arXiv research

Study optimal spectral estimator for semi-supervised node classification.

Efficient algorithm for CLSBM reduces misclassification rate.

New algorithm optimally clusters networks with side information.

Sharp thresholds and contiguity for community detection in contextual SBM.

A new algorithm tackles graph-based contextual bandits with efficient regret bounds.

CAMS selects best pre-trained model for unlabeled data points.

Graph attention is not always beneficial; conditions for perfect node classification are identified.

We study the stochastic block model with two communities where vertices contain side information in the form of a vertex label. These vertex labels may have arbitrary label distributions, depending on the community memberships. We analyze a linearized version of the popular belief propagation algorithm. We show that th…

A main task in data analysis is to organize data points into coherent groups or clusters. The stochastic block model is a probabilistic model for the cluster structure. This model prescribes different probabilities for the presence of edges within a cluster and between different clusters. We assume that the cluster ass…

The labeled stochastic block model is a random graph model representing networks with community structure and interactions of multiple types. In its simplest form, it consists of two communities of approximately equal size, and the edges are drawn and labeled at random with probability depending on whether their two en…

A novel bandit problem with context-dependent rewards and blocking.

We study the misclassification error for community detection in general heterogeneous stochastic block models (SBM) with noisy or partial label information. We establish a connection between the misclassification rate and the notion of minimum energy on the local neighborhood of the SBM. We develop an optimally weighte…

We study the community detection and recovery problem in partially-labeled stochastic block models (SBM). We develop a fast linearized message-passing algorithm to reconstruct labels for SBM (with $n$ nodes, $k$ blocks, $p,q$ intra and inter block connectivity) when $δ$ proportion of node labels are revealed. The signa…

Study how noisy labels affect semi-supervised learning.

New algorithm IAC recovers hidden communities in labeled SBM with optimal performance.

Study community detection in multi-view data with various types of information.

Paper models graph edge dependencies using latent variables for community detection.

We analyze the information-theoretic limits for the recovery of node labels in several network models. This includes the Stochastic Block Model, the Exponential Random Graph Model, the Latent Space Model, the Directed Preferential Attachment Model, and the Directed Small-world Model. For the Stochastic Block Model, the…

Locally-contextual CRFs improve sequence labeling performance.

The geometric block model is a recently proposed generative model for random graphs that is able to capture the inherent geometric properties of many community detection problems, providing more accurate characterizations of practical community structures compared with the popular stochastic block model. Galhotra et al…

New algorithms detect communities in sparse graphs with labeled data.

New method improves community detection for large networks.

Signed graphs encode positive (attractive) and negative (repulsive) relations between nodes. We extend spectral clustering to signed graphs via the one-parameter family of Signed Power Mean Laplacians, defined as the matrix power mean of normalized standard and signless Laplacians of positive and negative edges. We pro…

New algorithm detects community labels in networks using unlabeled data.

There has been a recent interest in understanding the power of local algorithms for optimization and inference problems on sparse graphs. Gamarnik and Sudan (2014) showed that local algorithms are weaker than global algorithms for finding large independent sets in sparse random regular graphs. Montanari (2015) showed t…

This paper tackles exact recovery of clusters in a stochastic Ising model on a SBM graph.

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…

Power of network tests degrades when vertices are misaligned.

Suppose that a graph is realized from a stochastic block model where one of the blocks is of interest, but many or all of the vertices' block labels are unobserved. The task is to order the vertices with unobserved block labels into a ``nomination list'' such that, with high probability, vertices from the interesting b…

We consider the problem of community detection or clustering in the labeled Stochastic Block Model (LSBM) with a finite number $K$ of clusters of sizes linearly growing with the global population of items $n$. Every pair of items is labeled independently at random, and label $\ell$ appears with probability $p(i,j,\ell)…

A test for comparing networks using stochastic block models.

The stochastic block model (SBM) is a probabilistic model for community structure in networks. Typically, only the adjacency matrix is used to perform SBM parameter inference. In this paper, we consider circumstances in which nodes have an associated vector of continuous attributes that are also used to learn the node-…

We provide the first information theoretic tight analysis for inference of latent community structure given a sparse graph along with high dimensional node covariates, correlated with the same latent communities. Our work bridges recent theoretical breakthroughs in the detection of latent community structure without no…

The paper analyzes oversmoothing in GNNs and quantifies the effects of mixing and denoising.

New model for community detection with side information improves recovery accuracy.

Enhances community detection in correlated networks with node attributes.

Sharp threshold for exact recovery in non-uniform hypergraph stochastic block model.

GNNs generalize better on homophilic graphs than heterophilic ones.

Adaptive GPR-GNN optimizes node feature and topology learning.

A new SBM for non-negative zero-inflated edge weights in networks.

Unified approach for non-stationary linear bandits with dynamic regret.

Paper solves stochastic contextual linear bandits using linear bandit algorithms.

Suppose that one particular block in a stochastic block model is of interest, but block labels are only observed for a few of the vertices in the network. Utilizing a graph realized from the model and the observed block labels, the vertex nomination task is to order the vertices with unobserved block labels into a rank…

Poly-GNNs achieve similar performance regardless of depth, highlighting graph noise's dominance.

Model clusters networks and their communities simultaneously.

Corrected graph convolutions improve node classification on graphs.

New algorithm achieves strong consistency in binary non-uniform hypergraph classification.

New algorithm reduces regret from sqrt(T) to polylog(T) in stochastic contextual linear bandits.