TSAM predicts directed temporal links using GCN and self-attention.
problem Predicting links in directed temporal networks.
method GCN, self-attention mechanism, autoencoder architecture, graph attentional layers, graph convolutional layers, graph recurrent unit layer.
result TSAM outperforms benchmarks on four realistic networks.
Next point-of-interest (POI) recommendation aims to offer suggestions on which POI to visit next, given a user's POI visit history. This problem has a wide application in the tourism industry, and it is gaining an increasing interest as more POI check-in data become available. The problem is often modeled as a sequenti…
Flow prediction (e.g., crowd flow, traffic flow) with features of spatial-temporal is increasingly investigated in AI research field. It is very challenging due to the complicated spatial dependencies between different locations and dynamic temporal dependencies among different time intervals. Although measurements of …
Enhances understanding of patient healthcare journeys using self-attention.
problem Capturing hidden dependencies in multi-level patient journey data.
method Proposes a multi-level self-attention network (MusaNet) for encoding patient journeys.
result MusaNet produces higher-quality representations than state-of-the-art methods.
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…
Self-attention model improves HAR from wearable sensors.
problem Capturing spatio-temporal context from sensor data.
method Proposes a self-attention based neural network model.
result Significant performance improvement over state-of-the-art models.
Modern deep learning approaches have achieved groundbreaking performance in modeling and classifying sequential data. Specifically, attention networks constitute the state-of-the-art paradigm for capturing long temporal dynamics. This paper examines the efficacy of this paradigm in the challenging task of emotion recog…
GTEA learns node representations in temporal interaction graphs.
problem Inductive representation learning on temporal interaction graphs.
method Integrates sequence model with time encoder and self-attention scheme for edge and node embeddings.
result GTEA learns comprehensive node representations capturing temporal and structural characteristics.
SARD improves deep learning clinical prediction performance.
problem Deep learning models struggle to match linear models in healthcare predictions.
method Reverse Distillation to initialize deep models, combined with contextual and temporal embeddings.
result SARD outperforms state-of-the-art methods on clinical prediction outcomes.
Sequential modelling with self-attention has achieved cutting edge performances in natural language processing. With advantages in model flexibility, computation complexity and interpretability, self-attention is gradually becoming a key component in event sequence models. However, like most other sequence models, self…
A method to generate long-range human actions by leveraging graph convolutional networks and self-attention.
problem Generating long-range skeleton-based human actions is challenging due to small frame deviations.
method Proposes a variant of GCNs with self-attention to adaptively sparsify action graphs and capture structure information.
result Extensive experiments show superior performance compared to existing methods on human action datasets.
EFA extends self-attention to handle mixed data types and dynamic relevance.
problem Handling high-dimensional, mixed data types with dynamic relevance.
method Probabilistic generative model using self-attention and latent factor model.
result EFA consistently outperforms existing models in complex latent structure capture and reconstruction.
MetNet forecasts precipitation up to 8 hours with high spatial and temporal resolution.
problem Precise weather forecasting for long lead times.
method Neural network architecture using axial self-attention for global context aggregation.
result MetNet outperforms Numerical Weather Prediction at forecasts of up to 8 hours.
MEANTIME improves sequential recommendation by using multi-temporal embeddings and attention mechanisms.
problem Limited use of timestamp information and information bottleneck in sequential recommendation models.
method MEANTIME employs multiple types of temporal embeddings and attention mechanisms to capture diverse patterns from user behavior sequences.
result MEANTIME outperforms state-of-the-art sequential recommendation methods.
The paper uses GRU and self-attention for SPY option pricing.
problem Precise prediction of SPY option prices for better investment decisions.
method Partitioned dataset, built four models, used SHAP for interpretation.
result Self-attention GRU model outperforms traditional models.
OracleAD detects multivariate time series anomalies without labels.
problem Rare and unlabeled multivariate time series anomalies.
method OracleAD encodes past sequences into causal embeddings, projects them into a latent space, and identifies anomalies based on deviations from a stable latent structure.
result OracleAD achieves state-of-the-art results and is interpretable.
Study examines asset pricing using various attention models, finding global self-attention and sliding window sparse attention models perform well.
problem Traditional asset pricing models miss temporal dependency and short memory issues.
method Investigates RNN attention models with various attention mechanisms for large-cap US stocks.
result Global self-attention and sliding window sparse attention models outperform in deriving returns and hedging risks, especially during the pandemic.
