DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization

TL;DR

DIVERSIFY is a novel framework that enhances time series out-of-distribution detection and generalization by exploiting subdomains and adversarial training to handle non-stationary data.

Contribution

It introduces DIVERSIFY, a general iterative framework that improves OOD detection and generalization in time series by reducing distribution gaps through adversarial learning.

Findings

Outperforms existing methods on seven diverse datasets.

Learns more generalized features for dynamic time series.

Effectively handles non-stationary distribution shifts.

Abstract

Time series remains one of the most challenging modalities in machine learning research. The out-of-distribution (OOD) detection and generalization on time series tend to suffer due to its non-stationary property, i.e., the distribution changes over time. The dynamic distributions inside time series pose great challenges to existing algorithms to identify invariant distributions since they mainly focus on the scenario where the domain information is given as prior knowledge. In this paper, we attempt to exploit subdomains within a whole dataset to counteract issues induced by non-stationary for generalized representation learning. We propose DIVERSIFY, a general framework, for OOD detection and generalization on dynamic distributions of time series. DIVERSIFY takes an iterative process: it first obtains the "worst-case" latent distribution scenario via adversarial training, then reduces the gap between these latent distributions. We implement DIVERSIFY via combining existing OOD detection methods according to either extracted features or outputs of models for detection while we also directly utilize outputs for classification. In addition, theoretical insights illustrate that DIVERSIFY is theoretically supported. Extensive experiments are conducted on seven datasets with different OOD settings across gesture recognition, speech commands recognition, wearable stress and affect detection, and sensor-based human activity recognition. Qualitative and quantitative results demonstrate that DIVERSIFY learns more generalized features and significantly outperforms other baselines.