首页/论文/2007.00533

arXiv 2007.005332020-07stat.MLcs.DScs.LGcs.SImath.PR

Partial Recovery in the Graph Alignment Problem

INSEAD（欧洲工商管理学院）；INRIA（法国国家信息与自动化研究所）

Georgina Hall, Laurent Massoulié

英文摘要：

In this paper, we consider the graph alignment problem, which is the problem of recovering, given two graphs, a one-to-one mapping between nodes that maximizes edge overlap. This problem can be viewed as a noisy version of the well-known graph isomorphism problem and appears in many applications, including social network deanonymization and cellular biology. Our focus here is on partial recovery, i.e., we look for a one-to-one mapping which is correct on a fraction of the nodes of the graph rather than on all of them, and we assume that the two input graphs to the problem are correlated Erdős-Rényi graphs of parameters $(n,q,s)$. Our main contribution is then to give necessary and sufficient conditions on $(n,q,s)$ under which partial recovery is possible with high probability as the number of nodes $n$ goes to infinity. In particular, we show that it is possible to achieve partial recovery in the $nqs=Θ(1)$ regime under certain additional assumptions.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Impossibility of Partial Recovery in the Graph Alignment Problem

INRIA（法国国家信息与自动化研究所）；DI/ENS（巴黎高等师范学院计算机科学系）；PSL Research University（巴黎文理研究大学）；MSR-Inria Joint Centre（微软研究院-INRIA联合中心）

Random graph alignment refers to recovering the underlying vertex correspondence between two random graphs with correlated edges. This can be viewed as an average-case and noisy version of the well-known graph isomorphism problem. For the correlated Erdös-Rényi model, we prove an impossibility result for partial recovery in the sparse regime, with constant average degree and correlation, as well as a general bound on the maximal reachable overlap. Our bound is tight in the noiseless case (the graph isomorphism problem) and we conjecture that it is still tight with noise. Our proof technique re…

2021-06-29cs.LGmath.PRmath.ST

Partial Recovery for Top-$k$ Ranking: Optimality of MLE and Sub-Optimality of Spectral Method

Given partially observed pairwise comparison data generated by the Bradley-Terry-Luce (BTL) model, we study the problem of top-$k$ ranking. That is, to optimally identify the set of top-$k$ players. We derive the minimax rate with respect to a normalized Hamming loss. This provides the first result in the literature that characterizes the partial recovery error in terms of the proportion of mistakes for top-$k$ ranking. We also derive the optimal signal to noise ratio condition for the exact recovery of the top-$k$ set. The maximum likelihood estimator (MLE) is shown to achieve both optimal pa…

2021-07-15math.STstat.MLstat.TH

Partial Recovery Bounds for the Sparse Stochastic Block Model

In this paper, we study the information-theoretic limits of community detection in the symmetric two-community stochastic block model, with intra-community and inter-community edge probabilities $\frac{a}{n}$ and $\frac{b}{n}$ respectively. We consider the sparse setting, in which $a$ and $b$ do not scale with $n$, and provide upper and lower bounds on the proportion of community labels recovered on average. We provide a numerical example for which the bounds are near-matching for moderate values of $a - b$, and matching in the limit as $a-b$ grows large.

2016-04-04cs.ITcs.SImath.IT

SGA: A Robust Algorithm for Partial Recovery of Tree-Structured Graphical Models with Noisy Samples

National University of Singapore（新加坡国立大学）

We consider learning Ising tree models when the observations from the nodes are corrupted by independent but non-identically distributed noise with unknown statistics. Katiyar et al. (2020) showed that although the exact tree structure cannot be recovered, one can recover a partial tree structure; that is, a structure belonging to the equivalence class containing the true tree. This paper presents a systematic improvement of Katiyar et al. (2020). First, we present a novel impossibility result by deriving a bound on the necessary number of samples for partial recovery. Second, we derive a sign…

2021-01-22cs.ITcs.LGmath.IT

潜变量动力系统中的状态耦合波动性：部分观测下的恢复

State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observation

The Herbert Wertheim School of Public Health and Human Longevity Science（赫伯特·韦特海姆公共卫生与人类长寿科学学院）；University of California San Diego（加州大学圣地亚哥分校）

提出状态耦合随机波动框架，利用粒子期望最大化算法在部分观测下估计潜变量过程方差与平衡点位移的关系，并通过仿真验证了恢复与检测性能。

2026-06-01cs.LGstat.ML

Community Detection with Known, Unknown, or Partially Known Auxiliary Latent Variables

The University of Texas at Dallas（德克萨斯大学达拉斯分校）

Empirical observations suggest that in practice, community membership does not completely explain the dependency between the edges of an observation graph. The residual dependence of the graph edges are modeled in this paper, to first order, by auxiliary node latent variables that affect the statistics of the graph edges but carry no information about the communities of interest. We then study community detection in graphs obeying the stochastic block model and censored block model with auxiliary latent variables. We analyze the conditions for exact recovery when these auxiliary latent variabl…

