Skip to yearly menu bar Skip to main content


Poster
in
Workshop: UniReps: Unifying Representations in Neural Models

DisCoV: Disentangling Time Series Representations via Contrastive based $l$-Variational Inference

Khalid OUBLAL · Said Ladjal · David Benhaiem · Emmanuel LE BORGNE · Fran├žois Roueff

[ ] [ Project Page ]
 
presentation: UniReps: Unifying Representations in Neural Models
Fri 15 Dec 6:15 a.m. PST — 3:15 p.m. PST

Abstract: Learning disentangled representations is crucial for Time Series, offering benefits like feature derivation and improved interpretability, thereby enhancing task performance. We focus on disentangled representation learning for home appliance electricity usage, enabling users to understand and optimize their consumption for a reduced carbon footprint. Our approach frames the problem as disentangling each attribute's role in total consumption (e.g., dishwashers, fridges, \dots). Unlike existing methods assuming attribute independence, we acknowledge real-world time series attribute correlations, like the operating of dishwashers and washing machines during the winter season. To tackle this, we employ weakly supervised contrastive disentanglement, facilitating representation generalization across diverse correlated scenarios and new households. Our method utilizes innovative $l$-variational inference layers with self-attention, effectively addressing temporal dependencies across bottom-up and top-down networks. We find that DisCoV (Disentangling via Contrastive $l$-Variational) can enhance the task of reconstructing electricity consumption for individual appliances. We introduce TDS (Time Disentangling Score) to gauge disentanglement quality. TDS reliably reflects disentanglement performance, making it a valuable metric for evaluating time series representations. Code available at https://anonymous.4open.science/r/DisCo.

Chat is not available.