Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding

Deldari, Shohreh; Smith, Daniel; Xue, Hao; Salim, Flora D.

doi:10.1145/3442381.3449903

Cited by 56 publications

(28 citation statements)

References 61 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[67] applied contrastive predictive coding [105] for HAR. Similarly, [41] extended contrastive predictive coding to detect change points in multidimensional time-series data. [48] proposed a similar approach to SimCLR for time-series representation learning using a transformer by maximising context similarity between strongly and weakly augmented inputs.…”

Section: Multi-task Lossesmentioning

confidence: 99%

See 1 more Smart Citation

Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data

Deldari¹,

Xue²,

Saeed³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Recently, Self-Supervised Representation Learning (SSRL) has attracted much attention in the field of computer vision, speech, natural language processing (NLP), and recently, with other types of modalities, including time series from sensors. The popularity of self-supervised learning is driven by the fact that traditional models typically require a huge amount of well-annotated data for training. Acquiring annotated data can be a difficult and costly process. Self-supervised methods have been introduced to improve the efficiency of training data through discriminative pre-training of models using supervisory signals that have been freely obtained from the raw data. Unlike existing reviews of SSRL that have pre-dominately focused upon methods in the fields of CV or NLP for a single modality, we aim to provide the first comprehensive review of multimodal self-supervised learning methods for temporal data.To this end, we 1) provide a comprehensive categorization of existing SSRL methods, 2) introduce a generic pipeline by defining the key components of a SSRL framework, 3) compare existing models in terms of their objective function, network architecture and potential applications, and 4) review existing multimodal techniques in each category and various modalities. Finally, we present existing weaknesses and future opportunities. We believe our work develops a perspective on the requirements of SSRL in domains that utilise multimodal and/or temporal data.

show abstract

Section: Multi-task Lossesmentioning

confidence: 99%

“…In most methods, different pairs within batches are treated as negative pairs while some of them may be semantically related. This problem causes more issues in cases with a limited range of classes, such as medical applications, human activity and emotion recognition [41].…”

Section: Cross-modal Learning Categoriesmentioning

confidence: 99%

Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data

Deldari¹,

Xue²,

Saeed³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…More recently, contrastive learning based techniques are becoming popular for time series anomaly detection. For instance, self-supervised contrastive predictive coding is proposed to handle anomaly points [23]. Cho et al propose a masked contrastive method by using class-wise scale factor [24].…”

Section: Unsupervised Anomaly Detectionmentioning

confidence: 99%

Deep Federated Anomaly Detection for Multivariate Time Series Data

Zhu¹,

Song²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Despite the fact that many anomaly detection approaches have been developed for multivariate time series data, limited effort has been made on federated settings in which multivariate time series data are heterogeneously distributed among different edge devices while data sharing is prohibited. In this paper, we investigate the problem of federated unsupervised anomaly detection and present a Federated Exemplarbased Deep Neural Network (Fed-ExDNN) to conduct anomaly detection for multivariate time series data on different edge devices. Specifically, we first design an Exemplar-based Deep Neural network (ExDNN) to learn local time series representations based on their compatibility with an exemplar module which consists of hidden parameters learned to capture varieties of normal patterns on each edge device. Next, a constrained clustering mechanism (FedCC) is employed on the centralized server to align and aggregate the parameters of different local exemplar modules to obtain a unified global exemplar module. Finally, the global exemplar module is deployed together with a shared feature encoder to each edge device and anomaly detection is conducted by examining the compatibility of testing data to the exemplar module. Fed-ExDNN captures local normal time series patterns with ExDNN and aggregates these patterns by FedCC, and thus can handle the heterogeneous data distributed over different edge devices simultaneously. Thoroughly empirical studies on six public datasets show that ExDNN and Fed-ExDNN can outperform state-ofthe-art anomaly detection algorithms and federated learning techniques.

show abstract

“…More recently, Haresamudram et al [22] also proposed Contrastive Predictive Coding which leverages the long-term temporal structure of sensor data streams for self-supervised learning. SSL has also been used in the context of change point detection [11] and federated learning [47].…”

Section: Introductionmentioning

confidence: 99%

ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition

Jain¹,

Tang²,

Min³

et al. 2022

Preprint

View full text Add to dashboard Cite

A major bottleneck in training robust Human-Activity Recognition models (HAR) is the need for large-scale labeled sensor datasets. Because labeling large amounts of sensor data is an expensive task, unsupervised and semi-supervised learning techniques have emerged that can learn good features from the data without requiring any labels. In this paper, we extend this line of research and present a novel technique called Collaborative Self-Supervised Learning (ColloSSL) which leverages unlabeled data collected from multiple devices worn by a user to learn high-quality features of the data. A key insight that underpins the design of ColloSSL is that unlabeled sensor datasets simultaneously captured by multiple devices can be viewed as natural transformations of each other, and leveraged to generate a supervisory signal for representation learning. We present three technical innovations to extend conventional self-supervised learning algorithms to a multi-device setting: a Device Selection approach which selects positive and negative devices to enable contrastive learning, a Contrastive Sampling algorithm which samples positive and negative examples in a multi-device setting, and a loss function called Multi-view Contrastive Loss which extends standard contrastive loss to a multi-device setting. Our experimental results on three multi-device datasets show that ColloSSL outperforms both fully-supervised and semi-supervised learning techniques in majority of the experiment settings, resulting in an absolute increase of upto 7.9% in 𝐹 1 score compared to the best performing baselines. We also show that ColloSSL outperforms the fully-supervised methods in a low-data regime, by just using one-tenth of the available labeled data in the best case. CCS Concepts: • Computing methodologies → Unsupervised learning; • Hardware → Sensor applications and deployments; • Human-centered computing → Ubiquitous computing.

show abstract

Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding

Cited by 56 publications

References 61 publications

Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data

Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data

Deep Federated Anomaly Detection for Multivariate Time Series Data

ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition

Contact Info

Product

Resources

About