171 citations · 248 across the 20 of their papers we have counts for
20 papers
Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization
Yuxin Wang, Yuanzhe Hu, Xiaokun Zhong +7
Neural networks trained under different hyperparameter settings can fall into distinct training "regimes," with consistent behavior within regimes and qualitative differences acros…
GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Models
Tuo Wang, Adithya Kulkarni, Tyler Cody +3
Uncertainty estimation is essential for enhancing the reliability of Large Language Models (LLMs), particularly in high-stakes applications. Existing methods often overlook semanti…
Non-exchangeable Conformal Prediction for Temporal Graph Neural Networks
Tuo Wang, Jian Kang, Yujun Yan +2
Conformal prediction for graph neural networks (GNNs) offers a promising framework for quantifying uncertainty, enhancing GNN reliability in high-stakes applications. However, exis…
Spectral Insights into Data-Oblivious Critical Layers in Large Language Models
Xuyuan Liu, Lei Hsiung, Yaoqing Yang +1
Understanding how feature representations evolve across layers in large language models (LLMs) is key to improving their interpretability and robustness. While recent studies have…
Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge
Chiyu Ma, Enpei Zhang, Yilun Zhao +7
LLM-as-Judge has emerged as a scalable alternative to human evaluation, enabling large language models (LLMs) to provide reward signals in trainings. While recent work has explored…
Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift
Yi Zhang, Elynn Chen, Yujun Yan
We study contextual dynamic pricing when a target market can leverage K auxiliary markets -- offline logs or concurrent streams -- whose mean utilities differ by a structured prefe…
MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding
Weikang Qiu, Zheng Huang, Haoyu Hu +3
Decoding functional magnetic resonance imaging (fMRI) signals into text has been a key challenge in the neuroscience community, with the potential to advance brain-computer interfa…
Exploring Consistency in Graph Representations:from Graph Kernels to Graph Neural Networks
Xuyuan Liu, Yinghao Cai, Qihui Yang +1
Graph Neural Networks (GNNs) have emerged as a dominant approach in graph representation learning, yet they often struggle to capture consistent similarity relationships among grap…
Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance
Haiquan Lu, Xiaotian Liu, Yefan Zhou +6
Recent studies on deep ensembles have identified the sharpness of the local minima of individual learners and the diversity of the ensemble members as key factors in improving test…
Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning
Zheng Huang, Qihui Yang, Dawei Zhou +1
Although most graph neural networks (GNNs) can operate on graphs of any size, their classification performance often declines on graphs larger than those encountered during trainin…
Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification
Yihe Wang, Nan Huang, Taida Li +2
Medical time series (MedTS) data, such as Electroencephalography (EEG) and Electrocardiography (ECG), play a crucial role in healthcare, such as diagnosing brain and heart diseases…
Interpretable Sparsification of Brain Graphs: Better Practices and Effective Designs for Graph Neural Networks
Gaotang Li, Marlena Duda, Xiang Zhang +2
Brain graphs, which model the structural and functional relationships between brain regions, are crucial in neuroscientific and clinical applications involving graph classification…
Tackling Size Generalization of Graph Neural Networks on Biological Data from a Spectral Perspective
Gaotang Li, Danai Koutra, Yujun Yan
We address the key challenge of size-induced distribution shifts in graph neural networks (GNNs) and their impact on the generalization of GNNs to larger graphs. Existing literatur…
EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs
Haohui Wang, Yuzhen Mao, Yujun Yan +8
Non-IID transfer learning on graphs is crucial in many high-stakes domains. The majority of existing works assume stationary distribution for both source and target domains. Howeve…
A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks
Yefan Zhou, Yiru Shen, Yujun Yan +2
Neural networks (NN) for single-view 3D reconstruction (SVR) have gained in popularity. Recent work points out that for SVR, most cutting-edge NNs have limited performance on recon…
Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices
Puja Trivedi, Ekdeep Singh Lubana, Yujun Yan +2
Unsupervised graph representation learning is critical to a wide range of applications where labels may be scarce or expensive to procure. Contrastive learning (CL) is an increasin…
Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
Yujun Yan, Milad Hashemi, Kevin Swersky +2
In node classification tasks, graph convolutional neural networks (GCNs) have demonstrated competitive performance over traditional methods on diverse graph data. However, it is kn…
Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models
Zhengming Zhang, Yaoqing Yang, Zhewei Yao +3
Federated learning (FL) is a promising way to use the computing power of mobile devices while maintaining the privacy of users. Current work in FL, however, makes the unrealistic a…
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Jiong Zhu, Yujun Yan, Lingxiao Zhao +3
We investigate the representation power of graph neural networks in the semi-supervised node classification task under heterophily or low homophily, i.e., in networks where connect…
Neural Execution Engines: Learning to Execute Subroutines
Yujun Yan, Kevin Swersky, Danai Koutra +2
A significant effort has been made to train neural networks that replicate algorithmic reasoning, but they often fail to learn the abstract concepts underlying these algorithms. Th…