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.
Study error bounds in evaluating distributional computational graphs.
Probabilistic inference in graphical models is the task of computing marginal and conditional densities of interest from a factorized representation of a joint probability distribution. Inference algorithms such as variable elimination and belief propagation take advantage of constraints embedded in this factorization …
WEGL embeds graphs in a vector space for faster machine learning.
Proposes GFMMD for comparing signals on graphs.
AUC-spec optimizes graph-based SSL for complex label distributions.
Graph embedding aims at learning a vector-based representation of vertices that incorporates the structure of the graph. This representation then enables inference of graph properties. Existing graph embedding techniques, however, do not scale well to large graphs. We therefore propose a framework for parallel computat…
A new method uses matrix sketches for efficient graph clustering in dynamic environments.
We propose a new \cu{class-optimal} algorithm for the distributed computation of Wasserstein Barycenters over networks. Assuming that each node in a graph has a probability distribution, we prove that every node can reach the barycenter of all distributions held in the network by using local interactions compliant with…
We define and study the statistical models in exponential family form whose sufficient statistics are the degree distributions and the bi-degree distributions of undirected labelled simple graphs. Graphs that are constrained by the joint degree distributions are called -graphs in the computer science literature and…
A fast graph embedding method for large graphs.
A distributed algorithm for training graph convolutional networks.
Reinforcement learning (RL) tasks are challenging to implement, execute and test due to algorithmic instability, hyper-parameter sensitivity, and heterogeneous distributed communication patterns. We argue for the separation of logical component composition, backend graph definition, and distributed execution. To this e…
SIGMA model improves graph matching across various applications.
We propose a novel model for generating graphs similar to a given example graph. Unlike standard approaches that compute features of graphs in Euclidean space, our approach obtains features on a surface of a hypersphere. We then utilize a von Mises-Fisher distribution, an exponential family distribution on the surface …
New spectral clustering method for graphs with uneven node degrees.
New distribution simplifies covariance matrix inference.
Federated learning on graphs tackles heterogeneity with efficient parameter estimation.
Tree Mover's Distance measures graph attributes and improves GNN performance.
DistShap parallelizes GNN explanation for large graphs.
HDT improves MCMC on graphs with history-dependent sampling.
Recent methods for generating novel molecules use graph representations of molecules and employ various forms of graph convolutional neural networks for inference. However, training requires solving an expensive graph isomorphism problem, which previous approaches do not address or solve only approximately. In this wor…
Distributed algorithms are often beset by the straggler effect, where the slowest compute nodes in the system dictate the overall running time. Coding-theoretic techniques have been recently proposed to mitigate stragglers via algorithmic redundancy. Prior work in coded computation and gradient coding has mainly focuse…
The reparameterization trick enables optimizing large scale stochastic computation graphs via gradient descent. The essence of the trick is to refactor each stochastic node into a differentiable function of its parameters and a random variable with fixed distribution. After refactoring, the gradients of the loss propag…
Graph representation learning aims to encode all nodes of a graph into low-dimensional vectors that will serve as input of many compute vision tasks. However, most existing algorithms ignore the existence of inherent data distribution and even noises. This may significantly increase the phenomenon of over-fitting and d…
To scale Gaussian processes (GPs) to large data sets we introduce the robust Bayesian Committee Machine (rBCM), a practical and scalable product-of-experts model for large-scale distributed GP regression. Unlike state-of-the-art sparse GP approximations, the rBCM is conceptually simple and does not rely on inducing or …
We present Placeto, a reinforcement learning (RL) approach to efficiently find device placements for distributed neural network training. Unlike prior approaches that only find a device placement for a specific computation graph, Placeto can learn generalizable device placement policies that can be applied to any graph…
We introduce vine computational graphs for efficient ML integration of vine copulas.
New method generates molecular conformations efficiently.
Graph Neural Networks struggle with generalization, especially OOD data; GRATIN solves this with Gaussian Mixture Model-based augmentation.
Most graph kernels are an instance of the class of -Convolution kernels, which measure the similarity of objects by comparing their substructures. Despite their empirical success, most graph kernels use a naive aggregation of the final set of substructures, usually a sum or average, thereby potentially dis…
Benchmark data sets are an indispensable ingredient of the evaluation of graph-based machine learning methods. We release a new data set, compiled from International Planning Competitions (IPC), for benchmarking graph classification, regression, and related tasks. Apart from the graph construction (based on AI planning…
COPT optimizes graph distances via simultaneous optimal transport.
In this paper, we propose Continuous Graph Flow, a generative continuous flow based method that aims to model complex distributions of graph-structured data. Once learned, the model can be applied to an arbitrary graph, defining a probability density over the random variables represented by the graph. It is formulated …
We study the statistical behavior of reasoning probes in a stylized model of iterative computation inspired by neural algorithmic reasoning. The underlying computation is given by a looped Boolean circuit whose graph is a perfect -ary tree (), with outputs recursively fed back as inputs across computation ro…
SA-GFN corrects biases in GFlowNets due to graph symmetries.
We present a model for random simple graphs with a degree distribution that obeys a power law (i.e., is heavy-tailed). To attain this behavior, the edge probabilities in the graph are constructed from Bertoin-Fujita-Roynette-Yor (BFRY) random variables, which have been recently utilized in Bayesian statistics for the c…
tf_geometric simplifies graph deep learning in TensorFlow.
We propose a novel framework for graph mean computation.
We study recursive-cube-of-rings (RCR), a class of scalable graphs that can potentially provide rich inter-connection network topology for the emerging distributed and parallel computing infrastructure. Through rigorous proof and validating examples, we have corrected previous misunderstandings on the topological prope…
This work considers the problem of computing distances between structured objects such as undirected graphs, seen as probability distributions in a specific metric space. We consider a new transportation distance (i.e. that minimizes a total cost of transporting probability masses) that unveils the geometric nature of …
Online CPD for weighted and directed graphs using RDPG model.
We present novel graph kernels for graphs with node and edge labels that have ordered neighborhoods, i.e. when neighbor nodes follow an order. Graphs with ordered neighborhoods are a natural data representation for evolving graphs where edges are created over time, which induces an order. Combining convolutional subgra…
Neighbor Mixture Model captures node correlations in graphs.
This work proposes a method to learn graph structure for multivariate time series forecasting.
New bounds improve graph node classification using optimal transport.
New AI model improves grid planning efficiency and reliability.
Graph neural networks improve combinatorial optimization by leveraging inductive bias.
Meta-learning model predicts intervention effects from uncertain causal graphs.