arXiv subjects

Yongyu Wang

Publications and source records attributed to Yongyu Wang.

18 recordsLinked to original sources

arXiv2026

Spectrally unstable nodes drive reliability failures in graph learning

Graph-learning algorithms can fail when graph structure is adversarially perturbed, intrinsically noisy or constructed from imperfect observations. Here we show that some nodes bear much greater responsibility than others for allowing adversarial perturbations and intrinsic noise to harm graph-learning algorithms. Building on graph-spectral distortion analysis, we identify these failure-driving nodes and introduce a reliability-aware intervention that isolates them from the main learning step. The target algorithm is applied to a stable induced subgraph, and predictions for isolated nodes are recovered through topology- or centroid-based propagation. Across graph neural networks under targeted and non-targeted structural attacks, spectral hypergraph clustering and multi-view spectral clustering, this principle improves reliability under both adversarial and intrinsic noise. These results suggest that node-level spectral instability provides a common mechanism for understanding and mitigating reliability failures in graph learning.

cs.LG↗

arXiv2026

Spectral structural distortion reveals redundant neurons in neural networks

Overparameterized neural networks often contain many removable neurons, yet what makes a neuron redundant remains poorly understood. Existing pruning criteria commonly rely on local quantities such as weight magnitude, activation strength, or gradient sensitivity, but these measures provide limited insight into the structural role of a neuron in the transformation performed by a layer. Here we show that neuronal redundancy can be characterized by weak participation in the spectral structural distortion induced by layer-wise representation transformations. For each hidden layer of a trained network, we record pre-activation and post-activation hidden states, model neurons as graph nodes, and construct input-side and output-side graphs that describe neuron-level relational structure before and after the layer transformation. We then define a spectral structural importance score that measures the contribution of each neuron to the dominant graph-spectral distortion between these two relational structures. Low-participation neurons are treated as structurally redundant and removed through an iterative pruning process in which scores are recomputed after each structural change. No parameter updates are performed during intermediate pruning rounds; after the target parameter reduction is reached, a single recovery fine-tuning stage is applied to the compact model. Direct ablation analysis and experiments across conventional neural networks, encoder-only Transformers, and decoder-only language models show that this graph-spectral criterion identifies removable neurons and Transformer units while preserving task performance after compression. These results suggest that neural redundancy is not merely a consequence of small weights or weak activations, but can be understood through weak participation in the spectral distortion of layer-wise relational structure.

cs.LG↗

arXiv2026

T2T-LA: A Topology-to-Topology LLM Agent for Graph Learning with Neither Feature Access nor Task Knowledge

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 optimization states are often modeled as graph-structured objects. Existing graph learning methods usually rely on carefully designed graph construction rules, extensive parameter tuning, and sophisticated mathematical theory; moreover, achieving good performance often requires task-specific graph construction tailored to the downstream objective. In this work, we study whether a large language model (LLM) can reason about graph structure and infer a useful topology without observing the feature matrix, without knowing the downstream task, and without relying on any carefully designed graph construction algorithm or parameter tuning process. To this end, we propose T2T-LA, a Topology-to-Topology LLM Agent that receives no input other than a set of previously failed topologies and the scores assigned to them by a private scorer. The agent is not told what task or algorithm produces the scores, how these topologies are generated, or what the scores mean. Since none of the observed topologies is satisfactory, T2T-LA cannot simply imitate a good example. Instead, it is forced to infer hidden relationships between graph connectivity patterns and the observed scores, a capability that is particularly relevant to CAD scenarios where useful design structures may be difficult to specify manually. Experimental results show that T2T-LA can generate, in one shot, a graph topology that enables the downstream algorithm to produce a sufficiently good solution, suggesting a new LLM-driven direction for topology reasoning and graph representation learning in ML-for-CAD workflows.

cs.LG↗

arXiv2025

Improving Collaborative Filtering Recommendation via Graph Learning

Recommendation systems aim to provide personalized predictions by identifying items that are most appealing to individual users. Among various recommendation approaches, k-nearest-neighbor (kNN)-based collaborative filtering (CF) remains one of the most widely used in practice. However, the kNN scheme often results in running the algorithm on a highly dense graph, which degrades computational efficiency. In addition, enforcing a uniform neighborhood size is not well suited to capturing the true underlying structure of the data. In this paper, we leverage recent advances in graph signal processing (GSP) to learn a sparse yet high-quality graph, improving the efficiency of collaborative filtering without sacrificing recommendation accuracy. Experiments on benchmark datasets demonstrate that our method can successfully perform CF-based recommendation using an extremely sparse graph while maintaining competitive performance.