Efficient sparse attention reduces self-attention complexity and improves model performance.
problem Quadratic compute and memory requirements of self-attention for long sequences.
method Content-based sparse attention with dynamic routing module.
result Routing Transformer achieves state-of-the-art performance on various benchmarks.
A new perspective on self-attention models using MLPs.
problem Improving sequence modeling with self-attention mechanisms.
method Introducing HyperMLP and HyperGLU, which use dynamic two-layer MLPs with reverse-offset layout.
result HyperMLP/HyperGLU consistently outperform softmax-attention baselines.
Model handles missing data in partial blackouts for multivariate time series.
problem Missing values in multivariate time series data.
method Two-stage imputation process using self-attention and diffusion processes.
result Model effectively handles missing data during training and outperforms state-of-the-art.
Asynchronous events on the continuous time domain, e.g., social media actions and stock transactions, occur frequently in the world. The ability to recognize occurrence patterns of event sequences is crucial to predict which typeof events will happen next and when. A de facto standard mathematical framework to do this …
Framework learns dynamic graph attributes and links co-evolution.
problem Forecasting change of node attributes and link formation in dynamic graphs.
method CoEvoGNN framework with temporal self-attention and joint optimization.
result Framework outperforms baselines on predicting unseen graph snapshots.
Proposes a transformer model with geostatistical inductive bias for spatio-temporal forecasting.
problem Combining probabilistic rigor of geostatistics with flexible deep learning representations.
method Spatially-informed transformer with learnable covariance kernel.
result Successfully recovers spatial decay parameters end-to-end via backpropagation.
OLinear forecasts time series more efficiently by transforming data orthogonally.
problem Efficiently forecasting time series with entangled dependencies.
method OLinear uses OrthoTrans to transform data orthogonally, then applies NormLin for linear layer.
result OLinear achieves state-of-the-art performance with high efficiency.
TGAT learns node embeddings for evolving graphs, capturing both static and temporal features.
problem Learning node embeddings for dynamic graphs with evolving topological structures and temporal patterns.
method Temporal Graph Attention (TGAT) layer using self-attention and functional time encoding.
result TGAT model can inductively infer node embeddings for new and observed nodes as the graph evolves.
Monoaural audio source separation is a challenging research area in machine learning. In this area, a mixture containing multiple audio sources is given, and a model is expected to disentangle the mixture into isolated atomic sources. In this paper, we first introduce a challenging new dataset for monoaural source sepa…
A new model captures complex event data using attention and Fourier kernels.
problem Capturing complex non-linear temporal dependencies in discrete event data.
method Integrates attention mechanism into point processes' conditional intensity function and uses Fourier kernel embedding.
result Established theoretical properties and demonstrated competitive performance.
NeoMLP improves neural fields by adding self-attention for better downstream tasks.
problem Complexity and lack of conditioning mechanisms in neural fields.
method Transformed MLP into NeoMLP with self-attention and weight-sharing.
result NeoMLP outperforms state-of-the-art methods in downstream tasks.
RKT model improves knowledge tracing by considering exercise relations and student forget behavior.
problem Traditional KT models fail to consider both exercise relations and student forget behavior.
method RKT model uses relation-aware self-attention to incorporate exercise relations and student forget behavior.
result RKT model outperforms state-of-the-art KT methods on real-world datasets.
Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context information, has been shown to achieve significantly lower word error rates (WERs) co…
Visual analytics system for comparing medical records using sequence embeddings.
problem Challenges in analyzing medical records due to high dimensionality, irregularity, and sparsity.
method Event and sequence embeddings using autoencoder and self-attention mechanism, with sequence alignment for comparison.
result Demonstrated effectiveness with real-world neonatal ICU dataset.
Multi-horizon forecasting problems often contain a complex mix of inputs -- including static (i.e. time-invariant) covariates, known future inputs, and other exogenous time series that are only observed historically -- without any prior information on how they interact with the target. While several deep learning model…
GSA-Nets apply group equivariance to self-attention for vision tasks.
problem Improving self-attention networks for vision tasks.
method Define group-equivariant positional encodings.
result GSA-Nets outperform non-equivariant self-attention networks on vision benchmarks.
