REVIEW 23 cited by
Multi-Time Attention Networks for Irregularly Sampled Time Series
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Irregular sampling occurs in many time series modeling applications where it presents a significant challenge to standard deep learning models. This work is motivated by the analysis of physiological time series data in electronic health records, which are sparse, irregularly sampled, and multivariate. In this paper, we propose a new deep learning framework for this setting that we call Multi-Time Attention Networks. Multi-Time Attention Networks learn an embedding of continuous-time values and use an attention mechanism to produce a fixed-length representation of a time series containing a variable number of observations. We investigate the performance of this framework on interpolation and classification tasks using multiple datasets. Our results show that the proposed approach performs as well or better than a range of baseline and recently proposed models while offering significantly faster training times than current state-of-the-art methods.
Forward citations
Cited by 23 Pith papers
-
SurF: A Generative Model for Multivariate Irregular Time Series Forecasting
SurF applies the Time Rescaling Theorem as a learnable bijection to create a single generative model for forecasting irregular multivariate event streams that outperforms or matches baselines on six benchmarks.
-
TIDES: Implicit Time-Awareness in Selective State Space Models
TIDES reconciles selective SSM expressivity with continuous-time physical discretization by moving input dependence onto the state matrix, enabling native irregular time series handling and achieving SOTA on UEA and P...
-
FLUID: Continuous-Time Hyperconnected Sparse Transformer for Sink-Free Learning
FLUID is a continuous-time transformer using Liquid Attention Networks to model attention as stable ODE solutions that interpolate between discrete SDPA and CT-RNNs, with an explicit sink gate and liquid hyper-connect...
-
MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusion
A diffusion model trained on C-GASF images of mobile usage generates synthetic user traces that match real trace statistics far better than prior time-series generative baselines.
-
Kepler-Encoder-v0.1: Towards a Multimodal Embedding Model for Robots
A self-supervised multimodal encoder trained with vision, proprioception, and force yields a vision-only latent that recovers end-effector state and force above vision baselines on RH20T, with modest absolute force accuracy.
-
CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series
CLIR-Bench shows generalist and time-series LLMs struggle to ground clinical answers in sparse irregular ICU evidence, with top accuracy near 50% and weak causal evidence use.
-
Missingness as Signal: Channel-Independent Spectrogram Learning for Clinical Time Series Prediction
A channel-independent spectrogram model with an aligned missingness stream improves ICU mortality prediction by treating which measurements were taken as structured 2D signal.
-
LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Data
LakeFM pre-trains on large ecological datasets to forecast irregular lake time series and reports competitive or superior performance with physically plausible outputs.
-
PAMF: Prior-Aware Multimodal Fusion for Incomplete Time Series Data
PAMF initializes flow matching with missingness-type priors and shares encoder weights between imputation and classification to improve multimodal time-series prediction under incomplete observations.
-
TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models
TRACE proposes a temporal conditional estimation paradigm for multimodal time series foundation models that infers incomplete target modalities from auxiliary ones, outperforming prior fusion methods on clinical and s...
-
Physically-Constrained Mamba-SDE for Remaining Useful Life Prediction under Irregular Observations
PC-MambaSDE combines Mamba with physics-constrained SDE for RUL prediction under irregular observations, with theoretical stability guarantees and empirical outperformance on benchmarks.
-
The hidden risks of temporal resampling in clinical reinforcement learning
Resampling clinical time series into uniform bins for offline RL reduces performance by up to 60% and causes retrospective evaluations to overestimate returns by 1.5-3x versus unprocessed data.
-
Online Irregular Multivariate Time Series Forecasting via Uncertainty-Driven Dual-Expert Calibration
Under-Cali is an uncertainty-driven dual-expert calibration framework for online adaptation in irregular multivariate time series forecasting that freezes the base model.
-
ReTAMamba: Reliability-Aware Temporal Aggregation with Mamba for Irregular Clinical Time Series Prediction
ReTAMamba adds reliability decay modeling and chronological weaving to Mamba for irregular clinical time series and reports 7.5-10% relative AUPRC gains on MIMIC-IV, eICU, and PhysioNet 2012.
-
Attention-based graph neural networks: a survey
The survey groups attention-based GNNs into three stages—graph recurrent attention networks, graph attention networks, and graph transformers—while reviewing architectures and future directions.
-
To Use AI as Dice of Possibilities with Timing Computation
A timing-aware possibility-space framework is claimed to enable automatic trajectory discovery and counterfactual timing deduction on 3,276 breast-cancer EHR patients.
-
To Use AI as Dice of Possibilities with Timing Computation
Proposes verb-based paradigm with timing computation to enable data-driven discovery of patient trajectories and counterfactual timing from EHR data without domain knowledge.
-
To Use AI as Dice of Possibilities with Timing Computation
The paper defines possibility space, timing computation, and causal factum to make timing a computable variable, and illustrates the framework with automatic trajectory discovery and counterfactual timing on 3,276 bre...
-
Beyond the Final Label: Exploiting the Untapped Potential of Classification Histories in Astronomical Light Curve Analysis
An RNN-plus-attention model that ingests classification histories outperforms standard final-label classifiers on ELAsTiCC synthetic data and is accompanied by new Wasserstein-based metrics for temporal stability and ...
-
DBGL: Decay-aware Bipartite Graph Learning for Irregular Medical Time Series Classification
DBGL models irregular medical time series via patient-variable bipartite graphs and node-specific temporal decay encoding to avoid artificial alignment and capture decay rates, outperforming baselines on four public datasets.
-
Perforated Neural Networks for Keyword Spotting
Dendritic models using Perforated Backpropagation reach 0.933 test accuracy with 1500 parameters on keyword spotting, beating a baseline of 0.921 accuracy that needs roughly 4000 parameters.
-
Transformer autoencoder with local attention for sparse and irregular time series with application on risk estimation
A transformer autoencoder with local attention learns discriminative latent features from sparse irregular time series, yielding more consistent risk estimates for electricity theft than standard methods.
-
To Use AI as Dice of Possibilities with Timing Computation
Proposes possibility space, timing computation, and causal factum as a new framework for data-driven trajectory discovery and counterfactual timing deduction on EHR data from 3,276 breast cancer patients.
Discussion (0). Sign in to comment.