1
|
Wu H, Xie Q, Yu Z, Zhang J, Liu S, Long J. Unsupervised heterogeneous domain adaptation for EEG classification. J Neural Eng 2024; 21:046018. [PMID: 38968936 DOI: 10.1088/1741-2552/ad5fbd] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2023] [Accepted: 07/04/2024] [Indexed: 07/07/2024]
Abstract
Objective.Domain adaptation has been recognized as a potent solution to the challenge of limited training data for electroencephalography (EEG) classification tasks. Existing studies primarily focus on homogeneous environments, however, the heterogeneous properties of EEG data arising from device diversity cannot be overlooked. This motivates the development of heterogeneous domain adaptation methods that can fully exploit the knowledge from an auxiliary heterogeneous domain for EEG classification.Approach.In this article, we propose a novel model named informative representation fusion (IRF) to tackle the problem of unsupervised heterogeneous domain adaptation in the context of EEG data. In IRF, we consider different perspectives of data, i.e. independent identically distributed (iid) and non-iid, to learn different representations. Specifically, from the non-iid perspective, IRF models high-order correlations among data by hypergraphs and develops hypergraph encoders to obtain data representations of each domain. From the non-iid perspective, by applying multi-layer perceptron networks to the source and target domain data, we achieve another type of representation for both domains. Subsequently, an attention mechanism is used to fuse these two types of representations to yield informative features. To learn transferable representations, the maximum mean discrepancy is utilized to align the distributions of the source and target domains based on the fused features.Main results.Experimental results on several real-world datasets demonstrate the effectiveness of the proposed model.Significance.This article handles an EEG classification situation where the source and target EEG data lie in different spaces, and what's more, under an unsupervised learning setting. This situation is practical in the real world but barely studied in the literature. The proposed model achieves high classification accuracy, and this study is important for the commercial applications of EEG-based BCIs.
Collapse
Affiliation(s)
- Hanrui Wu
- College of Information Science and Technology, Jinan University, Guangzhou 510006, People's Republic of China
| | - Qinmei Xie
- College of Information Science and Technology, Jinan University, Guangzhou 510006, People's Republic of China
| | - Zhuliang Yu
- School of Automation Science and Engineering, South China University of Technology, Guangzhou 510006, People's Republic of China
| | - Jia Zhang
- College of Information Science and Technology, Jinan University, Guangzhou 510006, People's Republic of China
| | - Siwei Liu
- College of Information Science and Technology, Jinan University, Guangzhou 510006, People's Republic of China
| | - Jinyi Long
- College of Information Science and Technology, Jinan University, Guangzhou 510006, People's Republic of China
- Guangdong Key Laboratory of Traditional Chinese Medicine Information Technology, Guangzhou 510632, People's Republic of China
| |
Collapse
|
2
|
Zhang F, Wu H, Guo Y. Semi-supervised multi-source transfer learning for cross-subject EEG motor imagery classification. Med Biol Eng Comput 2024; 62:1655-1672. [PMID: 38324109 DOI: 10.1007/s11517-024-03032-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2023] [Accepted: 12/27/2023] [Indexed: 02/08/2024]
Abstract
Electroencephalogram (EEG) motor imagery (MI) classification refers to the use of EEG signals to identify and classify subjects' motor imagery activities; this task has received increasing attention with the development of brain-computer interfaces (BCIs). However, the collection of EEG data is usually time-consuming and labor-intensive, which makes it difficult to obtain sufficient labeled data from the new subject to train a new model. Moreover, the EEG signals of different individuals exhibit significant differences, leading to a significant drop in the performance of a model trained on the existing subjects when directly classifying EEG signals acquired from new subjects. Therefore, it is crucial to make full use of the EEG data of the existing subjects and the unlabeled EEG data of the new target subject to improve the MI classification performance achieved for the target subject. This research study proposes a semi-supervised multi-source transfer (SSMT) learning model to address the above problems; the model learns informative and domain-invariant representations to address cross-subject MI-EEG classification tasks. In particular, a dynamic transferred weighting schema is presented to obtain the final predictions by integrating the weighted features derived from multi-source domains. The average accuracies achieved on two publicly available EEG datasets reach 83.57 % and 85.09 % , respectively, validating the effectiveness of the SSMT process. The SSMT process reveals the importance of informative and domain-invariant representations in MI classification tasks, as they make full use of the domain-invariant information acquired from each subject.
