24 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…
Haoran Sun, Likai Liang, Zhongrui Wang
Graph Neural Networks (GNNs) have become essential for analyzing graph-structured data, yet their deployment on resource-constrained edge devices is severely limited by high computational complexity and irregular memory access patterns. Here, we introduce DynamiGraph, a specialized FPGA-based overlay accelerator…
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.…
Sevvandi Kandanaarachchi, Cheng Soon Ong
Social networks have a small number of large hubs, and a large number of small dense communities. We propose a generative model that captures both hub and dense structures. Based on recent results about graphons on line graphs, our model is a graphon mixture, enabling us to generate sequences of graphs where each graph…
Anton Tsitsulin, Bryan Perozzi
In this work, we introduce the Graph Lottery Ticket (GLT) Hypothesis – that there is an extremely sparse backbone for every graph, and that graph learning algorithms attain comparable performance when trained on that subgraph as on the full graph. We identify and systematically study 8 key metrics of interest that…
Sevvandi Kandanaarachchi, Cheng Soon Ong
We consider the problem of estimating graph limits, known as graphons, from observations of sequences of sparse finite graphs. In this paper we show a simple method that can shed light on a subset of sparse graphs. The method involves mapping the original graphs to their line graphs. We show that graphs satisfying a…
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…
Yuhan Chen, Haojie Ye, Sanketh Vedula, Alex Bronstein + 3 more
Graphs are ubiquitous because of their great expressiveness and flexibility. Graphs can be used to represent complex relationships between individuals (vertices in the graph) by making connections (edges in the graph). Graphs are widely used to represent data in various application domains, e.g. social networks [30]…
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…
Heli Sun, Xuechun Liu, Miaomiao Sun, Ruichen Cao + 4 more
The Sparse Subgraph Finding (SGF) problem addresses the challenge of identifying sub-graphs with weak social interactions and sparse connections within a graph, which can be effectively modeled as discovering sparse subsystems in intelligent sensor networks. Traditional methods often rely on manually designed…
Runze Chen, Kaibiao Lin, Binsheng Hong, Shandan Zhang + 1 more
In previous research, the prevailing assumption was that Graph Neural Networks (GNNs) precisely depicted the interconnections among nodes within the graph's architecture. Nonetheless, real-world graph datasets are often rife with noise, elements that can disseminate through the network and ultimately affect the outcome…
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…
Ryan Wickman, Xiaofei Zhang, Weizi Li
—The interconnectedness and interdependence of modern graphs are growing ever more complex, causing enormous resources for processing, storage, communication, and decision-making of these graphs. In this work, we focus on the task graph sparsification: an edge-reduced graph of a similar structure to the original graph…
Zehan Li, Xuemeng Zhai, Hangyu Hu, Jiandong Liang + 2 more
Graph neural networks (GNNs) have achieved great success in graph classification, with graph pooling methods being widely adopted for related tasks. Existing approaches typically rely on node ranking or clustering to coarsen graphs, but often fail to effectively leverage global structural information, leading to loss…
Heewon Park, Satoru Miyano, Maria Ines Fariello Rico
Uncovering acquired drug resistance mechanisms has garnered considerable attention as drug resistance leads to treatment failure and death in patients with cancer. Although several bioinformatics studies developed various computational methodologies to uncover the drug resistance mechanisms in cancer chemotherapy, most…
Laura Eslava, Sayle Sigarreta Ricardo, Arno Siri-Jégousse
We prove that the generalized Randić index over graphs following the Erdos-Rényi model, for both the sparse and dense regimes, is concentrated around its mean when the number of vertices tends to infinity.
Satwik Acharyya, Jian Kang, Veerabhadran Baladandayuthapani
Modern spatial transcriptomic profiling techniques facilitate spatially resolved, high-dimensional assessment of cellular gene transcription across the tumor domain. The characterization of spatially varying gene networks enables the discovery of heterogeneous regulatory patterns and biological mechanisms underlying…
Jianshu Zhao, Jean Pierre Both, Rob Knight
Graph/network representation learning (or graph/network embedding) is a widely used machine learning technique in industry recommending systems and has recently been applied in computational biology. Popular network representation learning algorithms include random walk and matrix factorization methods, but they do not…
Wilfried Agbeto, Camille Coti, Vladimir Reinharz
Subgraph isomorphism is a fundamental combinatorial problem that involves finding one or more occurrences of a pattern graph within a target graph. It arises in a wide range of application domains, including biology, chemistry, social network analysis, and pattern recognition. Although subgraph isomorphism is…
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…
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…
Naomi Auer, Lars Chen, Jakob Stubenrauch, Benjamin Lindner + 1 more
The brain can efficiently learn and form memories based on limited exposure to stimuli. One key factor believed to support this ability is sparse coding, which can reduce overlap between representations and minimize interference. It is well known that increased sparseness can enhance memory capacity, yet its impact on…
Trevor Gokey, David L. Mobley
Molecular mechanics force fields require a chemical perception model to assign parameters to molecules. A recent advancement in force fields is the use of the SMARTS substructure query language as the perception model. Although it is straightforward to write SMARTS patterns to define new force field parameters, it is…
Authors not listed
Genetic Algorithms are a powerful method to solve optimization problems with complex cost functions over vast search spaces that rely in particular on recombining parts of previous solutions. Crossover operators play a crucial role in this context. Here, we describe a large class of these operators designed for…