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.
Paper introduces a conformer-based system for streaming language identification in long-form speech.
Acoustic scenes are rich and redundant in their content. In this work, we present a spatio-temporal attention pooling layer coupled with a convolutional recurrent neural network to learn from patterns that are discriminative while suppressing those that are irrelevant for acoustic scene classification. The convolutiona…
Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction. In this work, we present a novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for video-based person re-identification, which enables the feature extractor to be aware of …
Video-based emotion recognition is a challenging task because it requires to distinguish the small deformations of the human face that represent emotions, while being invariant to stronger visual differences due to different identities. State-of-the-art methods normally use complex deep learning models such as recurren…
Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to obtain an utterance level speaker representation. In this work we propose the use …
Hierarchical pretraining with slow-fast ODEs
PiNet improves graph classification efficiency and accuracy.
A new perspective on self-attention models using MLPs.
New approach reduces malware detection memory requirements and speeds up training.
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 …
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open research questions. Current research suggests using a simple temporal feature pooling…
ExNODE uses ODE to model sets with permutation equivariance.
Study reveals how attention helps in signal recovery from sequence models using random matrix theory.
Graph Neural Network (GNN) research has concentrated on improving convolutional layers, with little attention paid to developing graph pooling layers. Yet pooling layers can enable GNNs to reason over abstracted groups of nodes instead of single nodes. To close this gap, we propose a graph pooling layer relying on the …
While deep learning has achieved great success in computer vision and many other fields, currently it does not work very well on patient genomic data with the "big p, small N" problem (i.e., a relatively small number of samples with high-dimensional features). In order to make deep learning work with a small amount of …
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. …
Sound event detection (SED) methods are tasked with labeling segments of audio recordings by the presence of active sound sources. SED is typically posed as a supervised machine learning problem, requiring strong annotations for the presence or absence of each sound source at every time instant within the recording. Ho…
Distributed representations have been used to support downstream tasks in healthcare recently. Healthcare data (e.g., electronic health records) contain multiple modalities of data from heterogeneous sources that can provide complementary information, alongside an added dimension to learning personalized patient repres…
GSANet improves semantic segmentation accuracy with selective and global attention.
The spatio-temporal graph learning is becoming an increasingly important object of graph study. Many application domains involve highly dynamic graphs where temporal information is crucial, e.g. traffic networks and financial transaction graphs. Despite the constant progress made on learning structured data, there is s…
ST-SAN predicts flow with spatial-temporal dependencies using self-attention.
TSAM predicts directed temporal links using GCN and self-attention.
Hybrid model predicts flow and pressure in water systems.
Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition. For spatial attention, we learn a saliency mask to allow the model to focus…
Enhances SNNs for spatio-temporal feature extraction.
Paper proposes MTL for weakly labelled SED, improving performance with 2-step attention.
MEANTIME improves sequential recommendation by using multi-temporal embeddings and attention mechanisms.
This paper predicts stock prices using LLMs and news embeddings.
STCA discovers dynamic functional brain networks using spatial-temporal convolution and attention.
Proposes a graph pooling method leveraging node proximity for hierarchical graph representation learning.
SANST uses self-attentive networks with spatial and temporal embeddings for better POI recommendations.
New insights into how encoder-decoder networks generate attention matrices.
Federated learning interprets temporal dynamics across clients with graph attention.
RTFN extracts robust temporal features for time series analysis.
Optimal rebalancing strategy improves AMM pool performance by 25%.
Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampli…
A3T-GCN improves traffic forecasting by capturing spatial and temporal dependencies.
TGAT learns node embeddings for evolving graphs, capturing both static and temporal features.
Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire length of an input sequence. In this paper, we analyze the usage of attention mec…
Graph neural networks, which generalize deep neural network models to graph structured data, have attracted increasing attention in recent years. They usually learn node representations by transforming, propagating and aggregating node features and have been proven to improve the performance of many graph related tasks…
Graph Neural Networks (GNN) have been shown to work effectively for modeling graph structured data to solve tasks such as node classification, link prediction and graph classification. There has been some recent progress in defining the notion of pooling in graphs whereby the model tries to generate a graph level repre…
New protocol evaluates synthetic data for temporal consistency.
New framework predicts urban traffic with high accuracy.
As one of the important functions of the intelligent transportation system (ITS), supply-demand prediction for autonomous vehicles provides a decision basis for its control. In this paper, we present two prediction models (i.e. ARLP model and Advanced ARLP model) based on two system environments that only the current d…
Develops models for temporally abstract reasoning and attention.
EarnMore uses masked stock representations to train RL agents for customizable stock pools efficiently.
Paper proposes deep learning model for dynamic stock repurchase forecasting.
Representation learning (RL) plays an important role in extracting proper representations from complex medical data for various analyzing tasks, such as patient grouping, clinical endpoint prediction and medication recommendation. Medical data can be divided into two typical categories, outpatient and inpatient, that h…