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.
Survey on learning with graph-dependent data, deriving new generalization bounds.
New framework relaxes independence assumption for graph-mixing dependencies.
BeGIN benchmarks GNNs for instance-dependent label noise in graphs.
Improved GNN handles long-range dependencies in multi-relational graphs.
A crucial assumption in most statistical learning theory is that samples are independently and identically distributed (i.i.d.). However, for many real applications, the i.i.d. assumption does not hold. We consider learning problems in which examples are dependent and their dependency relation is characterized by a gra…
Novel graph neural network combines random walks with local message passing.
Spatial and time-dependent data is of interest in many applications. This task is difficult due to its complex spatial dependency, long-range temporal dependency, data non-stationarity, and data heterogeneity. To address these challenges, we propose Forecaster, a graph Transformer architecture. Specifically, we start b…
IGNN captures long-range graph dependencies using fixed-point equations.
Graph node embedding aims at learning a vector representation for all nodes given a graph. It is a central problem in many machine learning tasks (e.g., node classification, recommendation, community detection). The key problem in graph node embedding lies in how to define the dependence to neighbors. Existing approach…
Proposes a novel graph learning framework for robust graph topology learning from graph signals.
BAM model learns graph structure from data with robustness across linear and non-linear dependencies.
Alt-GNNs improve travel mode choice modeling by integrating graph neural networks with GEV models.
Proposes a GNN framework for multivariate time series forecasting.
Paper improves risk bound for MTL with graph-dependent data.
The covariance graph (aka bi-directed graph) of a probability distribution is the undirected graph where two nodes are adjacent iff their corresponding random variables are marginally dependent in . In this paper, we present a graphical criterion for reading dependencies from , under the assumption that $…
Unified framework for clustering and learning causal graphs across subjects.
Graph convolutional networks adapt the architecture of convolutional neural networks to learn rich representations of data supported on arbitrary graphs by replacing the convolution operations of convolutional neural networks with graph-dependent linear operations. However, these graph-dependent linear operations are d…
DynDepNet learns dynamic brain graphs from fMRI data for better prediction performance.
Boost GNNs for node classification by incorporating label dependencies.
Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph…
Graph attention network improves MLTC by capturing label dependencies.
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex temporal dependencies that imply variable-length semantic flows and their composi…
DA-GNN improves robustness of GNNs by modeling noise dependencies.
Framework for universal graph function approximators outperforms existing methods.
We propose graph-dependent implicit regularisation strategies for distributed stochastic subgradient descent (Distributed SGD) for convex problems in multi-agent learning. Under the standard assumptions of convexity, Lipschitz continuity, and smoothness, we establish statistical learning rates that retain, up to logari…
Paper models graph edge dependencies using latent variables for community detection.
Paper proposes methods to improve graph domain adaptation by decorrelating node features.
Gaussian graphical models are widely used to represent conditional dependence among random variables. In this paper, we propose a novel estimator for data arising from a group of Gaussian graphical models that are themselves dependent. A motivating example is that of modeling gene expression collected on multiple tissu…
We study the scenario of graph-based clustering algorithms such as spectral clustering. Given a set of data points, one first has to construct a graph on the data points and then apply a graph clustering algorithm to find a suitable partition of the graph. Our main question is if and how the construction of the graph (…
Paper estimates differences in conditional independence graphs from time-dependent data.
Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structur…
Semi-implicit graph variational auto-encoder (SIG-VAE) is proposed to expand the flexibility of variational graph auto-encoders (VGAE) to model graph data. SIG-VAE employs a hierarchical variational framework to enable neighboring node sharing for better generative modeling of graph dependency structure, together with …
Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional neural networks and gated recurrent neural networks. Recently, graph neural networks have been successfully applied to graph structured data such as point cloud and molecular data. These networks oft…
Low-rank tensor decomposition and completion have attracted significant interest from academia given the ubiquity of tensor data. However, the low-rank structure is a global property, which will not be fulfilled when the data presents complex and weak dependencies given specific graph structures. One particular applica…
Improves causal graph learning on dependent binary data.
Chordal graphs can be used to encode dependency models that are representable by both directed acyclic and undirected graphs. This paper discusses a very simple and efficient algorithm to learn the chordal structure of a probabilistic model from data. The algorithm is a greedy hill-climbing search algorithm that uses t…
Estimates marginal independence structure of Bayesian networks from data.
We consider the flow on complete non-compact graphs. We prove that a complete graph evolves by the curvature up to some time depending on the radius of a sphere enclosed by the initial graph.
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency. However, most of sequential data, as seen with videos, have complex dependency structures that imply variable-length semantic flows and their composi…
This paper tackles unknown causal graphs and soft interventions, establishing regret bounds and an efficient algorithm.
Graph matching in noisy environments with Markovian errors.
Paper explores exact recovery of communities in weighted graphs using Gaussian and exponential distributions.
Combines PCA and message passing for better graph node embeddings.
The paper gives bounds for how long it takes for gossip protocols to spread information in networks.
This study applies EMD to MSCI World index and converts IMFs into graphs for GNN modeling.
Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all nodes and edges belong to the same types, making them infeasible to represent heterogeneous structures. In this paper, we present the Hetero…
The edge structure of the graph defining an undirected graphical model describes precisely the structure of dependence between the variables in the graph. In many applications, the dependence structure is unknown and it is desirable to learn it from data, often because it is a preliminary step to be able to ascertain c…
We present graph wavelet neural network (GWNN), a novel graph convolutional neural network (CNN), leveraging graph wavelet transform to address the shortcomings of previous spectral graph CNN methods that depend on graph Fourier transform. Different from graph Fourier transform, graph wavelet transform can be obtained …