Correlation Clustering with Random Partial Information

• URL: http://arxiv.org/abs/2608.16315v1
• Date: Mon, 17 Aug 2026 09:22:22 GMT
• Title: Correlation Clustering with Random Partial Information
• Abstract summary: Correlation clustering is a fundamental unsupervised learning problem.<n>We study a natural class of graphs obtained by randomly subsampling a complete signed graph $G$.<n>We prove approximation guarantees that are substantially better than the bounds achievable for general graphs.
• Score: 4.706621352211144
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Correlation clustering is a fundamental unsupervised learning problem. On complete graphs, both the min-disagreement and min-max objectives admit constant-factor approximations, yet on general (non-complete) graphs, the best guarantees blow up to $O(\log n)$ and $O(\sqrt{n})$. This gap between the two regimes motivates the following question: are there classes of incomplete graphs that circumvent the lower bounds on general graphs and admit approximation guarantees approaching those attainable on complete graphs? We study a natural class of graphs obtained by randomly subsampling a complete signed graph $G$, where each edge is independently deleted with probability $q$. For such graph instances both for the min-max and the min-disagreement objectives, we prove approximation guarantees (depending on $q$) that are substantially better than the bounds achievable for general graphs. We supplement our theoretical results with experiments that also suggest that the approximation ratios of our algorithm are close to those of the complete graph and better than the worst-case bounds for general (non-complete) graphs.

Related papers

• Simultaneous variances of Pauli strings, weighted independence numbers, and a new kind of perfection of graphs [13.60873698530933]
  A graph that encodes its commutatitivity structure, i.e., by its frustration graph, provides a natural interface between graph theory and quantum information.<n>We call this class $hbar$-perfect, as it extends the class of perfect and $h$-perfect graphs.<n>We find efficient schemes for entanglement detection, a connection to the complexity of shadow tomography, tight uncertainty relations and a construction for computing good lower on ground state energies.
  arXiv  Detail & Related papers  (2025-11-17T16:05:28Z)
• On Approximate MMS Allocations on Restricted Graph Classes [0.31457219084519]
  We study the problem of fair division of a set of indivisible goods with connectivity constraints.<n>It is known that for some classes of graphs, such as complete graphs, cycles, and $d$-claw-free graphs for any fixed $d$, such approximate allocations indeed exist.<n>We show that such allocations exist for several well-studied classes, including block graphs, cacti, complete multipartite graphs, and split graphs.
  arXiv  Detail & Related papers  (2025-08-08T14:17:44Z)
• Efficient Graph Matching for Correlated Stochastic Block Models [7.320365821066744]
  We study learning problems on correlated block models with two balanced communities.<n>Our main result gives the first efficient algorithm for graph matching in this setting.<n>We extend this to an efficient algorithm for exact graph matching whenever this is information-theoretically possible.
  arXiv  Detail & Related papers  (2024-12-03T18:36:45Z)
• MGNet: Learning Correspondences via Multiple Graphs [78.0117352211091]
  Learning correspondences aims to find correct correspondences from the initial correspondence set with an uneven correspondence distribution and a low inlier rate. Recent advances usually use graph neural networks (GNNs) to build a single type of graph or stack local graphs into the global one to complete the task. We propose MGNet to effectively combine multiple complementary graphs.
  arXiv  Detail & Related papers  (2024-01-10T07:58:44Z)
• Improved High-Probability Regret for Adversarial Bandits with Time-Varying Feedback Graphs [62.52390282012508]
  We study high-probability regret bounds for adversarial $K$-armed bandits with time-varying feedback graphs over $T$ rounds. We develop an algorithm that achieves the optimal regret $widetildemathcalO((sum_t=1Talpha_t)1/2+max_tin[T]alpha_t]$ with high probability. We also develop the first algorithm that achieves the optimal high-probability regret bound for weakly observable graphs.
  arXiv  Detail & Related papers  (2022-10-04T04:36:15Z)
• Collaborative likelihood-ratio estimation over graphs [55.98760097296213]
  Graph-based Relative Unconstrained Least-squares Importance Fitting (GRULSIF) We develop this idea in a concrete non-parametric method that we call Graph-based Relative Unconstrained Least-squares Importance Fitting (GRULSIF) We derive convergence rates for our collaborative approach that highlights the role played by variables such as the number of available observations per node, the size of the graph, and how accurately the graph structure encodes the similarity between tasks.
  arXiv  Detail & Related papers  (2022-05-28T15:37:03Z)
• The Performance of the MLE in the Bradley-Terry-Luce Model in $\ell_{\infty}$-Loss and under General Graph Topologies [76.61051540383494]
  We derive novel, general upper bounds on the $ell_infty$ estimation error of the Bradley-Terry-Luce model. We demonstrate that the derived bounds perform well and in some cases are sharper compared to known results.
  arXiv  Detail & Related papers  (2021-10-20T23:46:35Z)
• Settling the Sharp Reconstruction Thresholds of Random Graph Matching [19.54246087326288]
  We study the problem of recovering the hidden correspondence between two edge-correlated random graphs. For dense graphs with $p=n-o(1)$, we prove that there exists a sharp threshold. For sparse ErdHos-R'enyi graphs with $p=n-Theta(1)$, we show that the all-or-nothing phenomenon no longer holds.
  arXiv  Detail & Related papers  (2021-01-29T21:49:50Z)
• Random Graph Matching with Improved Noise Robustness [2.294014185517203]
  We propose a new algorithm for graph matching under probabilistic models. Our algorithm recovers the underlying matching with high probability when $alpha le 1 / (log log n)C$. This improves the condition $alpha le 1 / (log n)C$ achieved in previous work.
  arXiv  Detail & Related papers  (2021-01-28T02:39:27Z)
• Multilevel Graph Matching Networks for Deep Graph Similarity Learning [79.3213351477689]
  We propose a multi-level graph matching network (MGMN) framework for computing the graph similarity between any pair of graph-structured objects. To compensate for the lack of standard benchmark datasets, we have created and collected a set of datasets for both the graph-graph classification and graph-graph regression tasks. Comprehensive experiments demonstrate that MGMN consistently outperforms state-of-the-art baseline models on both the graph-graph classification and graph-graph regression tasks.
  arXiv  Detail & Related papers  (2020-07-08T19:48:19Z)
• Graph Pooling with Node Proximity for Hierarchical Representation Learning [80.62181998314547]
  We propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Results show that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.
  arXiv  Detail & Related papers  (2020-06-19T13:09:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.