2023-01-08cs.ITcs.LGcs.SI

更多相关论文收起更多论文

通过协作对齐的联邦LoRA微调大型语言模型

Federated LoRA Fine-Tuning for LLMs via Collaborative Alignment

School of Computing & Data Science, The University of Hong Kong（计算与数据科学学院，香港大学）

本文研究了在联邦学习环境下使用LoRA进行参数高效微调的问题，提出了一种名为CLAIR的框架，通过结构低秩加块稀疏分解来恢复共享LoRA子空间并检测污染客户端，从而在噪声情况下实现精确恢复，并在不同条件下实现稳定和一致的协作集恢复。

2026-05-20cs.LGstat.ML

Sparse Recovery via Partial Regularization: Models, Theory and Algorithms

Simon Fraser University（西蒙弗雷泽大学）

In the context of sparse recovery, it is known that most of existing regularizers such as $\ell_1$ suffer from some bias incurred by some leading entries (in magnitude) of the associated vector. To neutralize this bias, we propose a class of models with partial regularizers for recovering a sparse solution of a linear system. We show that every local minimizer of these models is sufficiently sparse or the magnitude of all its nonzero entries is above a uniform constant depending only on the data of the linear system. Moreover, for a class of partial regularizers, any global minimizer of these …

2015-11-23cs.ITcs.LGmath.IT

结构化预测中的部分推断

Partial Inference in Structured Prediction

Purdue University（普渡大学）

针对结构化预测中的部分推断问题，提出基于生成模型的两阶段凸优化标签恢复方法，并从 KKT 条件及原始-对偶构造出发给出可证明的统计与拓扑保证。

2023-06-06cs.LGstat.ML

部分相关图对齐的信息论阈值

Information-Theoretic Thresholds for the Alignments of Partially Correlated Graphs

本文针对部分相关的 Erdős-Rényi 图模型，确定了恢复隐藏顶点对应关系的信息论阈值，并给出了部分恢复与精确恢复的最优速率。

2025-10-07cs.ITmath.ITmath.ST

带属性网络对齐：统计极限与高效算法

Attributed Network Alignment: Statistical Limits and Efficient Algorithm

Tsinghua University（清华大学）；Weiyang College, Tsinghua University（清华大学未央学院）

本文研究在观察到边权重和节点特征时恢复两个相关图间隐藏顶点对应关系的问题，提出带属性相关高斯威根模型，并设计QPAlign算法，理论和实验均展示其有效性。

2026-04-06math.STstat.MLstat.TH

Sparse Partial Least Squares for Coarse Noisy Graph Alignment

University of Florida（佛罗里达大学）；Rice University（莱斯大学）

Graph signal processing (GSP) provides a powerful framework for analyzing signals arising in a variety of domains. In many applications of GSP, multiple network structures are available, each of which captures different aspects of the same underlying phenomenon. To integrate these different data sources, graph alignment techniques attempt to find the best correspondence between vertices of two graphs. We consider a generalization of this problem, where there is no natural one-to-one mapping between vertices, but where there is correspondence between the community structures of each graph. Beca…

2021-04-06cs.LGcs.SIeess.SP

Band Target Entropy Minimization and Target Partial Least Squares for Spectral Recovery and Calibration

The resolution and calibration of pure spectra of minority components in measurements of chemical mixtures without prior knowledge of the mixture is a challenging problem. In this work, a combination of band target entropy minimization (BTEM) and target partial least squares (T-PLS) was used to obtain estimates for single pure component spectra and to calibrate those estimates in a true, one-at-a-time fashion. This approach allows for minor components to be targeted and their relative amounts estimated in the presence of other varying components in spectral data. The use of T-PLS estimation is…

2018-03-27stat.APstat.ML

多图对齐的可行性：一种贝叶斯方法

The feasibility of multi-graph alignment: a Bayesian approach

INRIA Paris, PSL Research University（巴黎国家信息与自动化研究所，巴黎文理研究大学）

研究随机多图对齐的可行性阈值，在高斯模型中揭示“全有或全无”现象，在稀疏Erdős-Rényi模型中严格识别部分对齐的阈值，并开发了度量空间上的通用贝叶斯估计框架。

2026-05-22math.PRmath.STstat.ML

Iterative Algorithm for Discrete Structure Recovery

We propose a general modeling and algorithmic framework for discrete structure recovery that can be applied to a wide range of problems. Under this framework, we are able to study the recovery of clustering labels, ranks of players, signs of regression coefficients, cyclic shifts, and even group elements from a unified perspective. A simple iterative algorithm is proposed for discrete structure recovery, which generalizes methods including Lloyd's algorithm and the power method. A linear convergence result for the proposed algorithm is established in this paper under appropriate abstract condi…

2020-09-27math.STstat.COstat.ME

基于部分 Gromov-Wasserstein 距离的鲁棒对齐

Robust Alignment via Partial Gromov-Wasserstein Distances

针对 Gromov-Wasserstein (GW) 对齐对异常值敏感的问题，提出基于部分 GW 距离的估计器，通过修剪部分质量实现鲁棒对齐，并证明其在总体和有限样本下分别具有极小极大最优和近似最优性。

2025-06-26math.STstat.MLstat.TH