Renjie Liao   I am an Assistant Professor (since Jan. 2022) in ECE Department and an associated member in CS Department at UBC. I am broadly interested in machine learning and its intersection with vision, self-driving, healthcare, and other areas, with a focus on probabilistic and geometric deep learning. I was a Visiting Faculty Researcher at Google Brain, working with Geoffrey Hinton and David Fleet. I received my PhD from UofT in 2021, advised by Richard Zemel and Raquel Urtasun. During my PhD, I also worked as a Senior Research Scientist at Uber ATG. I obtained my MPhil from CUHK, advised by Jiaya Jia, and my BEng from Beihang.

CV

How to Join

Email: rjliao@ece.ubc.ca

"There is nothing as practical as a good theory." - Kurt Lewin "The test of all knowledge is experiment." - Richard Feynman

Research Highlights:

• Energy-based models: Gaussian-Bernoulli RBMs
• Generalization bounds for GNNs: PAC-Bayes Bounds for GNNs (ICLR 2021)
• Deep generative models of graphs: Graph Recurrent Attention Networks (NeurIPS 2019)
• Multi-scale spectral graph convolutional networks: LanczosNet (ICLR 2019)
• Implicit differentiation: Improving Recurrent Back-Propagation (ICML 2018)
• Differentiable bipartite matching: DMM-Net (ICCV 2019)

News (More)

• I was invited to give a talk "Gaussian Bernoulli RBMs Without Tears" at the Math Machine Learning Seminar Max Planck Institute for Mathematics in the Sciences (MPI MIS) and UCLA, Feb. 9 2023
• Our work Specformer: Spectral Graph Neural Networks Meet Transformers was accepted by International Conference on Learning Representations (ICLR) 2023
  Congratulations to Deyu!
• Our work Scaling Forward Gradient With Local Losses was accepted by International Conference on Learning Representations (ICLR) 2023
  Congratulations to Mengye!
• Congratulations to Sadegh for receiving UBC Graduate Support Initiative (GSI) Award 2023!
• I am teaching CPEN 400D: Deep Learning in Term 2 of 2022 Winter!
• I was invited to give a talk "Gaussian Bernoulli RBMs Without Tears" at SFU-UBC AI Research Day, Dec. 10 2022
• Our work VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge was accepted by IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023
  Congratulations to Aditya!
• Our work NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds was accepted by IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023
  Congratulations to Weiwei!
• I am teaching EECE 571F: Deep Learning with Structures in Term 1 of 2022 Winter!
• I was invited to give a Tutorial "On the Generalization of Graph Neural Networks"
  at Chinese Association for Artificial Intelligence (CAAI) International Conference on Artificial Intelligence 2022
• I was invited to give a Keynote Talk "On the Generalization of Graph Neural Networks"
  at Deep Exploration of non-Euclidean Data with Geometric and Topological Representation Learning Workshop hosted by The Banff International Research Station for Mathematical Innovation and Discovery
• Our work EchoGNN: Explainable Ejection Fraction Estimation with Graph Neural Networks was accepted by International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022
  Congratulations to Masoud!
• Congratulations to Hanwen for receiving UBC Four Year Doctoral Fellowship (4YF) 2022!
• Congratulations to Qi for receiving UBC Four Year Doctoral Fellowship (4YF) 2022!
• Congratulations to Anxing for receiving UBC Four Year Doctoral Fellowship (4YF) 2022!
• Congratulations to Masoud for receiving NSERC Canada Graduate Scholarships (CGS M) 2022!
• Congratulations to Sadegh for receiving UBC Graduate Support Initiative (GSI) Award 2022!
• Congratulations to Muchen for receiving UBC Four Year Doctoral Fellowship (4YF) 2022!
• I was invited to give a Keynote Talk "On the Generalization of Graph Neural Networks"
  at AAAI 2022 Workshop on Deep Learning on Graphs: Methods and Applications

Last Updated: Feb. 9, 2023