cs.IR↗

arXiv2025

Defending Collaborative Filtering Recommenders via Adversarial Robustness Based Edge Reweighting

User based collaborative filtering (CF) relies on a user and user similarity graph, making it vulnerable to profile injection (shilling) attacks that manipulate neighborhood relations to promote (push) or demote (nuke) target items. In this work, we propose an adversarial robustness based edge reweighting defense for CF. We first assign each user and user edge a non robustness score via spectral adversarial robustness evaluation, which quantifies the edge sensitivity to adversarial perturbations. We then attenuate the influence of non robust edges by reweighting similarities during prediction. Extensive experiments demonstrate that the proposed method effectively defends against various types of attacks.

cs.LG↗

arXiv2025

Adversarial-Robustness-Guided Graph Pruning

Graph learning plays a central role in many data mining and machine learning tasks, such as manifold learning, data representation and analysis, dimensionality reduction, clustering, and visualization. In this work, we propose a highly scalable, adversarial-robustness-guided graph pruning framework for learning graph topologies from data. By performing a spectral adversarial robustness evaluation, our method aims to learn sparse, undirected graphs that help the underlying algorithms resist noise and adversarial perturbations. In particular, we explicitly identify and prune edges that are most vulnerable to adversarial attacks. We use spectral clustering, one of the most representative graph-based machine learning algorithms, to evaluate the proposed framework. Compared with prior state-of-the-art graph learning approaches, the proposed method is more scalable and significantly improves both the computational efficiency and the solution quality of spectral clustering.

cs.CV↗

arXiv2025

Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defenses

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 information encoded in the graph topology. This joint modeling, however, also introduces a critical weakness: perturbations or noise in either the structure or the features can be amplified through message passing, making GNNs highly vulnerable to adversarial attacks and spurious connections. In this work, we introduce a pruning framework that leverages adversarial robustness evaluation to explicitly identify and remove fragile or detrimental components of the graph. By using robustness scores as guidance, our method selectively prunes edges that are most likely to degrade model reliability, thereby yielding cleaner and more resilient graph representations. We instantiate this framework on three representative GNN architectures and conduct extensive experiments on benchmarks. The experimental results show that our approach can significantly enhance the defense capability of GNNs in the high-perturbation regime.

cs.LG↗

arXiv2024

Enabling DBSCAN for Very Large-Scale High-Dimensional Spaces

DBSCAN is one of the most important non-parametric unsupervised data analysis tools. By applying DBSCAN to a dataset, two key analytical results can be obtained: (1) clustering data points based on density distribution and (2) identifying outliers in the dataset. However, the time complexity of the DBSCAN algorithm is $O(n^2 β)$, where $n$ is the number of data points and $β= O(D)$, with $D$ representing the dimensionality of the data space. As a result, DBSCAN becomes computationally infeasible when both $n$ and $D$ are large. In this paper, we propose a DBSCAN method based on spectral data compression, capable of efficiently processing datasets with a large number of data points ($n$) and high dimensionality ($D$). By preserving only the most critical structural information during the compression process, our method effectively removes substantial redundancy and noise. Consequently, the solution quality of DBSCAN is significantly improved, enabling more accurate and reliable results.

cs.CV↗

arXiv2024

Mitigating the Impact of Noisy Edges on Graph-Based Algorithms via Adversarial Robustness Evaluation

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 present within the constructed graphs. In this paper, we view these noisy edges as adversarial attack and propose to use a spectral adversarial robustness evaluation method to mitigate the impact of noisy edges on the performance of graph-based algorithms. Our method identifies the points that are less vulnerable to noisy edges and leverages only these robust points to perform graph-based algorithms. Our experiments demonstrate that our methodology is highly effective and outperforms state-of-the-art denoising methods by a large margin.

