A Supervised Low-Rank Method for Learning Invariant Subspaces

Siyahjani, Farzad; Almohsen, Ranya; Sabri, Sinan; Doretto, Gianfranco

doi:10.1109/iccv.2015.480

Cited by 8 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As far as we are concerned, this strategy has only been performed in centralized settings. Nonetheless, in a decentralized setting each participant could Changes in the input space through clients Domain transformation Domains with particular features [62,63,64] Domain factorization [65,66,67,68] Personalization [36,37,38,39,45,56] Domain adaptation [69,70,71] Dissimilarity methods [72,73,74,75] Sample reweighting [76,77] Generative adversarial networks [78,79,80,81,82] Figure 1: Classification of the different approaches that are able to solve the problem of spatial heterogeneity in the input spaces.…”

Section: Changes In the Input Space Throughout Clientsmentioning

confidence: 99%

“…For instance, [62,63,64] consider each domain may have its own set of features to characterize the samples, causing incompatibilities across domains, and they develop methods to extract a common feature representation. A different approach, performed in [65,66,67,68], consists of constructing a factorization of the feature space with some properties. [65,66] split the feature space into two orthogonal subspaces: one of them contains the domain variations, whereas the other one keeps the common parts, and both are used separately to perform learning.…”

Section: Changes In the Input Space Throughout Clientsmentioning

confidence: 99%

See 1 more Smart Citation

Non-IID data and Continual Learning processes in Federated Learning: A long road ahead

Criado¹,

Casado²,

Iglesias³

et al. 2021

Preprint

View full text Add to dashboard Cite

Federated Learning is a novel framework that allows multiple devices or institutions to train a machine learning model collaboratively while preserving their data private. This decentralized approach is prone to suffer the consequences of data statistical heterogeneity, both across the different entities and over time, which may lead to a lack of convergence. To avoid such issues, different methods have been proposed in the past few years. However, data may be heterogeneous in lots of different ways, and current proposals do not always determine the kind of heterogeneity they are considering. In this work, we formally classify data statistical heterogeneity and review the most remarkable learning strategies that are able to face it. At the same time, we introduce approaches from other machine learning frameworks, such as Continual Learning, that also deal with data heterogeneity and could be easily adapted to the Federated Learning settings.

show abstract

Section: Changes In the Input Space Throughout Clientsmentioning

confidence: 99%

Section: Changes In the Input Space Throughout Clientsmentioning

confidence: 99%

Non-IID data and Continual Learning processes in Federated Learning: A long road ahead

Criado¹,

Casado²,

Iglesias³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…[60,17,18,59,40]) used a learned similarity measure together with nearest neighbors classifier. [48,46,10,44,9] propose methods in which features are learned along with the metric learning. Chechik et al [9] uses similarity measure in large-scale image search.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Domain Adaptation with Similarity Learning

Pinheiro¹

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

246

131

View full text Add to dashboard Cite

The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to domain adaptation consist of two steps: (i) learn features that preserve a low risk on labeled samples (source domain) and (ii) make the features from both domains to be as indistinguishable as possible, so that a classifier trained on the source can also be applied on the target domain. In general, the classifiers in step (i) consist of fully-connected layers applied directly on the indistinguishable features learned in (ii). In this paper, we propose a different way to do the classification, using similarity learning. The proposed method learns a pairwise similarity function in which classification can be performed by computing similarity between prototype representations of each category. The domain-invariant features and the categorical prototype representations are learned jointly and in an end-to-end fashion. At inference time, images from the target domain are compared to the prototypes and the label associated with the one that best matches the image is outputed. The approach is simple, scalable and effective. We show that our model achieves state-of-the-art performance in different unsupervised domain adaptation scenarios.

show abstract

“…Siyahjani et al [35] introduce the invariant components to the sparse representation and low-rank matrix decomposition approaches and successfully apply to solve computer vision problems. They add orthogonal constraint to assume that invariant and variant components are linear independent.…”

Section: Low-rank Matrix Decompositionmentioning

confidence: 99%

Low-Rank Linear Dynamical Systems for Motor Imagery EEG

Zhang

Sun

Tan

et al. 2016

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The common spatial pattern (CSP) and other spatiospectral feature extraction methods have become the most effective and successful approaches to solve the problem of motor imagery electroencephalography (MI-EEG) pattern recognition from multichannel neural activity in recent years. However, these methods need a lot of preprocessing and postprocessing such as filtering, demean, and spatiospectral feature fusion, which influence the classification accuracy easily. In this paper, we utilize linear dynamical systems (LDSs) for EEG signals feature extraction and classification. LDSs model has lots of advantages such as simultaneous spatial and temporal feature matrix generation, free of preprocessing or postprocessing, and low cost. Furthermore, a low-rank matrix decomposition approach is introduced to get rid of noise and resting state component in order to improve the robustness of the system. Then, we propose a low-rank LDSs algorithm to decompose feature subspace of LDSs on finite Grassmannian and obtain a better performance. Extensive experiments are carried out on public dataset from “BCI Competition III Dataset IVa” and “BCI Competition IV Database 2a.” The results show that our proposed three methods yield higher accuracies compared with prevailing approaches such as CSP and CSSP.

show abstract

A Supervised Low-Rank Method for Learning Invariant Subspaces

Cited by 8 publications

References 37 publications

Non-IID data and Continual Learning processes in Federated Learning: A long road ahead

Non-IID data and Continual Learning processes in Federated Learning: A long road ahead

Unsupervised Domain Adaptation with Similarity Learning

Low-Rank Linear Dynamical Systems for Motor Imagery EEG

Contact Info

Product

Resources

About