Paper proposes LCP for structural encodings, outperforming existing methods.
problem Improving Graph Neural Networks performance through effective structural encodings.
method Geometric perspective, Local Curvature Profiles (LCP) for structural encodings, combining with global positional encodings, comparing with rewiring techniques.
result LCP significantly outperforms existing structural encodings and combining LCP with global positional encodings improves performance.
Deep learning speeds up design of organic photovoltaic structures.
problem Designing optimal organic photovoltaic structures is expensive and intractable.
method Introduced a CNN architecture as a fast surrogate for structure-property mapping and used it for robust microstructural design.
result Deep learning accelerates the design process for enhancing photovoltaic device performance.
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.
Structure plays a key role in learning performance. In centralized computational systems, hyperparameter optimization and regularization techniques such as dropout are computational means to enhance learning performance by adjusting the deep hierarchical structure. However, in decentralized deep learning by the Interne…
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.
EDAs with matrix transpose improve Bayesian structure learning performance.
problem Improving Bayesian structure learning performance.
method Introducing a matrix transpose mutation operator for EDAs in Bayesian structure learning.
result EDAs with transpose mutation give markedly better performance than conventional EDAs.
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.
We study the effect of structural variation in graph data on the predictive performance of graph kernels. To this end, we introduce a novel, noise-robust adaptation of the GraphHopper kernel and validate it on benchmark data, obtaining modestly improved predictive performance on a range of datasets. Next, we investigat…
GCNs learn by embedding similar nodes within a class and leveraging consistent neighborhood structures.
problem Understanding how GCNs perform semi-supervised node classification on both homophilous and heterophilous graphs.
method Investigated the latent node embeddings and neighborhood structures of GCNs.
result GCNs learn by embedding similar nodes within a class and leveraging consistent neighborhood structures.
Global graph structure improves GNN performance.
problem Limited graph structure in GNNs leads to indistinguishable node embeddings.
method Empirically tested the impact of global graph information on GNN performance.
result Global information can significantly improve GNN performance by more than 5%.
End-to-end neural network extracts graph structure from EEG signals for improved emotional video classification.
problem Challenges in achieving accurate EEG classification for emotional video analysis.
method Proposes an end-to-end neural network model that learns an appropriate multi-layer graph structure from raw EEG signals.
result Improves performance in emotional video classification compared to manually defined connectivity structures.
New MOSC clusters networks by considering both second- and third-order structures.
problem Limited consideration of higher-order structures in spectral clustering.
method Mixed-Order Spectral Clustering (MOSC) combining GL and RW for second- and third-order structures.
result MOSC outperforms existing SC methods on real-world networks.
This study validates BN structure learning algorithms under noisy data, revealing performance discrepancies.
problem Inconsistent performance claims across BN structure learning algorithms due to inconsistent evaluation methods.
method Applied 15 algorithms to noisy data in multiple studies, evaluating with various criteria.
result Traditional synthetic performance may overestimate real-world performance by 10-50%.
Study validates capital structure theories in Indian public sector banks.
problem Understanding the impact of capital structure on financial performance in Indian banks.
method Developed theoretical framework from capital structure theories, tested hypotheses using statistical techniques.
result Established relation between debt component and financial performance variables.
We consider the problem of joint estimation of structured inverse covariance matrices. We perform the estimation using groups of measurements with different covariances of the same unknown structure. Assuming the inverse covariances to span a low dimensional linear subspace in the space of symmetric matrices, our aim i…
Study examines how mergers and acquisitions affect Indian banks' financial performance and capital structure.
problem Impact of mergers and acquisitions on Indian banks' financial performance and capital structure.
method Statistical analysis using paired t-test on selected banks' annual reports.
result Mergers and acquisitions significantly impact financial performance and capital structure of Indian banks.
Graph classification models are sensitive to initialisation and structure, but simple models perform well.
problem Graph classification models' performance is sensitive to initialisation and structure.
method Examined recent graph coarsening architectures and their performance sensitivity.
result Simple models like MLP, single-layer GCN, and fixed-weight GCN achieve competitive performance.
In this report we describe a tool for comparing the performance of graphical causal structure learning algorithms implemented in the TETRAD freeware suite of causal analysis methods. Currently the tool is available as package in the TETRAD source code (written in Java). Simulations can be done varying the number of run…
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.
Many predicted structured objects (e.g., sequences, matchings, trees) are evaluated using the F-score, alignment error rate (AER), or other multivariate performance measures. Since inductively optimizing these measures using training data is typically computationally difficult, empirical risk minimization of surrogate …
A new predictive coding algorithm improves machine learning performance.
problem Improving performance of variational inference algorithms in high-dimensional, structured problems.
method Divide-and-Conquer Predictive Coding (DCPC) that respects generative model correlation structure and performs maximum-likelihood updates.
result DCPC achieves better numerical performance and accurate inference in structured generative models.
Adapts manifold structure for better clustering performance.
problem Lack of consideration for local manifold structure in existing multiple kernel k-means methods.
method Adopts manifold adaptive kernel to integrate local manifold structure of kernels.
result Proposed method outperforms state-of-the-art methods.
We discuss structured Schatten norms for tensor decomposition that includes two recently proposed norms ("overlapped" and "latent") for convex-optimization-based tensor decomposition, and connect tensor decomposition with wider literature on structured sparsity. Based on the properties of the structured Schatten norms,…
Study shows structured reservoirs improve deep ESN performance.
problem Improving performance of deep reservoir computing networks.
method Investigated structured reservoir topologies in deep ESNs.
result Structured reservoirs significantly enhance predictive performance.
