URN neural network dynamically generates various neural structures during training.
problem Creating neural networks with flexible, dynamic structures during training.
method Introduced Unstructured Recursive Network (URN) and used gradient descent on a single loss function.
result Different neural structures can emerge from a single URN during training.
A new method learns deep neural network structures from input distributions.
problem Learning the structure of deep neural networks.
method Bayesian network structure learning applied to neural networks.
result Deep layers of common networks can be replaced by smaller learned structures without loss of accuracy.
Capsule Networks classify RAS protein structures with GPU acceleration.
problem Classifying RAS protein structures accurately and interpretably.
method Implemented Capsule Network architecture trained on 2D and 3D structural encodings.
result Capsule Network outperforms traditional CNNs in accuracy and interpretability.
The structure of complex networks has been of interest in many scientific and engineering disciplines over the decades. A number of studies in the field have been focused on finding the common properties among different kinds of networks such as heavy-tail degree distribution, small-worldness and modular structure and …
Transform classical network structures to graph CNN for better graph recognition.
problem Transforming classical network structures to graph CNN for better graph recognition.
method Review and introduce ResNet, Inception, and DenseNet into graph CNN, constructing G_ResNet, G_Inception, G_DenseNet.
result Demonstrated how different network structures work on graph CNN in the graph recognition task.
Paper introduces a core-periphery model for identifying informative network structures.
problem Noise and bias in non-informative periphery structures obscure the informative core in complex networks.
method Spectral algorithms for core identification as a preprocessing step for network analysis.
result The proposed method outperforms traditional core-periphery methods in various downstream tasks.
This paper improves deep learning by integrating Bayesian inference into network structure learning.
problem Bayesian inference in high-dimensional, over-parameterized neural networks.
method Developed an efficient stochastic variational inference approach to learn both network structure and weights.
result Empirically, the method exhibits competitive predictive performance and preserves Bayesian benefits.
Deep neural networks (DNNs) are powerful machine learning models and have succeeded in various artificial intelligence tasks. Although various architectures and modules for the DNNs have been proposed, selecting and designing the appropriate network structure for a target problem is a challenging task. In this paper, w…
New method amplifies hidden structure in complex networks.
problem Difficulty in uncovering hidden structure in complex networks.
method Iterative weakening of dominant structure through randomization.
result Theoretical support for the effectiveness of structure amplification.
Tackles network structure inference from time series data using GNN.
problem Inferring network structure from incomplete or no information.
method Gumbel Graph Network (GGN) model for network reconstruction and completion.
result GGN can reconstruct up to 100% network structure and infer missing parts with up to 90% accuracy.
Study compares investor networks and cellphone communication networks to analyze layer structures.
problem Comparing investor networks and cellphone communication networks to understand information diffusion.
method Used clustering algorithms to detect layer structures in ego networks of both networks.
result Nodes in both networks can be divided into two groups with specific layer structures.
MDNE embeds network structures and attributes for better analysis.
problem Preserving both structural and attribute features in network embedding.
method Multimodal Deep Network Embedding (MDNE) using deep model with multiple layers of non-linear functions.
result MDNE outperforms baselines on various tasks with real-world datasets.
Improved protein structure classification using weighted graphlets and deep neural networks.
problem Protein structure classification for function prediction.
method Developed a weighted network and graphlet-based measure, combined with a deep neural network.
result Significantly improved performance on 36 real datasets compared to existing methods.
Neural networks learn symbolic structure to perform compositional tasks.
problem How neural networks perform well on compositional tasks without explicit representations.
method ROLE analysis to uncover symbolic structure in recurrent neural networks.
result Neural networks converge to solutions that implicitly represent symbolic structure.
AN2VEC disentangles feature and structural information in social networks.
problem Difficulty in separating feature and structural information in social networks.
method Graph Convolutional Networks (GCN) Variational Autoencoder for disentangled node embeddings.
result AN2VEC captures joint information of structure and features better than unshared information.
Framework learns structural and functional brain network embeddings while preserving their properties.
problem Joint learning of structural and functional brain networks while preserving their intrinsic properties.
method Siamese community-preserving graph convolutional network (SCP-GCN) that learns from both structural and functional connectivity.
result Superior performance in neurological disorder analysis compared to existing methods.
