338 citations · 1.4k across the 59 of their papers we have counts for
7 papers · 1 filter
Diffusion Modeling with Domain-conditioned Prior Guidance for Accelerated MRI and qMRI Reconstruction
Wanyu Bian, Albert Jang, Fang Liu
This study introduces a novel approach for image reconstruction based on a diffusion model conditioned on the native data domain. Our method is applied to multi-coil MRI and quanti…
Bkd-FedGNN: A Benchmark for Classification Backdoor Attacks on Federated Graph Neural Network
Fan Liu, Siqi Lai, Yansong Ning +1
Federated Graph Neural Network (FedGNN) has recently emerged as a rapidly growing research topic, as it integrates the strengths of graph neural networks and federated learning to…
Discovering Dynamic Causal Space for DAG Structure Learning
Fangfu Liu, Wenchang Ma, An Zhang +3
Discovering causal structure from purely observational data (i.e., causal discovery), aiming to identify causal relationships among variables, is a fundamental task in machine lear…
Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models
Fan Liu, Hao Liu, Wenzhao Jiang
Machine learning based traffic forecasting models leverage sophisticated spatiotemporal auto-correlations to provide accurate predictions of city-wide traffic states. However, exis…
Variational Inference with NoFAS: Normalizing Flow with Adaptive Surrogate for Computationally Expensive Models
Yu Wang, Fang Liu, Daniele E. Schiavazzi
Fast inference of numerical model parameters from data is an important prerequisite to generate predictive models for a wide range of applications. Use of sampling-based approaches…
Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks
Fan Liu, Shuyu Zhao, Xuelong Dai +1
Meta-learning model can quickly adapt to new tasks using few-shot labeled data. However, despite achieving good generalization on few-shot classification tasks, it is still challen…
Selective Cascade of Residual ExtraTrees
Qimin Liu, Fang Liu
We propose a novel tree-based ensemble method named Selective Cascade of Residual ExtraTrees (SCORE). SCORE draws inspiration from representation learning, incorporates regularized…