A new method improves AI fairness assessment by estimating performance across intersectional subgroups.
problem Limited evaluation of AI systems across intersectional subgroups due to small sample sizes.
method Structured regression approach to disaggregated evaluation.
result Our method yields more accurate performance estimates, especially for small subgroups.
Backtests of structured strategies lose much of their predictive power in live trading.
problem Uncertainty in how marketed backtests predict live performance of structured strategies.
method Analysis of 1,726 structured strategies from ten global institutions.
result Raw backtests have limited portability into live trading and deteriorate sharply.
New method improves meta-learning performance by task-specific initialization.
problem Difficulties in generalizing and achieving theoretical guarantees in conditional meta-learning.
method Structured prediction approach for task-specific initialization.
result TASML improves performance of existing meta-learning models.
Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been addressed with representational learning technique…
Proposes a new NMF method incorporating neighborhood structure for better anomaly detection.
problem NMF's inability to incorporate neighborhood structure information limits its performance in nonlinear manifold structures.
method Integrates neighborhood structure information using Minimum Spanning Tree (MST) within NMF framework.
result Empirical results show superior performance in anomaly detection using the proposed method.
BLAST optimizes deep model inference by learning efficient matrix structures.
problem Efficient inference of large-scale deep neural networks.
method Introduces BLAST matrix for adaptive structured weights.
result Significant compression and performance improvements for various model sizes.
Sparse deep neural networks(DNNs) are efficient in both memory and compute when compared to dense DNNs. But due to irregularity in computation of sparse DNNs, their efficiencies are much lower than that of dense DNNs on regular parallel hardware such as TPU. This inefficiency leads to poor/no performance benefits for s…
We study the problem of structured prediction under test-time budget constraints. We propose a novel approach applicable to a wide range of structured prediction problems in computer vision and natural language processing. Our approach seeks to adaptively generate computationally costly features during test-time in ord…
Machine learning improves RNA secondary structure prediction.
problem Stagnant performance of RNA secondary structure prediction methods.
method Machine learning, especially deep learning, is used to predict RNA secondary structures.
result Machine learning methods have improved the prediction of RNA secondary structures.
EEGNN improves graph neural networks by enhancing graph structure.
problem Mis-simplification of graphs by removing self-loops and unweighted edges reduces GNN performance.
method Proposes EEGNN framework using DMPGM for better graph structural information.
result EEGNN achieves significant performance improvement over baselines.
We study the classification performance of Kronecker-structured models in two asymptotic regimes and developed an algorithm for separable, fast and compact K-S dictionary learning for better classification and representation of multidimensional signals by exploiting the structure in the signal. First, we study the clas…
This paper introduces structure learning for autoencoder recommenders to improve performance and generalization.
problem Efficient training and generalization in sparse collaborative filtering data.
method Learn groups of related items and use this information to determine the connectivity structure of an auto-encoding neural network.
result The proposed structure learning method results in a sparse network that converges to a local optimum with smaller spectral norm and generalization error.
The performance of sparse signal recovery from noise corrupted, underdetermined measurements can be improved if both sparsity and correlation structure of signals are exploited. One typical correlation structure is the intra-block correlation in block sparse signals. To exploit this structure, a framework, called block…
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.
Approaches to learning Bayesian networks from data typically combine a scoring function with a heuristic search procedure. Given a Bayesian network structure, many of the scoring functions derived in the literature return a score for the entire equivalence class to which the structure belongs. When using such a scoring…
A new method for graph-structured data improves transformer performance by incorporating topology.
problem Improving transformer performance on graph-structured data.
method Parameterizing topological masks as a learnable function of a weighted adjacency matrix, approximated with graph random features.
result Efficient masking algorithms provide strong performance gains for tasks on image and point cloud data.
Two new methods improve graph embedding without needing a complete graph structure.
problem Graph autoencoders' performance depends on the adjacency matrix quality.
method BAGE and VBAGE: unsupervised graph embedding via adaptive graph learning.
result The methods expand GAEs' applicability to datasets without graph 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.
We conduct an extensive empirical study on short-term electricity price forecasting (EPF) to address the long-standing question if the optimal model structure for EPF is univariate or multivariate. We provide evidence that despite a minor edge in predictive performance overall, the multivariate modeling framework does …
This work proposes a method to learn graph structure for multivariate time series forecasting.
problem Improving multivariate time series forecasting by leveraging pairwise information.
method Learning a probabilistic graph model through optimizing mean performance over graph distribution parameterized by a neural network.
result Our method outperforms existing approaches in simplicity, efficiency, and performance.
Rewiring GNNs to optimize community and feature alignment improves their performance.
problem Improving GNNs' performance by addressing over-squashing and generalization issues.
method Three rewiring strategies: ComMa, FeaSt, and ComFy, targeting community structure, node labels, and their alignment.
result Rewiring strategies enhance GNNs' performance by optimizing label-community alignment.
ShotgunCSP predicts crystal structures using machine learning, achieving high accuracy with minimal computation.
problem Predicting stable or metastable crystal structures of large systems.
method Noniterative screening using transfer learning and generative models.
result ShotgunCSP achieves 93.3% accuracy in benchmark tests with 90 different crystal structures.
We introduce structured prediction energy networks (SPENs), a flexible framework for structured prediction. A deep architecture is used to define an energy function of candidate labels, and then predictions are produced by using back-propagation to iteratively optimize the energy with respect to the labels. This deep a…
Algorithm identifies best arm with prior info in structured bandits.
problem Bayesian fixed-budget best-arm identification in structured bandits.
method Prior-dependent allocations based on structure and prior information.
result Improved theoretical bounds and robust performance across diverse models.