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.
Improved graph attention model for noisy graphs.
SpGAT learns graph representations using spectral attention for efficiency.
Graph attention networks improve performance on heterogeneous graphs.
Graph attention improves node classification by distinguishing important edges.
Attention operators have been widely applied in various fields, including computer vision, natural language processing, and network embedding learning. Attention operators on graph data enables learnable weights when aggregating information from neighboring nodes. However, graph attention operators (GAOs) consume exces…
This paper explains GNNs using graph signal denoising.
CLEAR learns causal graphs from attention in recommender systems to explain user behavior.
PiNet improves graph classification efficiency and accuracy.
HopGAT improves node classification in sparsely labeled graphs by learning from distant neighbors.
Graph attention is not always beneficial; conditions for perfect node classification are identified.
Enhanced GNN with expanded attention window and partially random embeddings.
We aim to better understand attention over nodes in graph neural networks (GNNs) and identify factors influencing its effectiveness. We particularly focus on the ability of attention GNNs to generalize to larger, more complex or noisy graphs. Motivated by insights from the work on Graph Isomorphism Networks, we design …
We investigate Relational Graph Attention Networks, a class of models that extends non-relational graph attention mechanisms to incorporate relational information, opening up these methods to a wider variety of problems. A thorough evaluation of these models is performed, and comparisons are made against established be…
Study compares deep learning models for traffic forecasting, highlighting graph elements' impact.
We present an attention mechanism inspired from definition of screened Coulomb potential. This attention mechanism was used to interpret the Graph Attention (GAT) model layers and training dataset by using a flexible and scalable framework (CoulGAT) developed for this purpose. Using CoulGAT, a forest of plain and resne…
Attention-based GNNs can't prevent oversmoothing, leading to homogeneous node representations.
FastGAT reduces GNN computation time by 10x using graph sparsification.
MAGNA improves graph neural networks by incorporating multi-hop context information.
Proposes a novel node embedding framework for graphs using Fisher Information.
Graph convolutional networks (GCNs) have shown the powerful ability in text structure representation and effectively facilitate the task of text classification. However, challenges still exist in adapting GCN on learning discriminative features from texts due to the main issue of graph variants incurred by the textual …
A new method reduces memory requirements for Graph Transformers by sparsely training a network.
Graph Attention Networks (GATs) are the state-of-the-art neural architecture for representation learning with graphs. GATs learn attention functions that assign weights to nodes so that different nodes have different influences in the feature aggregation steps. In practice, however, induced attention functions are pron…
RoGAT enhances GAT robustness against adversarial attacks.
EggNet reconstructs particle tracks from hits using evolving graph attention networks.
New interpretation of attention in Transformers and Graph Attention Networks.
Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art performance on many practical predictive tasks, such as node classification, link prediction and graph classification. Among the variants of GNNs, Graph Attention N…
Lipschitz normalization boosts deep attention models, especially for graph neural networks.
Graph convolutional networks (GCNs) have recently become one of the most powerful tools for graph analytics tasks in numerous applications, ranging from social networks and natural language processing to bioinformatics and chemoinformatics, thanks to their ability to capture the complex relationships between concepts. …
Graph attention network improves MLTC by capturing label dependencies.
Transformer learns graph structure better with subgraph info.
Graph convolutional network (GCN) is generalization of convolutional neural network (CNN) to work with arbitrarily structured graphs. A binary adjacency matrix is commonly used in training a GCN. Recently, the attention mechanism allows the network to learn a dynamic and adaptive aggregation of the neighborhood. We pro…
Can neural networks learn to compare graphs without feature engineering? In this paper, we show that it is possible to learn representations for graph similarity with neither domain knowledge nor supervision (i.e.\ feature engineering or labeled graphs). We propose Deep Divergence Graph Kernels, an unsupervised method …
GAT-AGNN learns stock trends using graph and attention mechanisms.
Graph Neural Networks (GNNs) are powerful to learn the representation of graph-structured data. Most of the GNNs use the message-passing scheme, where the embedding of a node is iteratively updated by aggregating the information of its neighbors. To achieve a better expressive capability of node influences, attention m…
NGAT predicts long-term stock trends using graph attention networks.
GACAN combines multi-granularity time series for traffic forecasting.
Recently, graph neural networks have attracted great attention and achieved prominent performance in various research fields. Most of those algorithms have assumed pairwise relationships of objects of interest. However, in many real applications, the relationships between objects are in higher-order, beyond a pairwise …
TSAM predicts directed temporal links using GCN and self-attention.
GAT-RWOS uses graph attention to improve imbalanced data classification.
Learning latent representations of nodes in graphs is an important and ubiquitous task with widespread applications such as link prediction, node classification, and graph visualization. Previous methods on graph representation learning mainly focus on static graphs, however, many real-world graphs are dynamic and evol…
Graph embedding methods represent nodes in a continuous vector space, preserving information from the graph (e.g. by sampling random walks). There are many hyper-parameters to these methods (such as random walk length) which have to be manually tuned for every graph. In this paper, we replace random walk hyper-paramete…
GATs improve node regression on noisy graphs with provable advantage.
Single-cell RNA sequencing (scRNA-seq) has revolutionized biological discovery, providing an unbiased picture of cellular heterogeneity in tissues. While scRNA-seq has been used extensively to provide insight into both healthy systems and diseases, it has not been used for disease prediction or diagnostics. Graph Atten…
AdaCAD improves semi-supervised classification by focusing on intra-class nodes.
Advanced methods of applying deep learning to structured data such as graphs have been proposed in recent years. In particular, studies have focused on generalizing convolutional neural networks to graph data, which includes redefining the convolution and the downsampling (pooling) operations for graphs. The method of …
This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regions are superpixels and edges connect neighboring superpixels. Our experiments suggest that Graph Attention Networks (GATs), which combine g…
Novel GNN model tackles few-shot learning with improved performance.
CoMGNN models heterogeneous graphs with evolving nodes and edges.