Graph Edge Sparsification

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, up 80% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 45

All topics

Reinforcement Learning-Guided Graph Transformations for SpTRSV Optimization
Sep 30, 2026Buse YılmazMultiplex Graph Transformers Graph Edge Sparsification
Department of Computer Engineering, MEF University, Huzur, Maslak Ayazağ̆a Cd., İstanbul, Turkey.
Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph Signals
Sep 30, 2026Jinwei Li, Daniel TenbrinckResidual Conditional Diffusion Model Graph Edge Sparsification
Department of Data Science Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen, Germany
Pheno-GS: Phenoscape-scale Geodesic Sinkhorn
Sep 23, 2026Alistair Wilkinson, Christopher J. Tape, Smita KrishnaswamyFused Sinkhorn-Localized Similarity Single-Cell Rna
Department of Oncology, University College London, London, UK. · Department of Computer Science, Yale University, New Haven, CT, USA.
Graph Learning with Spectral Connectivity Priors for Scarce Data
Sep 23, 2026Mingxiao Liu, Bahar Oveisgharan, Bingyan Zou +3Graph Edge Sparsification Graph Laplacians
Tsinghua University, China · York University, Canada
Dual-GNN Multilevel Coarsening for Maximum Independent Set
Sep 21, 2026Tianfeng Chen, Xianyue LiSalesman Problem Graph Edge Sparsification
School of Mathematics and Statistics Lanzhou University
Provable Guarantees for Spectral Structured Prediction
Sep 16, 2026Violet Zheng, Jean HonorioGraph Edge Sparsification Provable Guarantees
CIS, The University of Melbourne
Learning structural balance of graphs from quantum spectral features
Sep 11, 2026Stefano Scali, Oleksandr KyriienkoGraph Edge Sparsification Qubit
Department of Physics and Astronomy, University of Exeter, Exeter EX4 4QL, UK · School of Mathematical and Physical Sciences, University of Sheffield, Sheffield S10 2TN, UK
When does a spectral prior help graph learning? Connectivity-loss estimation under road-network disruptions
Sep 11, 2026Van-Truong LeGraph Edge Sparsification Mean Squared Error
Faculty of Information Technology, University of Science, Viet Nam National University Ho Chi Minh City, Viet Nam
Kernel-Complexity Edge Sanitization for Training-Free Defense against Structural Graph Attacks
Sep 9, 2026Yaning Jia, Shenyang Deng, Yaoqing Yang +3Graph Neural Networks Graph Edge Sparsification
Department of Computer Science Dartmouth College Hanover, New Hampshire, USA
Concept drift mitigation through community and spectral graph analysis for the detectionof cyberattacks in network traffic
Sep 8, 2026Julien Michel, Abdul Qadir Khan, Majed Jaber +1Threat Detection Generalist Graph Anomaly Detection
Laboratoire de Recherche de l’EPITA, 14-16 Rue Voltaire, Le Kremlin-Bicêtre, 94270, France · ICube, UMR7357, Université de Strasbourg, Strasbourg, 67000, France
Geometry-Aware Graph Construction via Adaptive Spectral Bandwidth Control
Sep 3, 2026Ecem Bozkurt, Antonio OrtegaGraph Edge Sparsification Kernel Method
Department of Electrical and Computer Engineering University of Southern California, Los Angeles, CA, USA
Domain-Aware Lightweight Spectral-Grouped Convolutions for Hyperspectral Fish Freshness Classification
Aug 12, 2026Kazi Nabiul Alam, Pooneh Bagheri Zadeh, Akbar Sheikh-AkbariHyperspectral Image Convolutional
School of Built Environment, Engineering, and Computing, Leeds Beckett University. Leeds LS6 3QS, United Kingdom.
Spectral graph clustering with inhomogeneous latent geometry
Aug 11, 2026Konstantin Avrachenkov, Lucas S. Sibemberg, Alexander Van WerdeGraph Edge Sparsification Spectral Decomposition
Inria Sophia Antipolis, France · Federal University of Rio Grande do Sul, Brazil · University of Münster, Germany
Spectral Embeddings of Degree- $α$ Laplacians in Random Dot Product Graphs
Aug 11, 2026John Park, Ning HaoGraph Edge Sparsification Graph Laplacians
University of Hong Kong · University of Arizona
Edge Sparsification via Temporal Forman-Ricci Curvature for Dynamic Graph Learning
Aug 7, 2026Poupak Azad, Cuneyt Gurcan Akcora, Kiarash ShamsiTemporal Graph Neural Networks Graph Edge Sparsification
University of Manitoba, Canada · University of Central Florida, United States
Physics-Based Molecular Fingerprints from Spectral Graph Theory Provide Efficient Geometry-Aware Measures of Chemical Similarity
Aug 5, 2026Jacob W. Toney, Ayleen Y. Farnood, Samir Darouich +1Molecular Representation Learning Chemical Structures
Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Institute for Theoretical Chemistry, University of Stuttgart, 70569 Stuttgart, Germany +2
Kohn-Sham Spectral Embedding on Sparse Graphs at the Nishimori Temperature for Image Classification
Jul 30, 2026V. S. Usatyuk, D. A. Sapozhnikov, S. I. EgorovGraph Edge Sparsification Image Classification
Department of Computer Engineering, South-West State University (SWSU), Kursk, 305040 Russia · T8 LLC, R&D Department, Information Theory Group, Moscow, 107076 Russia
Does Graph Compression Preserve Signal Propagation?
Jul 25, 2026Kawshik Banerjee, Khaled Mohammed SaifuddinGraph Edge Sparsification Data Compression Methods
School of Computing, Southern Illinois University, Carbondale, IL, USA
Group Invariant Spectral Embedding
Jul 9, 2026Yeari Vigder, Paulina Hoyos, David Thong +3Graph Edge Sparsification Symmetry
Department of Statistics and Operations Research, Tel Aviv University, Tel Aviv, Israel · Department of Mathematics, University of Texas at Austin, Austin, TX, USA · Department of Mathematics, KTH Royal Institute of Technology, Stockholm, Sweden
DiPhon: Diffusion on Graphons for Scalable Graph Generation
Jul 8, 2026Sergio Rozada, Yiming Qin, Manuel Madeira +2Physics-Guided Diffusion Diffusion Models
King Juan Carlos University · EPFL, Lausanne, Switzerland · University of Pennsylvania
Eigenbasis-Independent Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces
Jul 8, 2026Jiaqing Xie, Yuxin WangGraph Edge Sparsification Graph Laplacians
Fudan University
A Generalization Theory for JEPA-Based World Models
Jun 25, 2026Jingyi Cui, Qi Zhang, Hongwei Wen +1Joint-Embedding Predictive Architectures World Models
