25 papers · ranked by Valyu relevance
Adithya Gungi, Pradyumna Sepúlveda Delgado, Ines F. Aitsahalia, Marta Blanco-Pozo + 1 more
Flexible, goal-directed behavior depends on learning predictive relationships, yet how reward shapes learned transition structure remains incompletely understood. Here we introduce the Sparse Cognitive Graph, a reinforcement-learning framework in which a continuously updated transition representation is sparsified into…
Yiming Qin, Clément Vignac, Pascal Frossard
Generative graph models struggle to scale due to the need to predict the existence or type of edges between all node pairs. To address the resulting quadratic complexity, existing scalable models often impose restrictive assumptions such as a cluster structure within graphs, thus limiting their applicability. To…
Martin Rektoris, Milan Papež, Václav Šmídl, Tomáš Pevný
Deep generative models (DGMs) for graphs achieve impressively high expressive power thanks to very efficient and scalable neural networks. However, these networks contain non-linearities that prevent analytical computation of many standard probabilistic inference queries, i.e., these DGMs are considered intractable.…
Harsh Shrivastava
There is a considerable body of work in the field of computer science on the topic of sparse graph recovery, particularly with regards to the innovative deep learning approaches that have been recently introduced. Despite this abundance of research, however, these methods are often not applied to the recovery of Gene…
Lionel Zoubritzky, François-Xavier Coudert
We present here an open-source Julia library for the topological identification of crystalline materials, with algorithmic and computational improvements over the previously available software in the field, resulting in a speed increase of one order of magnitude. This new algorithm and implementation can therefore be…
Mary Pitman, David Hahn, Gary Tresadern, David Mobley
Drug discovery is accelerated with computational methods such as alchemical simulations to estimate ligand affinities. In particular, relative binding free energy (RBFE) simulations are beneficial for lead optimization. To use RBFE simulations to compare prospective ligands in silico, researchers first plan the…
Tomokaze Shiratori, Yuichi Takano, Jianchao Bai
Sparse estimation of a Gaussian graphical model (GGM) is an important technique for making relationships between observed variables more interpretable. Various methods have been proposed for sparse GGM estimation, including the graphical lasso that uses the ℓ1 norm regularization term, and other methods that use…
Valentin Lemaire, Youssef Achenchabe, Lucas Ody, Houssem Eddine Souid + 3 more
'Houssem Eddine Souid' 'Gianmarco Aversano' 'Nicolas Posocco' 'Sabri Skhiri'] The topic of synthetic graph generators (SGGs) has recently received much attention due to the wave of the latest breakthroughs in generative modelling. However, many state-ofthe-art SGGs do not scale well with the graph size. Indeed, in the…
Huang XiKun, RUAN Tianyu, Zhang Chihao, Zhang Shihua
—Graph generation is a fundamental task with wide applications in modeling complex systems. Although existing methods align the spectrum or degree profile of the target graph, they often ignore the geometry induced by eigenvectors and the global structure of the graph. In this work, we propose Spectral Geodesic Flow…
Bram Mornie, Didier Colle, Pieter Audenaert, Mario Pickavet + 1 more
'Enrique Hernandez-Lemus'] Testing or benchmarking network algorithms in bioinformatics requires a diverse set of networks with realistic properties. Real networks are often supplemented by randomly generated synthetic ones, but most graph generative models do not take into account the distribution of subgraph…
Maksudul Alam, Kalyan Perumalla
Synthetically generated, large graph networks serve as useful proxies to real-world networks for many graph-based applications. The ability to generate such networks helps overcome several limitations of real-world networks regarding their number, availability, and access. Here, we present the design, implementation…
Andreas Bergmeister, Karolis Martinkus, Nathanaël Perraudin, Roger Wattenhofer
'Roger Wattenhofer'] In the realm of generative models for graphs, extensive research has been conducted. However, most existing methods struggle with large graphs due to the complexity of representing the entire joint distribution across all node pairs and capturing both global and local graph structures…
Evgeny Ivanko, Mikhail Chernoskutov, António M. Lopes
