6 papers
Spectral structural distortion reveals redundant neurons in neural networks
Yongyu Wang
Overparameterized neural networks often contain many removable neurons, yet what makes a neuron redundant remains poorly understood. Existing pruning criteria commonly rely on loca…
T2T-LA: A Topology-to-Topology LLM Agent for Graph Learning with Neither Feature Access nor Task Knowledge
Yongyu Wang
Graph learning aims to convert data into graph representations, which are fundamental to many problems in machine learning for CAD, where circuits, layouts, designs, and optimizati…
Defending Collaborative Filtering Recommenders via Adversarial Robustness Based Edge Reweighting
Yongyu Wang
User based collaborative filtering (CF) relies on a user and user similarity graph, making it vulnerable to profile injection (shilling) attacks that manipulate neighborhood relati…
Adversarial-Robustness-Guided Graph Pruning
Yongyu Wang
Graph learning plays a central role in many data mining and machine learning tasks, such as manifold learning, data representation and analysis, dimensionality reduction, clusterin…
Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defenses
Yongyu Wang
Graph Neural Networks (GNNs) have emerged as a dominant paradigm for learning on graph-structured data, thanks to their ability to jointly exploit node features and relational info…
Mitigating the Impact of Noisy Edges on Graph-Based Algorithms via Adversarial Robustness Evaluation
Yongyu Wang, Xiaotian Zhuang
Given that no existing graph construction method can generate a perfect graph for a given dataset, graph-based algorithms are often affected by redundant and erroneous edges presen…