Collapse
Affiliation(s)
| | - Hanliang Wu
- Liwan District People's Hospital of Guangzhou, Guangzhou, China.
| | - Yuxin Guo
- Guangzhou Institute of Science and Technology, Guangzhou, China
| |
Collapse
|
3
|
Learning cross-domain representations by vision transformer for unsupervised domain adaptation. Neural Comput Appl 2023. [DOI: 10.1007/s00521-023-08269-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/27/2023]
|
4
|
Ma N, Wang H, Zhang Z, Zhou S, Chen H, Bu J. Source-free semi-supervised domain adaptation via progressive Mixup. Knowl Based Syst 2022. [DOI: 10.1016/j.knosys.2022.110208] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/01/2023]
|
5
|
Unsupervised domain adaptation via discriminative feature learning and classifier adaptation from center-based distances. Knowl Based Syst 2022. [DOI: 10.1016/j.knosys.2022.109022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
|
6
|
Class-rebalanced wasserstein distance for multi-source domain adaptation. APPL INTELL 2022. [DOI: 10.1007/s10489-022-03810-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
7
|
Wu H, Long J, Li N, Yu D, Ng MK. Adversarial Auto-encoder Domain Adaptation for Cold-start Recommendation with Positive and Negative Hypergraphs. ACM T INFORM SYST 2022. [DOI: 10.1145/3544105] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/01/2022]
Abstract
This paper presents a novel model named Adversarial Auto-encoder Domain Adaptation (AADA) to handle the recommendation problem under cold-start settings. Specifically, we divide the hypergraph into two hypergraphs, i.e., a positive hypergraph and a negative one. Below, we adopt the cold-start user recommendation for illustration. After achieving positive and negative hypergraphs, we apply hypergraph auto-encoders to them to obtain positive and negative embeddings of warm users and items. Additionally, we employ a multi-layer perceptron to get warm and cold-start user embeddings called regular embeddings. Subsequently, for warm users, we assign positive and negative pseudo-labels to their positive and negative embeddings, respectively, and treat their positive and regular embeddings as the source and target domain data, respectively. Then, we develop a matching discriminator to jointly minimize the classification loss of the positive and negative warm user embeddings and the distribution gap between the positive and regular warm user embeddings. In this way, warm users’ positive and regular embeddings are connected. Since the positive hypergraph maintains the relations between positive warm user and item embeddings, and the regular warm and cold-start user embeddings follow a similar distribution, the regular cold-start user embedding and positive item embedding are bridged to discover their relationship. The proposed model can be easily extended to handle the cold-start item recommendation by changing inputs. We perform extensive experiments on real-world datasets for both cold-start user and cold-start item recommendations. Promising results in terms of precision, recall, NDCG, and hit rate verify the effectiveness of the proposed method.
Collapse
Affiliation(s)
- Hanrui Wu
- College of Information Science and Technology, Jinan University, China
| | - Jinyi Long
- College of Information Science and Technology, Guangdong Key Lab of Traditional Chinese Medicine Information Technology, Jinan University, Pazhou Lab, China
| | - Nuosi Li
- College of Information Science and Technology, Jinan University, China
| | - Dahai Yu
- TCL Corporate Research Hong Kong, China
| | - Michael K. Ng
- Institute of Data Science and Department of Mathematics, The University of Hong Kong, China
| |
Collapse
|
8
|
A lattice LSTM-based framework for knowledge graph construction from power plants maintenance reports. SERVICE ORIENTED COMPUTING AND APPLICATIONS 2022. [DOI: 10.1007/s11761-022-00338-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
9
|
Joint bi-adversarial learning for unsupervised domain adaptation. Knowl Based Syst 2022. [DOI: 10.1016/j.knosys.2022.108903] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
|
10
|
Wang S, Zhang L, Chen W, Wang F, Li H. Refining pseudo labels for unsupervised Domain Adaptive Re-Identification. Knowl Based Syst 2022. [DOI: 10.1016/j.knosys.2022.108336] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
11
|
Chen C, Vong CM, Wang S, Wang H, Pang M. Easy Domain Adaptation for cross-subject multi-view emotion recognition. Knowl Based Syst 2022. [DOI: 10.1016/j.knosys.2021.107982] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
12
|
Transfer learning for regression via latent variable represented conditional distribution alignment. Knowl Based Syst 2022. [DOI: 10.1016/j.knosys.2021.108110] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
|
13
|
Guo LL, Pfohl SR, Fries J, Johnson AEW, Posada J, Aftandilian C, Shah N, Sung L. Evaluation of domain generalization and adaptation on improving model robustness to temporal dataset shift in clinical medicine. Sci Rep 2022; 12:2726. [PMID: 35177653 PMCID: PMC8854561 DOI: 10.1038/s41598-022-06484-1] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2021] [Accepted: 01/31/2022] [Indexed: 11/24/2022] Open
Abstract
Temporal dataset shift associated with changes in healthcare over time is a barrier to deploying machine learning-based clinical decision support systems. Algorithms that learn robust models by estimating invariant properties across time periods for domain generalization (DG) and unsupervised domain adaptation (UDA) might be suitable to proactively mitigate dataset shift. The objective was to characterize the impact of temporal dataset shift on clinical prediction models and benchmark DG and UDA algorithms on improving model robustness. In this cohort study, intensive care unit patients from the MIMIC-IV database were categorized by year groups (2008-2010, 2011-2013, 2014-2016 and 2017-2019). Tasks were predicting mortality, long length of stay, sepsis and invasive ventilation. Feedforward neural networks were used as prediction models. The baseline experiment trained models using empirical risk minimization (ERM) on 2008-2010 (ERM[08-10]) and evaluated them on subsequent year groups. DG experiment trained models using algorithms that estimated invariant properties using 2008-2016 and evaluated them on 2017-2019. UDA experiment leveraged unlabelled samples from 2017 to 2019 for unsupervised distribution matching. DG and UDA models were compared to ERM[08-16] models trained using 2008-2016. Main performance measures were area-under-the-receiver-operating-characteristic curve (AUROC), area-under-the-precision-recall curve and absolute calibration error. Threshold-based metrics including false-positives and false-negatives were used to assess the clinical impact of temporal dataset shift and its mitigation strategies. In the baseline experiments, dataset shift was most evident for sepsis prediction (maximum AUROC drop, 0.090; 95% confidence interval (CI), 0.080-0.101). Considering a scenario of 100 consecutively admitted patients showed that ERM[08-10] applied to 2017-2019 was associated with one additional false-negative among 11 patients with sepsis, when compared to the model applied to 2008-2010. When compared with ERM[08-16], DG and UDA experiments failed to produce more robust models (range of AUROC difference, - 0.003 to 0.050). In conclusion, DG and UDA failed to produce more robust models compared to ERM in the setting of temporal dataset shift. Alternate approaches are required to preserve model performance over time in clinical medicine.