cs.LG↗

arXiv2024

Enhancing Graph Topology and Clustering Quality: A Modularity-Guided Approach

Current modularity-based community detection algorithms attempt to find cluster memberships that maximize modularity within a fixed graph topology. Diverging from this conventional approach, our work introduces a novel strategy that employs modularity to guide the enhancement of both graph topology and clustering quality through a maximization process. Specifically, we present a modularity-guided approach for learning sparse graphs with high modularity by iteratively pruning edges between distant clusters, informed by algorithmically generated clustering results. To validate the theoretical underpinnings of modularity, we designed experiments that establish a quantitative relationship between modularity and clustering quality. Extensive experiments conducted on various real-world datasets demonstrate that our method significantly outperforms state-of-the-art graph construction methods in terms of clustering accuracy. Moreover, when compared to these leading methods, our approach achieves up to a hundredfold increase in graph construction efficiency on large-scale datasets, illustrating its potential for broad application in complex network analysis.

physics.data-an↗

arXiv2023

Towards High-Performance Exploratory Data Analysis (EDA) Via Stable Equilibrium Point

Exploratory data analysis (EDA) is a vital procedure for data science projects. In this work, we introduce a stable equilibrium point (SEP) - based framework for improving the efficiency and solution quality of EDA. By exploiting the SEPs to be the representative points, our approach aims to generate high-quality clustering and data visualization for large-scale data sets. A very unique property of the proposed method is that the SEPs will directly encode the clustering properties of data sets. Compared with prior state-of-the-art clustering and data visualization methods, the proposed methods allow substantially improving computing efficiency and solution quality for large-scale data analysis tasks.

cs.LG↗

arXiv2023

Accelerate Support Vector Clustering via Spectrum-Preserving Data Compression

This paper proposes a novel framework for accelerating support vector clustering. The proposed method first computes much smaller compressed data sets while preserving the key cluster properties of the original data sets based on a novel spectral data compression approach. Then, the resultant spectrally-compressed data sets are leveraged for the development of fast and high quality algorithm for support vector clustering. We conducted extensive experiments using real-world data sets and obtained very promising results. The proposed method allows us to achieve 100X and 115X speedups over the state of the art SVC method on the Pendigits and USPS data sets, respectively, while achieving even better clustering quality. To the best of our knowledge, this represents the first practical method for high-quality and fast SVC on large-scale real-world data sets

cs.LG↗

arXiv2023

Improving Spectral Clustering Using Spectrum-Preserving Node Aggregation

Spectral clustering is one of the most popular clustering methods. However, the high computational cost due to the involved eigen-decomposition procedure can immediately hinder its applications in large-scale tasks. In this paper we use spectrum-preserving node reduction to accelerate eigen-decomposition and generate concise representations of data sets. Specifically, we create a small number of pseudonodes based on spectral similarity. Then, standard spectral clustering algorithm is performed on the smaller node set. Finally, each data point in the original data set is assigned to the cluster as its representative pseudo-node. The proposed framework run in nearly-linear time. Meanwhile, the clustering accuracy can be significantly improved by mining concise representations. The experimental results show dramatically improved clustering performance when compared with state-of-the-art methods.

cs.LG↗

arXiv2021

Accelerate 3D Object Processing via Spectral Layout

3D image processing is an important problem in computer vision and pattern recognition fields. Compared with 2D image processing, its computation difficulty and cost are much higher due to the extra dimension. To fundamentally address this problem, we propose to embed the essential information in a 3D object into 2D space via spectral layout. Specifically, we construct a 3D adjacency graph to capture spatial structure of the 3D voxel grid. Then we calculate the eigenvectors corresponding to the second and third smallest eigenvalues of its graph Laplacian and perform spectral layout to map each voxel into a pixel in 2D Cartesian coordinate plane. The proposed method can achieve high quality 2D representations for 3D objects, which enables to use 2D-based methods to process 3D objects. The experimental results demonstrate the effectiveness and efficiency of our method.

cs.CV↗

arXiv2020

GRASPEL: Graph Spectral Learning at Scale

Learning meaningful graphs from data plays important roles in many data mining and machine learning tasks, such as data representation and analysis, dimension reduction, data clustering, and visualization, etc. In this work, for the first time, we present a highly-scalable spectral approach (GRASPEL) for learning large graphs from data. By limiting the precision matrix to be a graph Laplacian, our approach aims to estimate ultra-sparse (tree-like) weighted undirected graphs and shows a clear connection with the prior graphical Lasso method. By interleaving the latest high-performance nearly-linear time spectral methods for graph sparsification, coarsening and embedding, ultra-sparse yet spectrally-robust graphs can be learned by identifying and including the most spectrally-critical edges into the graph. Compared with prior state-of-the-art graph learning approaches, GRASPEL is more scalable and allows substantially improving computing efficiency and solution quality of a variety of data mining and machine learning applications, such as spectral clustering (SC), and t-Distributed Stochastic Neighbor Embedding (t-SNE). {For example, when comparing with graphs constructed using existing methods, GRASPEL achieved the best spectral clustering efficiency and accuracy.