TK-GCN forecasts spatiotemporal dynamics using Koopman-enhanced graph convolutional networks.
problem Forecasting complex spatiotemporal dynamics over irregular domains.
method Two-stage framework: Koopman-enhanced Graph Convolutional Network (K-GCN) for spatial encoding and Transformer for temporal modeling.
result TK-GCN outperforms state-of-the-art methods in spatiotemporal cardiac dynamics forecasting.
Sequence models assign probabilities to variable-length sequences such as natural language texts. The ability of sequence models to capture temporal dependence can be characterized by the temporal scaling of correlation and mutual information. In this paper, we study the mutual information of recurrent neural networks …
New model predicts ICU patients' stay duration efficiently.
problem Efficient ICU bed allocation under resource constraints.
method Temporal Pointwise Convolution (TPC) model combining temporal and pointwise convolutions.
result Significant performance improvements over LSTM and Transformer models.
Self-attention prefers sparse functions of input sequences, reducing sample complexity.
problem Understanding the inductive biases of self-attention in modeling long-range dependencies.
method Theoretical analysis and synthetic experiments to probe sample complexity of learning sparse functions with Transformers.
result Bounded-norm Transformer networks can represent sparse functions of the input sequence with logarithmic sample complexity.
Self-attention models benefit equally from width and depth, but beyond a certain point, depth becomes less efficient.
problem Understanding the optimal balance between depth and width in self-attention models.
method Theoretical predictions and empirical ablations on networks of varying depths and widths.
result An optimal width of 30K is recommended for a 1-Trillion parameter network, marking a significant width for self-attention models.
Study algebraic invariants from lightning self-attention models.
problem Understanding polynomial coefficients of self-attention mechanisms.
method Identify algebraic invariants using polynomial coefficients and coordinate geometry.
result Found linear and nonlinear families of algebraic invariants.
Random forests with attention and self-attention improve regression performance.
problem Improving regression model performance on various datasets.
method Proposes new models using attention and self-attention mechanisms to solve regression problems.
result The models improve model performance on many datasets.
Paper investigates Lipschitz constants of self-attention modules in neural networks.
problem Lipschitz constants of self-attention modules in neural networks.
method Proved standard dot-product self-attention is not Lipschitz for unbounded input domain. Proposed L2 self-attention that is Lipschitz. Derived upper bound on L2 self-attention's Lipschitz constant.
result Proved standard self-attention is not Lipschitz for unbounded input domain and proposed an alternative L2 self-attention that is Lipschitz.
FMA-ETA predicts travel time using FFN with attention.
problem Estimating travel time from spatial-temporal data.
method FFN with Multi-factor self-attention mechanism.
result FMA-ETA outperforms state-of-the-art methods in prediction accuracy with faster inference.
The key to a Transformer model is the self-attention mechanism, which allows the model to analyze an entire sequence in a computationally efficient manner. Recent work has suggested the possibility that general attention mechanisms used by RNNs could be replaced by active-memory mechanisms. In this work, we evaluate wh…
Self attention mechanisms have become a key building block in many state-of-the-art language understanding models. In this paper, we show that the self attention operator can be formulated in terms of 1x1 convolution operations. Following this observation, we propose several novel operators: First, we introduce a 2D ve…
Kernel PCA explains self-attention mechanisms in deep learning models.
problem Understanding and explaining self-attention mechanisms in deep learning models.
method Deriving self-attention from kernel principal component analysis (kernel PCA).
result RPC-Attention, a robust attention mechanism, outperforms softmax attention in various tasks.
Study reveals self-attention's role in learning and generalizing interactions.
problem Understanding self-attention's theoretical role in neural architectures.
method Interacting entities analysis, including multi-agent RL and genetic sequences.
result Self-attention efficiently represents, learns, and generalizes pairwise interactions.
Paper uses Time Series Transformer for bank stability prediction.
problem Predicting bank stability using complex financial data.
method Time Series Transformer model with self-attention mechanism.
result Time Series Transformer model outperforms other models in MSE and MAE.
Linformer reduces transformer complexity to linear, improving efficiency.
problem High cost of training and deploying large transformer models for long sequences.
method Approximates self-attention with low-rank matrix, proposing Linformer with O(n) complexity. result Linformer performs similarly to standard transformers but is more memory- and time-efficient.