Collapse
Affiliation(s)
- Lin Lawrence Guo
- Program in Child Health Evaluative Sciences, The Hospital for Sick Children, Toronto, ON, Canada
| | - Stephen R Pfohl
- Biomedical Informatics Research, Stanford University, Palo Alto, USA
| | - Jason Fries
- Biomedical Informatics Research, Stanford University, Palo Alto, USA
| | - Alistair E W Johnson
- Program in Child Health Evaluative Sciences, The Hospital for Sick Children, Toronto, ON, Canada
| | - Jose Posada
- Biomedical Informatics Research, Stanford University, Palo Alto, USA
| | | | - Nigam Shah
- Biomedical Informatics Research, Stanford University, Palo Alto, USA
| | - Lillian Sung
- Program in Child Health Evaluative Sciences, The Hospital for Sick Children, Toronto, ON, Canada.
- Division of Haematology/Oncology, The Hospital for Sick Children, 555 University Avenue, Toronto, ON, M5G1X8, Canada.
| |
Collapse
|
14
|
Wu H, Wu Q, Ng MK. Knowledge Preserving and Distribution Alignment for Heterogeneous Domain Adaptation. ACM T INFORM SYST 2022. [DOI: 10.1145/3469856] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/01/2022]
Abstract
Domain adaptation aims at improving the performance of learning tasks in a target domain by leveraging the knowledge extracted from a source domain. To this end, one can perform knowledge transfer between these two domains. However, this problem becomes extremely challenging when the data of these two domains are characterized by different types of features, i.e., the feature spaces of the source and target domains are different, which is referred to as heterogeneous domain adaptation (HDA). To solve this problem, we propose a novel model called Knowledge Preserving and Distribution Alignment (KPDA), which learns an augmented target space by jointly minimizing information loss and maximizing domain distribution alignment. Specifically, we seek to discover a latent space, where the knowledge is preserved by exploiting the Laplacian graph terms and reconstruction regularizations. Moreover, we adopt the Maximum Mean Discrepancy to align the distributions of the source and target domains in the latent space. Mathematically, KPDA is formulated as a minimization problem with orthogonal constraints, which involves two projection variables. Then, we develop an algorithm based on the Gauss–Seidel iteration scheme and split the problem into two subproblems, which are solved by searching algorithms based on the Barzilai–Borwein (BB) stepsize. Promising results demonstrate the effectiveness of the proposed method.
Collapse
Affiliation(s)
- Hanrui Wu
- The University of Hong Kong, Hong Kong, China
| | - Qingyao Wu
- South China University of Technology, Key Laboratory of Big Data and Intelligent Robot, Ministry of Education, Pazhou Lab, Guangzhou, China
| | | |
Collapse
|
15
|
|
16
|
Discriminative information preservation: A general framework for unsupervised visual Domain Adaptation. Knowl Based Syst 2021. [DOI: 10.1016/j.knosys.2021.107158] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
|
17
|
Wu H, Zhu H, Yan Y, Wu J, Zhang Y, Ng MK. Heterogeneous Domain Adaptation by Information Capturing and Distribution Matching. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2021; 30:6364-6376. [PMID: 34236965 DOI: 10.1109/tip.2021.3094137] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
Heterogeneous domain adaptation (HDA) is a challenging problem because of the different feature representations in the source and target domains. Most HDA methods search for mapping matrices from the source and target domains to discover latent features for learning. However, these methods barely consider the reconstruction error to measure the information loss during the mapping procedure. In this paper, we propose to jointly capture the information and match the source and target domain distributions in the latent feature space. In the learning model, we propose to minimize the reconstruction loss between the original and reconstructed representations to preserve information during transformation and reduce the Maximum Mean Discrepancy between the source and target domains to align their distributions. The resulting minimization problem involves two projection variables with orthogonal constraints that can be solved by the generalized gradient flow method, which can preserve orthogonal constraints in the computational procedure. We conduct extensive experiments on several image classification datasets to demonstrate that the effectiveness and efficiency of the proposed method are better than those of state-of-the-art HDA methods.
Collapse
|
18
|
|
19
|
|