Graph Reconstruction

Follow this topic Ask about this topic

Latest papers

13 papers2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Differentially Private GraphRAG: Protecting Relation Connectivity and Semantics
Nov 6, 2026Jie Fu, Yuan Hong, Yue Ning +1Privacy-Preserving RAG Graph Retrieval-Augmented Generation
Stevens Institute of Technology, Hoboken, NJ, USA · University of Connecticut, Storrs, CT, USA
Not All Latents Are Equal: Importance-Weighted Latent Graph Generation
Nov 5, 2026Biraaj Rout, Jay Revolinsky, Han Liu +1Graph Generation Graph Reconstruction
University of Texas at Arlington · Michigan State University
Decoupled Prune-and-Reconstruct: Training on a Compact Core with Double-Layer Sparsification
Oct 25, 2026Siqi Gu, Gaozhen Ma, Liheng Huang +4Graph Neural Networks Memory-Efficient Training
School of Physics and Electronic Engineering, Nanyang Normal University, Wolong District, Nanyang, 473061, Henan, China · School of Integrated Circuits, Huazhong University of Science and Technology, 1037 Luoyu Road, Hongshan District, Wuhan, 430074, Hubei, China · School of Architecture and Urban Planning, Huazhong University of Science and Technology, 1037 Luoyu Road, Hongshan District, Wuhan, 430074, Hubei, China +1
VisFlow: Interpretable Flow Matching for Visibility Reconstruction, Characterization, and Recognition
Oct 22, 2026Rahul Moorthy, Volkan IslerFlow Matching Graph Reconstruction
Feasible Flow Matching for Graph Reconstruction via Within-Sampling Primal-Dual Guidance
Sep 26, 2026Haoming Chen, Nicolas Zilberstein, Santiago Paternain +1Graph Reconstruction Constrained Generative Modeling
Graph Learning with Spectral Connectivity Priors for Scarce Data
Sep 23, 2026Mingxiao Liu, Bahar Oveisgharan, Bingyan Zou +3Graph Signal Processing Graph Structure Learning
Tsinghua University, China · York University, Canada
Structurally Speaking: Motif-Oriented Graph Captioning through Bidirectional Graph-Text Translation
Sep 10, 2026Hsiao-Ying Lu, Dongyu Liu, Kwan-Liu MaStructured Prompting Graph Reconstruction
Department of Computer Science, University of California, Davis
VisAdj: Learning Adjacency Matrices from Node-Link Images
Aug 22, 2026Jiahao Xie, Guangmo TongGraph Reconstruction Graph Structure Learning
University of Delaware Newark, Delaware, USA
Pairton: Iterative Reconstruction of Short-Lived Particles
Aug 14, 2026Andreas Hermansen, Chris Scheulen, Tobias GollingGraph Reconstruction High-Energy Physics
Département de physique nucléaire et corpusculaire, University of Geneva
ArchEGraph: A Large-Scale Graph Dataset for Geometry-Topology-Physics Aligned Building Energy Modeling
Aug 7, 2026Yihui Li, Yihui Chen, Kaidi Zha +7Graph Reconstruction Benchmark Construction
Tsinghua University · UC Berkeley · 1Tsinghua University 2UC Berkeley 3MIT +4
GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
May 15, 2026Roman Bresson, Konstantinos Divriotis, Johannes F. Lutzeyer +2Molecular Representation Learning Graph Transformer
Mohamed bin Zayed University of Artificial Intelligence · LIX, CNRS, École Polytechnique, IP Paris
Spectral Embeddings Leak Graph Topology: Theory, Benchmark, and Adaptive Reconstruction
Apr 22, 2026Thinh Nguyen-Cong, Truong-Son Hy, Thang N. DinhGraph Reconstruction Spectral Methods
Department of Computer Science Virginia Commonwealth University Richmond, VA, USA · Department of Computer Science The University of Alabama at Birmingham Birmingham, AL, USA
Toward Graph-Tokenizing Large Language Models with Reconstructive Graph Instruction Tuning
Mar 2, 2026Zhongjian Zhang, Xiao Wang, Mengmei Zhang +2Graph Reconstruction LLMs for Graph Learning
Beijing University of Posts and Telecommunications, Beijing, China · Beihang University, Beijing, China · China Telecom Bestpay, Beijing, China

Nov 6, 2026J/K move · Enter open · S save

Differentially Private GraphRAG: Protecting Relation Connectivity and Semantics

Jie Fu, Yuan Hong, Yue Ning, Wendy Hui Wang

Stevens Institute of Technology, Hoboken, NJ, USA · University of Connecticut, Storrs, CT, USA

Privacy-Preserving RAG Graph Retrieval-Augmented Generation Differential Privacy Graph Reconstruction

Open paper AskPDF arXiv

Graph Retrieval-Augmented Generation (GraphRAG) connects information across documents through entity relationships to support relational reasoning. However, black-box access to GraphRAG systems can enable adversaries to reconstruct knowledge graphs and recover both structural connectivity between entities and the semantics of their relationships. Existing defenses lack formal privacy guarantees and provide limited protection against such reconstruction attacks. We propose RelGuard, the first differentially private framework for GraphRAG, which provides formal privacy guarantees by mitigating connectivity leakage and protecting relations and their semantic meaning through relation removal. We formalize relation differential privacy (relation-DP), which bounds the distinguishability of mechanism outputs according to the semantic distance between alternative relations while accounting for relation removal. Building on this definition, we develop a four-step defense mechanism that sanitizes source documents before GraphRAG indexing by perturbing relation predicates or removing their associated connectivity using the exponential mechanism. Experiments across three GraphRAG systems and two targeted reconstruction attacks demonstrate that RelGuard provides stronger protection against reconstruction attacks than four existing defense mechanisms while better preserving downstream utility.