cs.LG↗

arXiv2020

GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding

Graph embedding techniques have been increasingly deployed in a multitude of different applications that involve learning on non-Euclidean data. However, existing graph embedding models either fail to incorporate node attribute information during training or suffer from node attribute noise, which compromises the accuracy. Moreover, very few of them scale to large graphs due to their high computational complexity and memory usage. In this paper we propose GraphZoom, a multi-level framework for improving both accuracy and scalability of unsupervised graph embedding algorithms. GraphZoom first performs graph fusion to generate a new graph that effectively encodes the topology of the original graph and the node attribute information. This fused graph is then repeatedly coarsened into much smaller graphs by merging nodes with high spectral similarities. GraphZoom allows any existing embedding methods to be applied to the coarsened graph, before it progressively refine the embeddings obtained at the coarsest level to increasingly finer graphs. We have evaluated our approach on a number of popular graph datasets for both transductive and inductive tasks. Our experiments show that GraphZoom can substantially increase the classification accuracy and significantly accelerate the entire graph embedding process by up to 40.8x, when compared to the state-of-the-art unsupervised embedding methods.

cs.LG↗

arXiv2018

Nearly-Linear Time Spectral Graph Reduction for Scalable Graph Partitioning and Data Visualization

This paper proposes a scalable algorithmic framework for spectral reduction of large undirected graphs. The proposed method allows computing much smaller graphs while preserving the key spectral (structural) properties of the original graph. Our framework is built upon the following two key components: a spectrum-preserving node aggregation (reduction) scheme, as well as a spectral graph sparsification framework with iterative edge weight scaling. We show that the resulting spectrally-reduced graphs can robustly preserve the first few nontrivial eigenvalues and eigenvectors of the original graph Laplacian. In addition, the spectral graph reduction method has been leveraged to develop much faster algorithms for multilevel spectral graph partitioning as well as t-distributed Stochastic Neighbor Embedding (t-SNE) of large data sets. We conducted extensive experiments using a variety of large graphs and data sets, and obtained very promising results. For instance, we are able to reduce the "coPapersCiteseer" graph with 0.43 million nodes and 16 million edges to a much smaller graph with only 13K (32X fewer) nodes and 17K (950X fewer) edges in about 16 seconds; the spectrally-reduced graphs also allow us to achieve up to 1100X speedup for spectral graph partitioning and up to 60X speedup for t-SNE visualization of large data sets.

cs.DS↗

arXiv2018

Towards Scalable Spectral Clustering via Spectrum-Preserving Sparsification

The eigendeomposition of nearest-neighbor (NN) graph Laplacian matrices is the main computational bottleneck in spectral clustering. In this work, we introduce a highly-scalable, spectrum-preserving graph sparsification algorithm that enables to build ultra-sparse NN (u-NN) graphs with guaranteed preservation of the original graph spectrums, such as the first few eigenvectors of the original graph Laplacian. Our approach can immediately lead to scalable spectral clustering of large data networks without sacrificing solution quality. The proposed method starts from constructing low-stretch spanning trees (LSSTs) from the original graphs, which is followed by iteratively recovering small portions of "spectrally critical" off-tree edges to the LSSTs by leveraging a spectral off-tree embedding scheme. To determine the suitable amount of off-tree edges to be recovered to the LSSTs, an eigenvalue stability checking scheme is proposed, which enables to robustly preserve the first few Laplacian eigenvectors within the sparsified graph. Additionally, an incremental graph densification scheme is proposed for identifying extra edges that have been missing in the original NN graphs but can still play important roles in spectral clustering tasks. Our experimental results for a variety of well-known data sets show that the proposed method can dramatically reduce the complexity of NN graphs, leading to significant speedups in spectral clustering.

cs.LG↗