A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Bayesian Cox model identifies biomarkers from multi-omics data.
Paper learns hypergraph structures from signals with smoothness priors.
We propose a Bayesian approximate inference method for learning the dependence structure of a Gaussian graphical model. Using pseudo-likelihood, we derive an analytical expression to approximate the marginal likelihood for an arbitrary graph structure without invoking any assumptions about decomposability. The majority…
Graphical model learning and inference are often performed using Bayesian techniques. In particular, learning is usually performed in two separate steps. First, the graph structure is learned from the data; then the parameters of the model are estimated conditional on that graph structure. While the probability distrib…
We propose an extension of Convolutional Neural Networks (CNNs) to graph-structured data, including strided convolutions and data augmentation on graphs. Our method matches the accuracy of state-of-the-art CNNs when applied on images, without any prior about their 2D regular structure. On fMRI data, we obtain a signifi…
New algorithm reduces regret in combinatorial causal bandits without graph structure.
Genome-wide association studies (GWA studies or GWAS) investigate the relationships between genetic variants such as single-nucleotide polymorphisms (SNPs) and individual traits. Recently, incorporating biological priors together with machine learning methods in GWA studies has attracted increasing attention. However, …
Proposes a model combining graph networks and variational Bayes for graph data.
Bayesian neural networks learn graph structure with interpretable parameters.
Algorithm estimates graph structure with prior information and Langevin diffusion.
Detects graph topology changes from noisy signals using prior spectral information.
MetaTNE tackles few-shot novel labels in graphs, improving node classification.
BetaExplainer improves GNN interpretability by masking unimportant edges.
Textual network embedding aims to learn low-dimensional representations of text-annotated nodes in a graph. Prior work in this area has typically focused on fixed graph structures; however, real-world networks are often dynamic. We address this challenge with a novel end-to-end node-embedding model, called Dynamic Embe…
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over thei…
The mixed membership stochastic blockmodel (MMSB) is a popular framework for community detection and network generation. It learns a low-rank mixed membership representation for each node across communities by exploiting the underlying graph structure. MMSB assumes that the membership distributions of the nodes are ind…
A new model learns graph structures from data.
Traditional approaches to Bayes net structure learning typically assume little regularity in graph structure other than sparseness. However, in many cases, we expect more systematicity: variables in real-world systems often group into classes that predict the kinds of probabilistic dependencies they participate in. Her…
Paper introduces a new metric to select optimal Graph Shift Operator for GNNs.
Bayesian method learns graph structures from Gaussian data efficiently.
We provide a theoretical analysis of the representation learning problem aimed at learning the latent variables (design matrix) of observations with the knowledge of the coefficient matrix . The design matrix is learned under the assumption that the latent variables are smooth with respect to a (known) t…
The regression of multiple inter-connected sequence data is a problem in various disciplines. Formally, we name the regression problem of multiple inter-connected data entities as the "dynamic network regression" in this paper. Within the problem of stock forecasting or traffic speed prediction, we need to consider bot…
Eigen-GNN enhances GNNs by preserving graph structures.
The main contribution of this article is a new prior distribution over directed acyclic graphs, which gives larger weight to sparse graphs. This distribution is intended for structured Bayesian networks, where the structure is given by an ordered block model. That is, the nodes of the graph are objects which fall into …
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.
Graph transformers outperform graph convolutions by preserving community information.
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…
Study on stability of GCNNs under graph perturbations.
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…
We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutiona…
Identifies root causes of outliers in unknown cyclic graphs.
Improved graph neural network bounds using graph diffusion matrix.
Estimates manifold dimension using local graph structure.
GraphSTONE uses topic models to capture graph structures, improving GCN performance.
Problems in machine learning (ML) can involve noisy input data, and ML classification methods have reached limiting accuracies when based on standard ML data sets consisting of feature vectors and their classes. Greater accuracy will require incorporation of prior structural information on data into learning. We study …
Bayesian methods estimate regression functions on submanifolds using graph Laplacian eigenbasis.
GraphITE estimates individual effects of graph-structured treatments.
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…
T-LoHo model detects structured sparsity and smoothness on graph data.