Code for "Multi-Time Attention Networks for Irregularly Sampled Time Series", ICLR 2021.

Last update: Dec 17, 2022

Overview

Multi-Time Attention Networks (mTANs)

This repository contains the PyTorch implementation for the paper Multi-Time Attention Networks for Irregularly Sampled Time Series by Satya Narayan Shukla and Benjamin M. Marlin. This work has been accepted at the International Conference on Learning Representations, 2021.

Requirements

The code requires Python 3.7 or later. The file requirements.txt contains the full list of required Python modules.

pip3 install -r requirements.txt

Training and Evaluation

Interpolation Task on Toy Dataset

python3 tan_interpolation.py --niters 5000 --lr 0.0001 --batch-size 128 --rec-hidden 32 --latent-dim 1 --length 20 --enc mtan_rnn --dec mtan_rnn --n 1000  --gen-hidden 50 --save 1 --k-iwae 5 --std 0.01 --norm --learn-emb --kl --seed 0 --num-ref-points 20 --dataset toy

Interpolation Task on PhysioNet Dataset

python3 tan_interpolation.py --niters 500 --lr 0.001 --batch-size 32 --rec-hidden 64 --latent-dim 16 --quantization 0.016  --enc mtan_rnn --dec mtan_rnn --n 8000  --gen-hidden 50 --save 1 --k-iwae 5 --std 0.01 --norm --learn-emb --kl --seed 0 --num-ref-points 64 --dataset physionet --sample-tp 0.9

Classification Task on PhysioNet Dataset (mTAND-Full)

python3 tan_classification.py --alpha 100 --niters 300 --lr 0.0001 --batch-size 50 --rec-hidden 256 --gen-hidden 50 --latent-dim 20 --enc mtan_rnn --dec mtan_rnn --n 8000 --quantization 0.016 --save 1 --classif --norm --kl --learn-emb --k-iwae 1 --dataset physionet

Classification Task on PhysioNet Dataset (mTAND-Enc)

python3 tanenc_classification.py --niters 200 --lr 0.0001 --batch-size 128 --rec-hidden 128 --enc mtan_enc --n 8000 --quantization 0.016 --save 1 --classif --num-heads 1 --learn-emb --dataset physionet --seed 0

Classification Task on MIMIC-III Dataset (mTAND-Full)

python3 tan_classification.py --alpha 5 --niters 300 --lr 0.0001 --batch-size 128 --rec-hidden 256 --gen-hidden 50 --latent-dim 128 --enc mtan_rnn --dec mtan_rnn   --save 1 --classif --norm --learn-emb --k-iwae 1 --dataset mimiciii

For MIMIC-III Dataset, first you need to have an access to the dataset which can be requested here. We follow the data extraction process described here: https://github.com/mlds-lab/interp-net.

Classification Task on MIMIC-III Dataset (mTAND-Enc)

python3 tanenc_classification.py --niters 200 --lr 0.0001 --batch-size 256 --rec-hidden 256 --enc mtan_enc  --quantization 0.016 --save 1 --classif --num-heads 1 --learn-emb --dataset mimiciii --seed 0

Classification Task on Human Activity Dataset (mTAND-Enc)

python3 tanenc_classification.py --niters 1000 --lr 0.001 --batch-size 256 --rec-hidden 512 --enc mtan_enc_activity  --quantization 0.016 --save 1 --classif --num-heads 1 --learn-emb --dataset activity --seed 0 --classify-pertp

Interpolation Results

Interpolation performance on PhysioNet with varying percent of observed time points:

Classification Results

Classification performance on PhysioNet, MIMIC-III and Human activity dataset, and time per epoch in minutes for all the methods on PhysioNet.

Reference

@inproceedings{
shukla2021multitime,
title={Multi-Time Attention Networks for Irregularly Sampled Time Series},
author={Satya Narayan Shukla and Benjamin Marlin},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=4c0J6lwQ4_}
}

Code for "Multi-Time Attention Networks for Irregularly Sampled Time Series", ICLR 2021.

Related tags

Overview

Multi-Time Attention Networks (mTANs)

Requirements

Training and Evaluation

Interpolation Results

Classification Results

Reference

Owner

The Laboratory for Robust and Efficient Machine Learning

Pipeline for employing a Lightweight deep learning models for LOW-power systems

Model parallel transformers in Jax and Haiku

Semantic Edge Detection with Diverse Deep Supervision

Preprossing-loan-data-with-NumPy - In this project, I have cleaned and pre-processed the loan data that belongs to an affiliate bank based in the United States.

MiraiML: asynchronous, autonomous and continuous Machine Learning in Python

Pytorch implementation of paper "Learning Co-segmentation by Segment Swapping for Retrieval and Discovery"

TensorRT examples (Jetson, Python/C++)(object detection)

Code for "Retrieving Black-box Optimal Images from External Databases" (WSDM 2022)

Orchestrating Distributed Materials Acceleration Platform Tutorial

Memory efficient transducer loss computation

MCMC samplers for Bayesian estimation in Python, including Metropolis-Hastings, NUTS, and Slice

PyTorch implementation of paper: HPNet: Deep Primitive Segmentation Using Hybrid Representations.

Keras Image Embeddings using Contrastive Loss

Code for paper Novel View Synthesis via Depth-guided Skip Connections

Sionna: An Open-Source Library for Next-Generation Physical Layer Research

[ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

Code for "The Box Size Confidence Bias Harms Your Object Detector"

Apache Spark - A unified analytics engine for large-scale data processing

A curated list of the top 10 computer vision papers in 2021 with video demos, articles, code and paper reference.

Generate image analogies using neural matching and blending