Qi (Cheems) Wang

Recent News and Publications

• May 17th: The research work "Balanced Confidence Calibration for Graph Neural Networks" was accepted to KDD2024, congratulations to Hao & Min! Predictive confidence matters when deploying graph neural networks in real-world scenarios. This work theoretically analyzes the underconfidence and overconfidence issues in GNN's prediction and develops a balanced calibration approach to address the problem.  

• May 1st: The research work "Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation" was accepted to ICML2024, congratulations to all my awesome collaborators! Here, a surrogate back-propagation algorithm is developed together with a variant of Layer Normalization. This work significantly reduces memory usage on Lima and ViT and provides theoretical guarantees. Codes will be released soon!

• April 2024: For researchers interested in Multi-task Learning, you cannot miss this wonderful work🥳, "GO4Align: Group Optimization for Multi-Task Alignment". Here, we align the learning progress across tasks to promote the exploitation of beneficial task-relatedness and achieve SOTA performance in most existing benchmarks. Codes will be released soon!

• October 2023: I joined Tsinghua University and working as a postdoc researcher in automation. Thanks for Prof. Xiangyang Ji's supervision.

• September 22nd 2023: Congratulations to Jiayi Shen! Our manuscript "Episodic Multi-Task Learning with Heterogeneous Neural Processes" was accepted to NeurIPS2023 Spotlight (top 3.06% in all submissions), and this work proposes heterogeneous neural processes to exploit task relatedness in multi-task learning. [Paper Link, Code Link]

• September 22nd 2023: Our manuscript "A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm" was accepted to NeurIPS2023, and this work proposes a solution with an improvement guarantee to probabilistically reducing the worst-case risk without sacrificing the average performance. [Paper Link, Slides Link]

• August 6th 2023: Our manuscript "Large-scale Generative Simulation Artificial Intelligence: the Next Hotspot" was accepted to the Innovation journal and the flowchart can be found at the top of this section.

• July 2023: Many thanks to Max and Herke's nomination and Sara, Yang, Sihang's recommendation, I am honored to be awarded China Computer Federation Multi-agent System Groups (CCF-CMAS) Best Dissertation Prize [中国计算机学会-多智能体系统学组优博论文奖].

• January 21st 2023: Our manuscript "Bridge the Inference Gaps of Neural Processes via Expectation Maximization" was accepted to ICLR2023.

• October 10th 2022: Very pleased that I received NeurIPS Scholar Award, and thanks to the NeurIPS Foundation.

• September 14th 2022: Our paper Learning Expressive Meta-Representations with Mixture of Expert Neural Processes was accepted to NeurIPS2022. Our method applies to few-shot supervised learning and meta reinforcement learning. It is able to handle stochastic processes with mixture components. [Paper Link]

• July 2022: The draft of my Ph.D. Thesis will be finished. 

• July 7th 2022: Delighted to receive ICML2022 Participation Grants.

• May 2022: Our paper Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search was accepted in ICML2022 Spotlight, and the final version will be released soon. It seems the log-likelihood of defending my Ph.D. thesis this year was increased!

Here a GNN based dynamics model is introduced with superior generalization, and the posterior sampling strategy is used in policy learning without additional policy gradients in new environments. 

Feel free to access our slides link below as a brief introduction to our proposed GSSM and Amortized Meta Model-based Policy Search. (Note that this is the first trial in amortizing task-specific policies in meta model-based policy search as far as we know. The significance is that the use of non-parametric modeling avoids re-training or gradient adaptations of policies in new environments, which might be promising to address data-efficient fast adaptation problems.)

[The latest version can be found here: Paper Link, Slides Link]

• June 1st, 2020 : Our paper entitled "Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables" is accepted in ICML2020. (Supplementary materials refer to the Link.)

 The slides for our ICML presentation are attached to the Link below. We propose a hierarchical neural process to simultaneously identify tasks and capture local correlations in high-dimensional problems.

[Paper Link, Slides Link]

Student Supervision

• Out-of-Distribution Detection on Time Series Dataset using Bayesian Deep Learning (Collaborate with Fraudio Company) --> Master Student: Berend Jansen --> Finished (2020.12~2021.07)