A gradient-based method learns the structure of TAN for Bayesian network classifiers.
problem Learning the structure of Bayesian networks is difficult.
method A distribution over graph structures learned via gradient-based optimization.
result Consistently outperforms random and Chow-Liu TAN structures.
A new probabilistic model detects communities in networks using both structure and node features.
problem Detecting communities in networks with node features for more accurate results.
method Generative probabilistic model considering network structure and node features.
result The model accurately detects communities and determines feature strength.
In recent years, there is a growing interest in learning Bayesian networks with continuous variables. Learning the structure of such networks is a computationally expensive procedure, which limits most applications to parameter learning. This problem is even more acute when learning networks with hidden variables. We p…
Small intrinsic scale reveals network structure.
problem Understanding the scale at which network identity is revealed.
method Defined intrinsic scale as distinguishability of subgraphs in random walks.
result Intrinsic scale is surprisingly small (7-20 vertices) across various networks.
Paper shows neural network derivatives have outer product structure.
problem Understanding and utilizing higher-order information in neural networks.
method Analyzes feedforward, recurrent, and convolutional neural networks to identify derivative structure.
result Derivatives of feedforward and recurrent networks have an outer product structure, while convolutional networks do not.
Investigates how neural network graph structure impacts predictive performance.
problem Lack of understanding between neural network graph structure and predictive performance.
method Developed relational graph representation to analyze neural networks, identifying a 'sweet spot' for improved performance.
result Identified a 'sweet spot' in relational graph structure that significantly improves neural network predictive performance.
A new method scores contextual Markov networks without assuming chordality.
problem Learning structure in contextual Markov networks is hard due to many possible structures.
method Marginal pseudo-likelihood as a consistent structure estimator.
result Marginal pseudo-likelihood yields a consistent structure estimator.
StrNN uses neural network structures to learn conditional independencies.
problem Learning conditional independencies in neural networks.
method Designing masks for neural networks based on binary matrix factorization.
result StrNN improves density estimation and causal inference.
Structured pruning yields inferior results compared to training from scratch.
problem Efficacy of structured pruning in neural network compression.
method Alternating pruning and fine-tuning of large networks, comparing to training from scratch.
result Reduced networks trained from scratch outperform pruned networks.
Graph neural networks struggle with structural noise.
problem Robustness of graph neural networks to structural noise.
method Controlled experiments with a representative GNN model.
result Graph neural networks are not robust to structural noise.
Symmetric CNNs improve sequential recommendation and protein structure prediction.
problem Improving prediction accuracy in sequential recommendation and protein structure inference.
method Developed a CNN architecture that preserves symmetry in convolutional layers, using parameterized convolutional kernels.
result Symmetric structured CNNs achieve better performance with fewer parameters.
New model for multiplex networks learns shared structure.
problem Complex network structures not well modeled by existing methods.
method Latent space model for multiplex networks with shared structure.
result Model recovers latent positions with sufficient separation.
Overview of structured data representation methods.
problem Structured data lacks vectorial form, complicating machine learning.
method Various approaches including kernel, distance, neural networks, and graph convolutional networks.
result New approaches like metric learning and recurrent decoder networks have emerged.
Braid theory optimizes neural network structures.
problem Optimizing the architecture of neural networks.
method Using braid theory to describe and construct neural network structures.
result Braid-based networks outperform other architectures in classification tasks.
We examine how the structure of the world trade network has been shaped by globalization and recessions over the last 40 years. We show that by treating the world trade network as an evolving system, theory predicts the trade network is more sensitive to evolutionary shocks and recovers more slowly from them now than i…
We present a novel condition, which we term the net- work nullspace property, which ensures accurate recovery of graph signals representing massive network-structured datasets from few signal values. The network nullspace property couples the cluster structure of the underlying network-structure with the geometry of th…
CoNN uses cooperative neural networks to leverage prior independence structure for improved text classification.
problem Improving text classification accuracy by exploiting prior independence structure.
method CoNN employs a set of cooperatively trained neural networks to capture latent representations based on prior independence structure.
result Demonstrated a 23% reduction in error on the MultiSent dataset compared to state-of-the-art methods.
