Research
On-device research index

arXiv research

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.

168,932 papers · 148 categories

Trend · papers per month

25.0%50.0%75.0%100.0% · Feb 199419922001200920172026
48 results for Graph Feature Network

Edge features contain important information about graphs. However, current state-of-the-art neural network models designed for graph learning, e.g. graph convolutional networks (GCN) and graph attention networks (GAT), adequately utilize edge features, especially multi-dimensional edge features. In this paper, we build…

2018-09-07abs ↗pdf ↗

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.

Graph auto-encoder predicts unobserved node features from biological networks and omics data.

problem Integrating biological networks and continuous node features for better prediction.
method Graph neural networks and feature auto-encoders trained on feature reconstruction.
result Graph feature auto-encoder outperforms auto-encoders trained on graph reconstruction for predicting unobserved node features.

Graph matching with feature vectors is solved using a two-layer graph neural network.

problem Graph matching in the presence of sparse binary features.
method Two-layer graph neural network with graph structure.
result Graph neural network can recover correct mapping with high probability under certain conditions.

Proposes dynamic graph and node feature learning in GCNNs for better adaptability.

problem Fixed graphs for all GCNN layers limit adaptability to node feature structures.
method Dynamic graph and node feature learning using Mahalanobis distance metric.
result Superior performance in point clouds and citation networks.

MR-GNN predicts interactions between structured entities using multi-resolution and dual graph neural networks.

problem Predicting interactions between structured entities, especially considering features in substructures of different sizes and interactions between entities.
method MR-GNN uses a multi-resolution architecture and dual graph-state L-STMs to extract features from different neighborhoods and pairwise graphs, respectively.
result MR-GNN improves prediction accuracy compared to state-of-the-art methods.

Enhances graph neural networks by considering feature similarities in node aggregation.

problem Ignoring node feature similarities in traditional graph aggregation schemes.
method Interprets node aggregation as kernel weighting, proposing a framework that considers feature similarities.
result Proposed framework outperforms traditional GCNs in real-world applications.

GCN adapted for graphs with missing features, improving performance.

problem GCN struggles with graphs containing missing features.
method Integrates missing feature processing within GCN architecture using Gaussian Mixture Model.
result Significantly outperforms imputation-based methods in node classification and link prediction.

Graph neural networks are found to be primarily low-pass filters, not manifold learners.

problem Improving performance and scalability of graph neural networks for graph-structured data.
method Developed a theoretical framework based on graph signal processing.
result Graph neural networks only perform low-pass filtering on feature vectors and do not have non-linear manifold learning property.

Cross-GCN models cross features in GCN for better performance.

problem GCN's lack of cross feature modeling limits its effectiveness.
method Introduces Cross-feature Graph Convolution (Cross-GCN) to model cross features explicitly.
result Explicit cross feature modeling improves GCN's performance on tasks requiring cross features.

Improved graph neural networks by separating feature aggregation and depth.

problem Understanding feature importance in graph neural networks without prior information.
method Decoupling feature aggregation and depth, using softmax as a regularizer, and introducing 'Soft-Selector' and 'Hop-Normalization'.
result FSGNN model achieves up to 64% accuracy improvements in node classification tasks.

New network learns image features inductively for disease classification.

problem Pre-processing image features limits network optimization.
method Inductive end-to-end learning with CNN and graph filters trained jointly.
result Significantly improved classification scores and higher stability.

engGNN combines external and generated graphs to improve disease classification and biomarker discovery.

problem Challenges in integrating omics data due to high dimensionality and small sample sizes.
method Dual-graph framework that integrates external biological networks with data-driven generated graphs.
result engGNN outperforms state-of-the-art methods in disease classification and biomarker discovery.

A new GNN module learns geometric scattering features for better graph classification and feature exploration.

problem Learning long-range graph relations and extracting meaningful features from graphs.
method Proposes a learnable geometric scattering (LEGS) module in graph neural networks (GNNs), incorporating wavelet filters.
result LEGS-based GNNs outperform existing methods in graph classification and feature extraction tasks.

Improves molecular activity prediction using graph convolutional neural networks considering graph distances.

problem Predicting molecular activity using graph convolutional neural networks with improved distance representation.
method Proposed three improvements: modified graph distances, distance-dependent weight matrices, and weighted sum conversion.
result The proposed method slightly outperforms the original weave module in compound activity prediction.

Paper presents a novel approach for global feature aggregation in Graph Neural Networks.

problem Graphs lack a straightforward way to perform non-local feature aggregation like images and texts.
method Utilizes Latent Fixed Data Structure (LFDS) to aggregate feature vectors from local extraction.
result Proposed methods achieve competitive or better results with linear computational complexity.

