Scholar
Lingxiao Zhao
Google Scholar ID: QKslW6EAAAAJ
Mistral AI
Citations & Impact
Citations
3,455
H-index
16
i10-index
19
Publications
20
Co-authors
7
list available
Publications
Cited
4
Cited
0
Resume (English only)
Academic Achievements
- Publications: 'Improving and Unifying Discrete- and Continuous-time Discrete Denoising Diffusion', 'Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation' (2024); 'A Practical, Progressively-Expressive GNN', 'Hyperparameter Sensitivity in Deep Outlier Detection: Analysis and a Scalable Hyper-Ensemble Solution' (NeurIPS 2022); 'From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness', 'Graph Condensation for Graph Neural Networks' (ICLR 2022); 'On Using Classification Datasets to Evaluate Graph Outlier Detection: Peculiar Observations and New Insights' (Big Data Journal, 2021); 'Connecting GCN and Graph-Regularized PCA' (GRL+ Workshop of ICML 2020); 'PairNorm: Tackling Oversmoothing in GNNs' (ICLR 2020).
Research Experience
- Last year Ph.D. student in the Machine Learning Department and Heinz College at Carnegie Mellon University.
Education
- Ph.D. in Machine Learning Joint Public Policy, Carnegie Mellon University, advised by Prof. Leman Akoglu; Master's in ECE, Carnegie Mellon University; Bachelor's in EE (power system area), Xi'an Jiaotong University.
Background
- Research interests: developing machine learning algorithms over graph-structured data, and applying designed algorithms to solve real-world problems. Also worked on pretraining LLMs and diffusion-based generative models. Future interests lie in combining graph models and LLMs to boost LLMs' reasoning and emergent abilities at different stages, moving towards a multimodal generative foundation model.
Miscellany
- Has a twin brother, Lingfei Zhao, who is pursuing his Ph.D. in Physics at Duke University. They enjoy playing games together.
