arXiv research

GraphITE estimates individual effects of graph-structured treatments.

GraphTEE estimates treatment effects on graph-structured targets, mitigating bias.

Study tackles causal effects of close contact on MRSA infections from entangled treatment data.

New method estimates causal effects without knowing graph structure.

This work addresses causal inference challenges in networked interference and proposes GNN-based estimators for individual treatment effects.

A Bayesian treatment of latent directed graph structure for non-iid data is provided where each child datum is sampled with a directed conditional dependence on a single unknown parent datum. The latent graph structure is assumed to lie in the family of directed out-tree graphs which leads to efficient Bayesian inferen…

Eigen-GNN enhances GNNs by preserving graph structures.

New research limits what GNNs can compute and generalizes their performance.

Auto-encoders have emerged as a successful framework for unsupervised learning. However, conventional auto-encoders are incapable of utilizing explicit relations in structured data. To take advantage of relations in graph-structured data, several graph auto-encoders have recently been proposed, but they neglect to reco…

Investigates how neural network graph structure impacts predictive performance.

This paper improves GNN robustness by aligning feature and adjacency matrix learning.

Online learning algorithms update models via one sample per iteration, thus efficient to process large-scale datasets and useful to detect malicious events for social benefits, such as disease outbreak and traffic congestion on the fly. However, existing algorithms for graph-structured models focused on the offline set…

Two new methods improve graph embedding without needing a complete graph structure.

In this paper, we propose an end-to-end graph learning framework, namely Deep Iterative and Adaptive Learning for Graph Neural Networks (DIAL-GNN), for jointly learning the graph structure and graph embeddings simultaneously. We first cast the graph structure learning problem as a similarity metric learning problem and…

We present GraphTSNE, a novel visualization technique for graph-structured data based on t-SNE. The growing interest in graph-structured data increases the importance of gaining human insight into such datasets by means of visualization. Among the most popular visualization techniques, classical t-SNE is not suitable o…

Graph Convolutional Neural Networks (Graph CNNs) are generalizations of classical CNNs to handle graph data such as molecular data, point could and social networks. Current filters in graph CNNs are built for fixed and shared graph structure. However, for most real data, the graph structures varies in both size and con…

IDGL learns better graph structure and embeddings iteratively.

Processes such as disease propagation and information diffusion often spread over some latent network structure which must be learned from observation. Given a set of unlabeled training examples representing occurrences of an event type of interest (e.g., a disease outbreak), our goal is to learn a graph structure that…

Estimates manifold dimension using local graph structure.

GraphSTONE uses topic models to capture graph structures, improving GCN performance.

Method learns graph structure for multi-task learning, revealing interpretable relationships.

New algorithms for causal bandits without knowing the graph structure.

Generating graph structures is a challenging problem due to the diverse representations and complex dependencies among nodes. In this paper, we introduce Graph Variational Recurrent Neural Network (GraphVRNN), a probabilistic autoregressive model for graph generation. Through modeling the latent variables of graph data…

New algorithm reduces regret in combinatorial causal bandits without graph structure.

This work proposes a method to learn graph structure for multivariate time series forecasting.

Graph Information Bottleneck (GIB) optimizes graph representations for robustness against adversarial attacks.

Proposes HypCSE for enhanced hierarchical clustering.

node2coords learns interpretable graph node representations robust to graph perturbations.

TrialGraph uses graph machine learning to improve clinical trial design and predict side effects.

GISST interprets GNNs by combining attention and sparsity for graph structure and node feature importance.

Discovering imaging biomarkers for autism spectrum disorder (ASD) is critical to help explain ASD and predict or monitor treatment outcomes. Toward this end, deep learning classifiers have recently been used for identifying ASD from functional magnetic resonance imaging (fMRI) with higher accuracy than traditional lear…

SANS uses graph structure to find meaningful negatives for entity and relation embeddings.

New method learns graph structure and uncertainty from data.

Sparsity-constrained optimization is an important and challenging problem that has wide applicability in data mining, machine learning, and statistics. In this paper, we focus on sparsity-constrained optimization in cases where the cost function is a general nonlinear function and, in particular, the sparsity constrain…

This paper introduces a generalization of Convolutional Neural Networks (CNNs) from low-dimensional grid data, such as images, to graph-structured data. We propose a novel spatial convolution utilizing a random walk to uncover the relations within the input, analogous to the way the standard convolution uses the spatia…

Neural network learns causal graph structure from data.

Based on \cite{DH94}, we introduce a bijective correspondence between first order differential calculi and the graph structure of the symmetric lattice that allows one to encode completely the interconnection structure of the graph in the exterior derivative. As a result, we obtain the Grassmannian character of the lat…

Study 2D spaces with curvature, finding a graph structure.

We study epidemic forecasting on real-world health data by a graph-structured recurrent neural network (GSRNN). We achieve state-of-the-art forecasting accuracy on the benchmark CDC dataset. To improve model efficiency, we sparsify the network weights via transformed-$\ell_1$ penalty and maintain prediction accuracy at…

Paper introduces HGSL for heterogeneous graphs, improving edge type and weight recovery.

As a new approach to train generative models, \emph{generative adversarial networks} (GANs) have achieved considerable success in image generation. This framework has also recently been applied to data with graph structures. We propose labeled-graph generative adversarial networks (LGGAN) to train deep generative model…

Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work on Graph Neural Networks (Scarselli et al., 2009), which we modif…

This work analyzes SGGMs, offering convergence insights and practical design tips.

A compact 4-dimensional manifold is a non-singular graph-manifold if it can be obtained by the glueing T^2-bundles over compact surfaces (with boundary) of negative Euler characteristics. If none of glueing diffeomorphisms respect the bundle structures, the graph-structure is called reduced. We prove that any homotopy …

M3E2 neural network estimates multiple treatment effects.

BAM model learns graph structure from data with robustness across linear and non-linear dependencies.

Global graph structure improves GNN performance.

Stochastic optimization algorithms update models with cheap per-iteration costs sequentially, which makes them amenable for large-scale data analysis. Such algorithms have been widely studied for structured sparse models where the sparsity information is very specific, e.g., convex sparsity-inducing norms or $\ell^0$-n…