most citedA Topology-aware Graph Coarsening Framework for Continual Graph Learning

3 citations · 3 across the 9 of their papers we have counts for

collaborators

9 papers

cs.SI2025

HyperEF 2.0: Spectral Hypergraph Coarsening via Krylov Subspace Expansion and Resistance-based Local Clustering

Hamed Sajadinia, Zhuo Feng

This paper introduces HyperEF 2.0, a scalable framework for spectral coarsening and clustering of large-scale hypergraphs through hyperedge effective resistances, aiming to decompo…

cs.LG2025

SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds

Wuxinlin Cheng, Yupeng Cao, Jinwen Wu +3

Recent strides in pretrained transformer-based language models have propelled state-of-the-art performance in numerous NLP tasks. Yet, as these models grow in size and deployment,…

cs.SI2025

dyGRASS: Dynamic Spectral Graph Sparsification via Localized Random Walks on GPUs

Yihang Yuan, Ali Aghdaei, Zhuo Feng

This work presents dyGRASS, an efficient dynamic algorithm for spectral sparsification of large undirected graphs that undergo streaming edge insertions and deletions. At its core,…

cs.SI2024

SHyPar: A Spectral Coarsening Approach to Hypergraph Partitioning

Hamed Sajadinia, Ali Aghdaei, Zhuo Feng

State-of-the-art hypergraph partitioners utilize a multilevel paradigm to construct progressively coarser hypergraphs across multiple layers, guiding cut refinements at each level…

cs.LG2024

SGM-PINN: Sampling Graphical Models for Faster Training of Physics-Informed Neural Networks

John Anticev, Ali Aghdaei, Wuxinlin Cheng +1

SGM-PINN is a graph-based importance sampling framework to improve the training efficacy of Physics-Informed Neural Networks (PINNs) on parameterized problems. By applying a graph…

cs.CR2024

Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning

Tao Liu, Yuhang Zhang, Zhu Feng +4

Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimate…