Explainable Multivariate Time Series Classification: A Deep Neural Network Which Learns To Attend To Important Variables As Well As Informative Time Intervals (2020-11-23T00:00:00.000000Z)

TL;DR

A novel, modular, convolution-based feature extraction and attention mechanism that simultaneously identifies the variables as well as time intervals which determine the classifier output on multi-variate time series classification task.

Abstract

Time series data is prevalent in a wide variety of real-world applications and it calls for trustworthy and explainable models for people to understand and fully trust decisions made by AI solutions. We consider the problem of building explainable classifiers from multi-variate time series data. A key criterion to understand such predictive models involves elucidating and quantifying the contribution of time varying input variables to the classification. Hence, we introduce a novel, modular, convolution-based feature extraction and attention mechanism that simultaneously identifies the variables as well as time intervals which determine the classifier output. We present results of extensive experiments with several benchmark data sets that show that the proposed method outperforms the state-of-the-art baseline methods on multi-variate time series classification task. The results of our case studies demonstrate that the variables and time intervals identified by the proposed method make sense relative to available domain knowledge.

Authors

Suhang Wang

4 papers

Tsung-Yu Hsieh

1 papers

Yiwei Sun

1 papers

TL;DR

Abstract

Authors

References76 items

A Causal Lens for Peeking into Black Box Predictive Models: Predictive Model Interpretation via Causal Attribution

Attention based Multi-Modal New Product Sales Time-series Forecasting

An Ontology-Aware Framework for Audio Event Classification

Ginger Cannot Cure Cancer: Battling Fake Health News with a Comprehensive Data Repository

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values

LMLFM: Longitudinal Multi-Level Factorization Machine

Adaptive Structural Co-regularization for Unsupervised Multi-view Feature Selection

Explainable machine learning in deployment

Transferring Robustness for Graph Neural Network Against Poisoning Attacks

MEGAN: A Generative Adversarial Network for Multi-View Network Embedding

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting

Exploring Interpretable LSTM Neural Networks over Multi-Variable Data

MetaPred: Meta-Learning for Clinical Risk Prediction with Limited Patient Electronic Health Records

Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI

Unsupervised Scalable Representation Learning for Multivariate Time Series

Improving Image Captioning by Leveraging Knowledge Graphs

Multi-view Network Embedding via Graph Factorization Clustering and Co-regularized Multi-view Agreement

MuVAN: A Multi-view Attention Network for Multivariate Temporal Data

INVASE: Instance-wise Variable Selection using Neural Networks

Deep learning for time series classification: a review

RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data

A review on distance based time series classification

Learning to Explain: An Information-Theoretic Perspective on Model Interpretation

A Survey of Methods for Explaining Black Box Models

Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs

Distilling a Neural Network Into a Soft Decision Tree

A Unified Approach to Interpreting Model Predictions

On Human Motion Prediction Using Recurrent Neural Networks

Learning Important Features Through Propagating Activation Differences

A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction

The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

WaveNet: A Generative Model for Raw Audio

RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism

Not Just a Black Box: Learning Important Features Through Propagating Activation Differences

“Why Should I Trust You?”: Explaining the Predictions of Any Classifier

Learning to Diagnose with LSTM Recurrent Neural Networks

Assessing Beijing's PM2.5 pollution: severity, weather impact, APEC and winter heating

Understanding Neural Networks Through Deep Visualization

Adam: A Method for Stochastic Optimization

On the Properties of Neural Machine Translation: Encoder–Decoder Approaches

Neural Machine Translation by Jointly Learning to Align and Translate

Highly Comparative Feature-Based Time-Series Classification

Visualizing and Understanding Convolutional Networks

Feature selection techniques with class separability for multivariate time series

Dynamic Covariance Models for Multivariate Financial Time Series

Fine-Grained Photovoltaic Output Prediction Using a Bayesian Ensemble

The motor cortex drives the muscles during walking in human subjects

Time series shapelets: a new primitive for data mining

The Role of Particle Composition on the Association Between PM2.5 and Mortality

Sensor-Based Abnormal Human-Activity Detection

Information retrieval for music and motion

Modeling changing dependency structure in multivariate time series

Feature Subset Selection on Multivariate Time Series with Extremely Large Spatial Features

Applied Longitudinal Analysis

The Elements of Statistical Learning: Data Mining, Inference, and Prediction

BCI2000: a general-purpose brain-computer interface (BCI) system

The Elements of Statistical Learning

Wavelet Methods for Time Series Analysis

Airborne particles are a risk factor for hospital admissions for heart and lung disease.

Wavelet Methods for Time Series Analysis

Long Short-Term Memory

Synchronization between motor cortex and spinal motoneuronal pool during the performance of a maintained motor task in man.

Shared neural substrates controlling hand movements in human motor cortex.

Using Dynamic Time Warping to Find Patterns in Time Series

Fourier Analysis of Time Series: An Introduction

Deep Learning

Effect of Meteorological Factors on PM2.5 during July to September of Beijing

Application of machine learning to epileptic seizure onset detection and treatment

Seizures in Children: Laboratory

The Elements of Statistical Learning: Data Mining, Inference, and Prediction

Physionet: components of a new research resource for complex physiologic signals

Dynamic Time Warping

WSDM ’21, March 08-12, 2021