arXiv research

ARGEW improves node embeddings for weighted homophilous graphs by emphasizing strong edge weights.

New framework for dense weighted networks with community-specific patterns.

New method estimates Nishimori temperature for node classification in weighted graphs.

GSAN learns adaptive node representations using geometric scattering and attention.

This paper is concerned with the sparsification of the input-hidden weights of ELM (Extreme Learning Machine). For ordinary feedforward neural networks, the sparsification is usually done by introducing certain regularization technique into the learning process of the network. But this strategy can not be applied for E…

The paper connects DNN generalization to node SNR using information theory.

A new model clusters network nodes based on relative edge weights.

The paper proves ML estimators are strongly consistent for identifying edge weights in BAR models.

In standard graph clustering/community detection, one is interested in partitioning the graph into more densely connected subsets of nodes. In contrast, the "search" problem of this paper aims to only find the nodes in a "single" such community, the target, out of the many communities that may exist. To do so , we are …

BGNN improves GNN by modeling interactions between neighbor nodes.

Unified model combines GCN and LPA for better node classification.

We examine the effect of the Group Lasso (gLasso) regularizer in selecting the salient nodes of Deep Neural Network (DNN) hidden layers by applying a DNN-HMM hybrid speech recognizer to TED Talks speech data. We test two types of gLasso regularization, one for outgoing weight vectors and another for incoming weight vec…

We present a novel spectral embedding of graphs that incorporates weights assigned to the nodes, quantifying their relative importance. This spectral embedding is based on the first eigenvectors of some properly normalized version of the Laplacian. We prove that these eigenvectors correspond to the configurations of lo…

When choosing a suitable technique for regression and classification with multivariate predictor variables, one is often faced with a tradeoff between interpretability and high predictive accuracy. To give a classical example, classification and regression trees are easy to understand and interpret. Tree ensembles like…

Neural networks with random hidden nodes have gained increasing interest from researchers and practical applications. This is due to their unique features such as very fast training and universal approximation property. In these networks the weights and biases of hidden nodes determining the nonlinear feature mapping a…

Paper proposes efficient weight updates for edge nodes with minimal communication.

A new type of quadrature is developed. The Gaussian quadrature, for a given measure, finds optimal values of a function's argument (nodes) and the corresponding weights. In contrast, the Lebesgue quadrature developed in this paper, finds optimal values of function (value-nodes) and the corresponding weights. The Gaussi…

New method detects overlapping communities in weighted graphs without pure nodes assumption.

We analyze the dynamics of training deep ReLU networks and their implications on generalization capability. Using a teacher-student setting, we discovered a novel relationship between the gradient received by hidden student nodes and the activations of teacher nodes for deep ReLU networks. With this relationship and th…

Local graph clustering improves with noisy labels, enhancing accuracy and performance.

Stochastic gradient descent (SGD) is a popular stochastic optimization method in machine learning. Traditional parallel SGD algorithms, e.g., SimuParallel SGD, often require all nodes to have the same performance or to consume equal quantities of data. However, these requirements are difficult to satisfy when the paral…

RR-GCN uses random transformations instead of learned weights for node embeddings.

Efficient algorithm removes redundant nodes and obsolete samples in machine learning.

SWAG uses graph convolutions to recommend products.

We investigate the problem of sequentially predicting the binary labels on the nodes of an arbitrary weighted graph. We show that, under a suitable parametrization of the problem, the optimal number of prediction mistakes can be characterized (up to logarithmic factors) by the cutsize of a random spanning tree of the g…

A UCB algorithm reduces regret in cooperative multi-agent graph bandits.

Improved covariate shift handling with node-based Bayesian neural networks.

Manipulation is an important issue for both developed and emerging stock markets. For the study of manipulation, it is critical to analyze investor behavior in the stock market. In this paper, an analysis of the full transaction records of over a hundred stocks in a one-year period is conducted. For each stock, a tradi…

Enhances graph neural networks by considering feature similarities in node aggregation.

New model for detecting communities in weighted bipartite networks.

Graph attention improves node classification by distinguishing important edges.

Learning representations of nodes in a low dimensional space is a crucial task with many interesting applications in network analysis, including link prediction and node classification. Two popular approaches for this problem include matrix factorization and random walk-based models. In this paper, we aim to bring toge…

Multi-label network classification is a well-known task that is being used in a wide variety of web-based and non-web-based domains. It can be formalized as a multi-relational learning task for predicting nodes labels based on their relations within the network. In sparse networks, this prediction task can be very chal…

Study of deep neural networks with dependent weights leading to new model limits and properties.

Researchers use information geometry to analyze and improve DRWs for node classification.

Improves GCNNs with node transition probabilities and DropNode regularization.

Learning node embeddings that capture a node's position within the broader graph structure is crucial for many prediction tasks on graphs. However, existing Graph Neural Network (GNN) architectures have limited power in capturing the position/location of a given node with respect to all other nodes of the graph. Here w…

Active search (AS) on graphs focuses on collecting certain labeled nodes (targets) given global knowledge of the network topology and its edge weights under a query budget. However, in most networks, nodes, topology and edge weights are all initially unknown. We introduce selective harvesting, a variant of AS where the…

Adaptive GPR-GNN optimizes node feature and topology learning.

New algorithm improves hypergraph clustering for unbalanced communities.

Kernel interpolation improved with continuous volume sampling.

Spectral clustering is a celebrated algorithm that partitions objects based on pairwise similarity information. While this approach has been successfully applied to a variety of domains, it comes with limitations. The reason is that there are many other applications in which only \emph{multi}-way similarity measures ar…

Bayesian GCNN uses node copying for graph inference.

This work identifies and mitigates topological bias in HGNNs using meta-weighting and debiasing.

Efficiently clusters nodes in Gaussian graphical models from data.

A new GCN model learns higher-order neighbors without explicit adjacency matrix computation.

Proposes a new model for clustering multiplex networks with compositional data.

Two new ridge solutions improve BLS on added nodes, achieving better accuracy.