State Key Lab of General AI, School of Intelligence Science and Technology, Peking University · University of Sydney
A Framework for Directed Hypergraph Signal Processing via tensor t-SVD
Jun 23, 2026Carlos Mundo-Levano, Nicolás Bello, Daniel L. Lau +1Hypergraphs Graph Edge Sparsification
Department of Electrical and Computer Engineering, University of Delaware, Newark, DE 19716, USA · Institute for Financial Services Analytics, University of Delaware, Newark, DE 19716, USA · Department of Electrical and Computer Engineering, University of Kentucky, Lexington, KY 40506, USA
GES-TSP: Graph Edge Sparsification for TSP
Jun 23, 2026Tianfeng Chen, Xianyue LiSalesman Problem Graph Edge Sparsification
School of Mathematics and Statistics Lanzhou Universtiy
Dual-Attention Convolution Experts for Sparse Tensor Completion
Jun 19, 2026Yanlei Liu, Zhenyu LiaoTensor Completion Graph Edge Sparsification
School of Electronic Information and Communications (EIC), Huazhong University of Science and Technology (HUST), Wuhan, China
Improved Convergence Analysis of Topology Dependence in Decentralized SGD
Jun 8, 2026Yuki Takezawa, Anastasia Koloskova, Sebastian U. StichDecentralized Learning Network Topology
Toyota Motor Corporation · University of Zurich · CISPA Helmholtz Center for Information Security
Learnable Token Sparsification for Efficient Gigapixel Whole Slide Image Reasoning
Jun 7, 2026Jingzhi Chen, Landi He, Zhuo Chen +2Whole-Slide Images Graph Edge Sparsification
Shenzhen University of Advanced Technology
Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them
May 22, 2026Snir Hordan, Nadav Dym, Tim SeppeltGraph Edge Sparsification Graph Neural Networks
Faculty of Mathematics Technion - Israel Institute of Technology · IT University of Copenhagen
Minimum Description Length based Granular-Ball Tree Regularization for Spectral Clustering
May 21, 2026Zeqiang Xian, Caihui Liu, Yong Zhang +1Granular-Ball Computing Clustering
Department of Mathematics and Computer Science, Gannan Normal University, Ganzhou 341000, Jiangxi, China · Key Laboratory of Data Science and Artificial Intelligence of Jiangxi Education Institutes, Gannan Normal University, Ganzhou 341000, Jiangxi, China
The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers
May 21, 2026Minh Triet Pham, Ian GallagherGraph Edge Sparsification Heterogeneity
School of Mathematics and Statistics The University of Melbourne, Australia
Neural Acceleration for Graph Partitioning
May 18, 2026Joshua Dennis Booth, Vishvam PatelGraph Edge Sparsification Partitioning
Department of Computer Science University of Alabama in Huntsville Huntsville AL, USA
Topological Signal Processing: An Application-Oriented Tutorial
May 18, 2026Flavia Petruso, Maria Giulia Preti, Dimitri Van De VilleGraph Edge Sparsification Graph Signal Processing
Self-Supervised Learning for Sparse Matrix Reordering
May 17, 2026Ziwei Li, Tao Yuan, Fangfang Liu +3Sparsity Graph Edge Sparsification
Institute of Software, Chinese Academy of Sciences, Beijing, China
Bridging the Gap between Sparse Matrix Reordering and Factorization: A Deep Learning Framework for Fill-in Reduction
May 17, 2026Ziwei Li, Tao Yuan, Shuzi Niu +1Graph Edge Sparsification Factor
Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China
Spectral structural distortion reveals redundant neurons in neural networks
May 14, 2026Yongyu WangNeurons Unstructured Pruning
Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models
May 11, 2026Nikolaos Nakis, Panagiotis Promponas, Konstantinos Tsirkas +4Graph Edge Sparsification Graph Representation Learning
Human Nature Lab, Yale University · Department of Electrical and Computer Engineering, Yale University · Department of Statistics and Data Science, Yale University +1
Spectral Graph Sparsification Preserves Representation Geometry in Graph Neural Networks
May 1, 2026Sanjukta KrishnagopalGraph Edge Sparsification Graph Neural Networks
Department of Computer Science, University of California Santa Barbara
Large-scale semi-supervised learning with online spectral graph sparsification
Apr 29, 2026Daniele Calandriello, Alessandro Lazaric, Michal ValkoGraph Edge Sparsification Sparsity
Team SequeL Inria Lille – Nord Europe, France
Sparse Graph Learning from Sparse Data via Fiedler Number Maximization
Apr 28, 2026Bahar Oveisgharan, Gene Cheung, Andrew EckfordGraph Edge Sparsification Graph Laplacians
York University, Canada
Spectral Embeddings Leak Graph Topology: Theory, Benchmark, and Adaptive Reconstruction
Apr 22, 2026Thinh Nguyen-Cong, Truong-Son Hy, Thang N. DinhGraph Edge Sparsification Federated Graph Learning
Department of Computer Science Virginia Commonwealth University Richmond, VA, USA · Department of Computer Science The University of Alabama at Birmingham Birmingham, AL, USA
Machine Learning-based Two-Stage Graph Sparsification for the Travelling Salesman Problem
Apr 22, 2026Bo-Cheng Lin, Yi Mei, Mengjie ZhangSalesman Problem Graph Edge Sparsification
Centre for Data Science and Artificial Intelligence, and the School of Engineering and Computer Science, Victoria University of Wellington, Wellington, 6140, New Zealand
Improved large-scale graph learning through ridge spectral sparsification
Apr 22, 2026Daniele Calandriello, Ioannis Koutis, Alessandro Lazaric +1Graph Edge Sparsification Graph Laplacians
SequeL team, INRIA Lille - Nord Europe, France · LCSL, IIT, Italy · New Jersey Institute of Technology, USA +1
Faster by Design: Interactive Aerodynamics via Neural Surrogates Trained on Expert-Validated CFD
Apr 20, 2026Nicholas Thumiger, Andrea Bartezzaghi, Mattia Rigotti +5Computational Fluid Dynamic Aerodynamics
IBM Research · Dallara Automobili
Spectral Analysis of Fake News Propagation
Apr 18, 2026Weibin Cai, Reza ZafaraniFake News Detection Spectral
Data Lab, Department of EECS, Syracuse University, New York, USA.
A Spectral Decomposition Framework for Multiscale Nonlinear Dimensionality Reduction
Apr 2, 2026Zeyang Huang, Angelos Chatzimparmpas, Thomas Höllt +1Dimensionality Reduction Graph Edge Sparsification
Linköping University, Sweden · Utrecht University, The Netherlands · University of Bergen, Norway +1