Algorithm discovers dynamic cell structures for better neural network performance.
problem Finding optimal neural network architectures for diverse data samples and time steps.
method Combines recurrent and recursive neural networks to dynamically search for customized cell structures.
result Achieves better prediction accuracy compared to existing models.
DiBS learns Bayesian network structure and parameters efficiently.
problem Bayesian structure learning with uncertainty reasoning.
method Differentiable framework for continuous latent graph representation, agnostic to local conditional distributions.
result Significantly outperforms related approaches in posterior inference.
Generative Adversarial Networks create synthetic data for structural damage detection.
problem Data scarcity in structural damage detection.
method 1-D Wasserstein Deep Convolutional Generative Adversarial Networks (1-D WDCGAN-GP) for synthetic data generation.
result Generated synthetic data improves damage detection accuracy in 1-D Deep Convolutional Neural Networks.
Bayesian method detects mesoscale structures in pathway data networks.
problem Mesoscale structures in pathway data networks are hard to detect due to dependencies between interactions.
method Bayesian approach modeling optimal partitioning and higher-order dynamics.
result Method can recover both proximity-based and role-based groupings of nodes.
Relational data-like graphs, networks, and matrices-is often dynamic, where the relational structure evolves over time. A fundamental problem in the analysis of time-varying network data is to extract a summary of the common structure and the dynamics of the underlying relations between the entities. Here we build on t…
Recent research on Bitcoin Transaction Networks reveals a growing, sparse, and core-periphery structure.
problem Understanding the evolution of Bitcoin's network structure and user behavior.
method Review of recent results on Bitcoin Transaction Networks, including Address Network, User Network, and Lightning Network.
result Bitcoin Transaction Networks exhibit a core-periphery structure, indicating increasing centralization.
This paper uncovers the low-rank structure of neural network Hessians.
problem Understanding the structure of Hessians in neural networks.
method Proposes a decoupling conjecture to decompose layer-wise Hessians into Kronecker products of smaller matrices.
result Proves the structure of top eigenspaces in 2-layer networks and shows high overlap in top eigenvectors across different models.
Graph neural networks detect structural perturbations from time series data.
problem Detecting structural causes of disturbances in complex systems.
method Graph neural network approach to infer structural perturbations from functional time series.
result Data-driven approach outperforms typical reconstruction methods and meets Bayesian inference accuracy.
New approach learns latent motifs in networks for mesoscale structure analysis.
problem Understanding large-scale behavior in complex systems through mesoscale structures.
method Network dictionary learning (NDL) combining network sampling and nonnegative matrix factorization.
result Networks can be approximated using a small set of latent motifs.
IC-Network improves CNNs by integrating elastic collision units.
problem Designing more effective basic units in neural networks.
method Developed IC layer and IC block units combining the IC structure with convolution operations.
result Significant performance improvements in existing CNNs, reducing top-1 error from 22.85% to 21.49% on imagenet.
New methods test correlation between network structure and node features.
problem Assessing correlation between network structure and node-level covariates.
method Four novel methods based on linear models and canonical correlation analysis.
result Theoretical guarantees and computational efficiency for testing network dependency.
Structured prediction energy networks (SPENs; Belanger & McCallum 2016) use neural network architectures to define energy functions that can capture arbitrary dependencies among parts of structured outputs. Prior work used gradient descent for inference, relaxing the structured output to a set of continuous variables a…
A growing number of systems are represented as networks whose architecture conveys significant information and determines many of their properties. Examples of network architecture include modular, bipartite, and core-periphery structures. However inferring the network structure is a non trivial task and can depend som…
Feature networks link ML features via graph structure for enhanced learning.
problem Enhancing feature expressiveness and learning efficiency in machine learning.
method Graph representation of feature vectors, leveraging Fourier and functional analysis.
result Feature networks enable novel, complex feature dependencies.
Bayesian network structures are usually built using only the data and starting from an empty network or from a naive Bayes structure. Very often, in some domains, like medicine, a prior structure knowledge is already known. This structure can be automatically or manually refined in search for better performance models.…