We consider the problem of modeling complex systems where little or nothing is known about the structure of the connections between the elements. In particular, when such systems are to be modeled by graphs, it is unclear what vertex degree distributions these graphs should have. We propose that, instead of attempting…
Tuna, Rodrigo, Soares, Carlos
Graph generation is an important area in network science. Traditional approaches focus on replicating specific properties of real-world graphs, such as small diameters or power-law degree distributions. Recent advancements in deep learning, particularly with Graph Neural Networks, have enabled data-driven methods to…
Liying Chen, Satwik Acharyya, Allison M. May, Aaron M. Udager + 2 more
Advances in spatial transcriptomics (ST) technologies enable systematic molecular characterization of tumor microenvironment, tumor gradients and gene regulatory networks. Cancer progression is known to vary along pathological gradients, yet existing network approaches for gene network inference typically ignore…
Michael W. Reimann, Daniela Egas-Santander
Neuronal connectivity has been characterized at various scales and with respect to various structural aspects. In models of connectivity, it has so far remained difficult to match all of them at once, in particular the higher-order structure appears to be elusive. Here we introduce a new type of graph model that…
Faezeh Faez, Negin Hashemi Dijujin, Mahdieh Soleymani Baghshah, Hamid R. Rabiee + 1 more
'Hamid R. Rabiee' 'Sathishkumar V E'] Deep learning-based graph generation approaches have remarkable capacities for graph data modeling, allowing them to solve a wide range of real-world problems. Making these methods able to consider different conditions during the generation procedure even increases their…
Xiaorui Qi, Yixue Wen, Xiaojie Yuan
Resources Authors: ['Xiaorui Qi' 'Yixue Wen' 'Xiaojie Yuan'] Abstract—Graph generation is one of the most challenging tasks in recent years, and its core is to learn the ground truth distribution hiding in the training data. However, training data may not be available due to security concerns or unaffordable costs…
Femke van Ieperen, Ivan Kryven
We discuss sequential stub matching for directed graphs and show that this process can be used to sample simple digraphs with asymptotically equal probability. The process starts with an empty edge set and repeatedly adds edges to it with a certain state-dependent bias until the desired degree sequence is fulfilled…
Brendan D. McKay, Mehmet Aziz Yirik, Christoph Steinbeck
Chemical structure generators are used in cheminformatics to produce or enumerate virtual molecules based on a set of boundary conditions. The result can then be tested for properties of interest, such as adherence to measured data or for their suitability as drugs. The starting point can be a potentially fuzzy set of…
Drew DeHaas, Ziqing Pan, Xinzhu Wei
Computational analysis of a large number of genomes requires a data structure that can represent the dataset compactly while also enabling efficient operations on variants and samples. Current practice is to store large-scale genetic polymorphism data using tabular data structures and file formats, where rows and…
Sanjar Adilov
Machine learning models for molecular-property prediction typically work with molecular representations in the form of fingerprints, descriptors, or graphs. In case of fingerprints and descriptors, molecular representations usually comprise thousands of features, which causes the curse of dimensionality for many…
Nathan Mancheun Lui, Max D Li, Matthew Ford
Deep generative models for molecular graphs offer a new avenue for property optimization in drug discovery. Optimizing differentiable models that generate molecular graphs is certainly faster, cheaper, and much more accessible than traditional methods of chemical synthesis. Recent advances in generative modeling have…
Siddharth Sabata, Russell Schwartz
Tumor phylogenies — rooted trees encoding clonal ancestry and mutation acquisition — are central to understanding cancer evolution, yet generating realistic phylogenies remains challenging. We investigate whether discrete graph diffusion can learn the structural constraints of tumor phylogenies directly from data.…
David Buterez, Jon Paul Janet, Steven Kiddle, Pietro Liò
We investigate the potential of graph neural networks for transfer learning and improving molecular property prediction on sparse and expensive to acquire high-fidelity data by leveraging low-fidelity measurements as an inexpensive proxy for a targeted property ofinterest. This problem arises in discovery processes…