Sep 30, 2026, cs.DCJ/K move · Enter open · S save

Reinforcement Learning-Guided Graph Transformations for SpTRSV Optimization

Buse Yılmaz

Department of Computer Engineering, MEF University, Huzur, Maslak Ayazağ̆a Cd., İstanbul, Turkey.

Multiplex Graph Transformers Graph Edge Sparsification Offline Reinforcement Learning

Open paper AskPDF arXiv

Sparse triangular solve (SpTRSV) is a fundamental kernel in numerous scientific and engineering applications. However, the data dependencies inherent in sparse triangular matrices significantly limit the available parallelism and make efficient workload distribution challenging. Recent graph transformation techniques address these limitations by modifying the dependency graph of the input matrix to improve parallel execution. Existing graph transformation strategies, however, rely on manually designed heuristics, making their development and adaptation to different optimization objectives challenging. This work proposes a reinforcement learning-guided graph transformation framework for SpTRSV, in which graph transformation is formulated as a sequential decision-making problem and an RL agent learns matrix-dependent transformation policies. Experimental results on real-world sparse matrices demonstrate level reductions of up to 94% and reductions of up to 80% in the coefficient of variation of level costs, while modifying only 1.50% of the rows in the highest case. On average, the RL- guided graph transformation achieves a 23% reduction in the number of levels and a 29% reduction in the coefficient of variation of level costs while rewriting only 0.82% of the matrix rows. Although the heuristic strategies generally achieve more aggressive level reduction(between 31% and 46%), the RL-based approach achieves the largest average reduction in the coefficient of variation of level costs, demonstrating its ability to balance competing graph transformation objectives. The results further show that the learned policies can be transferred to previously unseen matrices through curriculum learning and fine-tuning, while zero-shot experiments provide insights into the limitations of generalizing graph transformation policies across different sparsity patterns.

Momentum

Related topics

Latest papers 45