeurIPS 2024 (spotlight)

  3. On the Inherent Privacy Properties of Discrete Denoising Diffusion Models. TMLR, WSDAIF 2024 Oral 

  4. Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection, NeurIPS 2023 code 

• Graph-guided generation in Large Language Models: Investigating how LLMs can incorporate graph data as a structured knowledge source to guide their generation. By integrating graph-based knowledge graphs or relational databases, this research explores how LLMs can perform more accurate and contextually grounded reasoning and decision-making.

This is an on-going project in 2024. The relevant example paper is to be listed...

Theme III: AI for Science

This theme addresses the application of advanced AI methods to solve critical challenges in scientific research, particularly in high-energy physics and astrophysics.

• Data processing in particle physics: Applying machine learning techniques to improve particle tracking and denoising in large experiments like the Large Hadron Collider. My work focuses on enhancing the accuracy and efficiency of reconstructing particle trajectories from noisy data.

  1. GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shift (Benchmark Track), NeurIPS, 2024 (codes)

  2. Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics, ICML 2024 (codes, oral)

  3. Interpretable Geometric Deep Learning via Learnable Randomness Injection,  ICLR 2023. (codes)

  4. Semi-supervised Graph Neural Network for Particle-level Noise Removal, The European Physics Journal C 2023

• Neutrino reconstruction at IceCube: Developing algorithms to optimize the reconstruction of neutrino interactions in the IceCube Neutrino Observatory. By improving the precision of event detection and parameter estimation, this research contributes to a better understanding of neutrino properties and their role in the universe.

This is an on-going project in 2024. The relevant example paper is to be listed...