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.
GCRNNs improve graph problem solving with fewer parameters.
Enhances graph neural networks with Relational Pooling for better graph classification.
This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by an arbitrary graph. Such structured sequences can represent series of frames in v…
AGCRN forecasts traffic using adaptive graph and recurrent learning.
EWS-GCN improves credit scoring by analyzing money transfer connections.
SHARE predicts city-wide parking availability using a hierarchical graph neural network.
Overview of structured data representation methods.
Traffic forecasting is a particularly challenging application of spatiotemporal forecasting, due to the time-varying traffic patterns and the complicated spatial dependencies on road networks. To address this challenge, we learn the traffic network as a graph and propose a novel deep learning framework, Traffic Graph C…
PSTN improves traffic condition forecasting with deep neural networks.
EvolveGCN adapts GCN for dynamic graphs without node embeddings.
RecNets use RNNs to process image channels in a compact, recurrent way.
In this paper, we use variational recurrent neural network to investigate the anomaly detection problem on graph time series. The temporal correlation is modeled by the combination of recurrent neural network (RNN) and variational inference (VI), while the spatial information is captured by the graph convolutional netw…
ST-UNet models spatio-temporal graphs by pooling and unpooling operations.
Transfer learning improves highway traffic forecasting using graph neural networks.
Matrix completion models are among the most common formulations of recommender systems. Recent works have showed a boost of performance of these techniques when introducing the pairwise relationships between users/items in the form of graphs, and imposing smoothness priors on these graphs. However, such techniques do n…
FGNN generalizes graph neural networks to capture higher-order dependencies.
Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain. Traffic forecasting is one canonical example of such learning task. The task is challenging due to (1) complex spatial dependency on road networks, (2) non-linear temporal dynamics with changing road conditions and (…
CMDRNN predicts user location using WiFi fingerprints with deep learning.
Learning to predict solutions to real-valued combinatorial graph problems promises efficient approximations. As demonstrated based on the NP-hard edge clique cover number, recurrent neural networks (RNNs) are particularly suited for this task and can even outperform state-of-the-art heuristics. However, the theoretical…
We propose a multi-label multi-task framework based on a convolutional recurrent neural network to unify detection of isolated and overlapping audio events. The framework leverages the power of convolutional recurrent neural network architectures; convolutional layers learn effective features over which higher recurren…
We propose a machine learning approach to address a key challenge in materials science: predicting how fractures propagate in brittle materials under stress, and how these materials ultimately fail. Our methods use deep learning and train on simulation data from high-fidelity models, emulating the results of these mode…
Recurrent Neural Networks (RNNs) with sophisticated units that implement a gating mechanism have emerged as powerful technique for modeling sequential signals such as speech or electroencephalography (EEG). The latter is the focus on this paper. A significant big data resource, known as the TUH EEG Corpus (TUEEG), has …
Review of neural network expressivity and architectures.
This study compares RNN and CNN for predicting wave propagation using the Saint-Venant equations.
Paper presents RGNN for better graph node representation learning.
Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications …
A new neural network learns from acoustic scenes by suppressing irrelevant patterns.
New kernel-based models improve on traditional neural methods in sequence modeling.
NNs can learn efficient algorithms for certain problems.
In a number of disciplines, the data (e.g., graphs, manifolds) to be analyzed are non-Euclidean in nature. Geometric deep learning corresponds to techniques that generalize deep neural network models to such non-Euclidean spaces. Several recent papers have shown how convolutional neural networks (CNNs) can be extended …
Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structur…
New optimization algorithms on orthogonal group for machine learning.
Graph-partitioning-based DCRNN improves traffic forecasting for large highways.
Bird sounds possess distinctive spectral structure which may exhibit small shifts in spectrum depending on the bird species and environmental conditions. In this paper, we propose using convolutional recurrent neural networks on the task of automated bird audio detection in real-life environments. In the proposed metho…
RC reduces neural network redundancy and improves performance through independent BN layers.
Classical convolutional neural networks (cCNNs) are very good at categorizing objects in images. But, unlike human vision which is relatively robust to noise in images, the performance of cCNNs declines quickly as image quality worsens. Here we propose to use recurrent connections within the convolutional layers to mak…
Two solutions for multi-modal record linkage using Deep Learning inspired by Visual Question Answering.
Two deep learning models improve indoor location prediction from WiFi fingerprints.
Recent approaches based on artificial neural networks (ANNs) have shown promising results for short-text classification. However, many short texts occur in sequences (e.g., sentences in a document or utterances in a dialog), and most existing ANN-based systems do not leverage the preceding short texts when classifying …
Accurate and real-time traffic forecasting plays an important role in the Intelligent Traffic System and is of great significance for urban traffic planning, traffic management, and traffic control. However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road …
GraphVRNN generates graphs with latent variables and node attributes.
Recently, graph neural networks have been adopted in a wide variety of applications ranging from relational representations to modeling irregular data domains such as point clouds and social graphs. However, the space of graph neural network architectures remains highly fragmented impeding the development of optimized …
A hybrid CNN with shared parameters learns to incorporate recurrent structures.
Efficient deep GNNs achieve state-of-the-art performance without training.
In this article, we propose a novel technique for classification of the Murmurs in heart sound. We introduce a novel deep neural network architecture using parallel combination of the Recurrent Neural Network (RNN) based Bidirectional Long Short-Term Memory (BiLSTM) & Convolutional Neural Network (CNN) to learn visual …
Study compares deep learning models for traffic forecasting, highlighting graph elements' impact.
Automated protein structure prediction from cryo-EM data.
Generative model uses recurrent neural networks to predict graph edges.