Micro-Supervised Disturbance Learning: A Perspective of Representation Probability Distribution

Chu, Jielei; Liu, Jing; Wang, Hongjun; Meng, Hua; Gong, Zhiguo; Li, Tianrui

doi:10.1109/tpami.2022.3225461

Cited by 10 publications

(3 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The continuous growth of such data presents unparalleled challenges to the field of clustering research. Unlike static data, the characteristics of time series data are characterized by inherent multi-scale temporal dependencies that reflect the data’s dynamic changes, including both long-term and short-term pattern variations [ 5 , 6 ]. This unique temporal characteristic renders most traditional clustering algorithms unsuitable for time series data, as they often fail to capture the dynamic essence of such data.…”

Section: Introductionmentioning

confidence: 99%

Research on load clustering algorithm based on variational autoencoder and hierarchical clustering

Cai,

Zheng,

Peng

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Time series data complexity presents new challenges in clustering analysis across fields such as electricity, energy, industry, and finance. Despite advances in representation learning and clustering with Variational Autoencoders (VAE) based deep learning techniques, issues like the absence of discriminative power in feature representation, the disconnect between instance reconstruction and clustering objectives, and scalability challenges with large datasets persist. This paper introduces a novel deep time series clustering approach integrating VAE with metric learning. It leverages a VAE based on Gated Recurrent Units for temporal feature extraction, incorporates metric learning for joint optimization of latent space representation, and employs the sum of log likelihoods as the clustering merging criterion, markedly improving clustering accuracy and interpretability. Experimental findings demonstrate a 27.16% improvement in average clustering accuracy and a 47.15% increase in speed on industrial load data. This study offers novel insights and tools for the thorough analysis and application of time series data, with further exploration of VAE’s potential in time series clustering anticipated in future research.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on load clustering algorithm based on variational autoencoder and hierarchical clustering

Cai,

Zheng,

Peng

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning has experienced rapid advancements, leading to the widespread utilization of deep neural networks [1][2] across various domains. Deep neural networks typically exhibit a hierarchical structure with numerous parameters, necessitating a substantial amount of data for training and parameter adjustment.…”

Section: Introductionmentioning

confidence: 99%

“…However, in many practical application scenarios, it is often difficult for people to obtain enough data to support the training of deep learning models. Few-shot learning, on the other hand, has shown promising results with only a small number of samples [1] . Hence, it is crucial to investigate few-shot learning methods that offer high accuracy and superior generalization performance, particularly in scenarios where abundant training data is inaccessible.…”

Section: Introductionmentioning

confidence: 99%