Graph Laplacian spectrum serves as a robust feature representation.

problem Difficulties in analyzing and comparing graphs due to their structure.
method Proposes using the graph Laplacian spectrum (GLS) as a feature representation.
result Graph Laplacian spectrum (GLS) preserves structural information and is consistent under deformation and invariance under isomorphism.

GISST interprets GNNs by combining attention and sparsity for graph structure and node feature importance.

problem Lack of joint consideration of graph structure and node features in GNN interpretation.
method Model-agnostic framework using attention mechanism and sparsity regularization.
result GISST achieves superior node feature and edge explanation precision in synthetic and real-world datasets.

This study explores how feature graphs enhance GNNs' performance in modeling interactions.

problem Improving GNNs' ability to model feature interactions effectively.
method Investigates feature graphs and their importance in GNNs, using experiments and theoretical support.
result Edges between interacting features are crucial for GNNs, while non-interaction edges can degrade performance.

Graph learning is often unnecessary for common benchmarks, as node features can suffice.

problem The necessity of graph learning in common graph benchmarks is often assumed.
method We compared graph learning to feature-only models on seven datasets and found that graph structure often adds little to performance.
result Node features can often suffice for common graph benchmarks, challenging the orthodoxy.

The paper presents a method for analyzing shape graphs using specific features.

problem Analyzing geometric and topological variations in shape graphs.
method Curated set of topological, geometric, and directional features for shape graph analysis.
result The feature representation is effective for tasks like group comparison and classification.

DMGNN predicts 3D human motions using adaptive multiscale graphs.

problem Predicting 3D skeleton-based human motions accurately.
method Dynamic multiscale graph neural networks (DMGNN) with adaptive multiscale graphs and MGCU.
result DMGNN outperforms state-of-the-art methods in short and long-term predictions.

HTGCN improves community detection in dynamic, heterogeneous graphs.

problem Challenges in detecting communities in graphs with varying features and temporal dynamics.
method Designs HTGCN combining heterogeneous GCN and residual compressed aggregation for dynamic feature representation.
result HTGCN outperforms existing methods on DBLP and IMDB datasets.

Graphs from features improve classification accuracy in tasks.

problem Traditional classification tasks can be improved by incorporating relational information.
method Construct geometric graphs from features and use them in Graph Convolutional Networks.
result Graphs derived from features increase classification accuracy and improve class separation.

A hierarchy of GNNs based on learnable local features is proposed.

problem Limited understanding of GNN architectures and their systematic construction.
method A hierarchy of GNNs based on aggregation regions is derived, and theoretical results are provided.
result Simple GNN architecture exceeds Weisfeiler-Lehman graph isomorphism test.

Efficient memory layer improves graph neural networks for graph classification and regression.

problem Efficiently learning node representations and graph coarsening for arbitrary graph topology.
method Introduces a memory layer for GNNs that learns node representations and graph coarsening, and two new networks: MemGNN and GMN.
result Proposed models achieve state-of-the-art results in graph classification and regression benchmarks.

New graph representation learning network improves scalability and feature integration.

problem Scalability and feature integration in graph neural networks for large, dense graphs.
method Adaptive sampling of neighbours based on weighted multi-step transition probabilities.
result Comparable or better results on various graph benchmarks.

Graph neural networks perform better with more features and training data.

problem Comparing graph neural networks to simple models in semi-supervised node classification.
method Empirical evaluation of graph neural network architectures in various settings.
result More complex graph networks outperform simple models in settings with fewer features and more training data.

forgeNet uses a tree-based ensemble to learn feature graphs for deep learning in omics data.

problem Small sample size vs. large feature space in omics data.
method forgeNet integrates a forest feature graph extractor with a GEDFN architecture.
result ForgeNet achieves high classification accuracy on synthetic and real datasets.

Graph Neural Networks improve machine learning on relational databases.

problem Training machine learning models on relational databases requires costly data extraction and feature engineering.
method Uses Graph Neural Networks to extract features from relational databases.
result Outperforms state-of-the-art automatic feature engineering methods.

Simpler GNNs perform well on graph classification tasks.

problem Understanding what Graph Neural Networks (GNNs) learn and their complexity.
method Dissected GNNs into graph filtering and set function, linearizing them separately.
result Linear graph filtering with non-linear set function is efficient and powerful.

Simplifies GNN models by selecting important features for node classification.

problem Challenges in analyzing and selecting important features in GNN models.
method Decoupling feature aggregation and depth, using softmax and L2-normalization.
result FSGNN achieves comparable or higher accuracy than state-of-the-art GNN models.

PGMs and GNNs differ in capturing network data; PGMs outperform GNNs in noisy and heterophily scenarios.

problem Comparing PGMs and GNNs in network data.
method Link prediction task with synthetic and real networks; three experiments on input features, noise, and heterophily.
result PGMs outperform GNNs in noisy and heterophily scenarios.