Multi-Adversarial Domain Adaptation

Pei, Zhongyi; Cao, Zhangjie; Long, Mingsheng; Wang, Jianmin

doi:10.1609/aaai.v32i1.11767

Cited by 602 publications

(113 citation statements)

References 15 publications

Supporting

Mentioning

113

Contrasting

Order By: Relevance

“…For deep learning methods EEGNet, AConvNet, FConvNet, DLSVM, and NRDNN, the batch size and epoch were set to 40 and 1,000, respectively. The learning rate was dynamically changed during optimization using the formula as follows (Pei et al, 2018 ):

, in which p linearly changes from 0 to 1, η 0 = 1 e − 3, α = 10, and β = 0.75. Besides, the parameter r is set to 2 in the region-attention network.…”

Section: Methodsmentioning

confidence: 99%

Nuclear Norm Regularized Deep Neural Network for EEG-Based Emotion Recognition

Liang

Yin²,

Huang³

et al. 2022

Front. Psychol.

View full text Add to dashboard Cite

Electroencephalography (EEG) based emotion recognition enables machines to perceive users' affective states, which has attracted increasing attention. However, most of the current emotion recognition methods neglect the structural information among different brain regions, which can lead to the incorrect learning of high-level EEG feature representation. To mitigate possible performance degradation, we propose a novel nuclear norm regularized deep neural network framework (NRDNN) that can capture the structural information among different brain regions in EEG decoding. The proposed NRDNN first utilizes deep neural networks to learn high-level feature representations of multiple brain regions, respectively. Then, a set of weights indicating the contributions of each brain region can be automatically learned using a region-attention layer. Subsequently, the weighted feature representations of multiple brain regions are stacked into a feature matrix, and the nuclear norm regularization is adopted to learn the structural information within the feature matrix. The proposed NRDNN method can learn the high-level representations of EEG signals within multiple brain regions, and the contributions of them can be automatically adjusted by assigning a set of weights. Besides, the structural information among multiple brain regions can be captured in the learning procedure. Finally, the proposed NRDNN can perform in an efficient end-to-end manner. We conducted extensive experiments on publicly available emotion EEG dataset to evaluate the effectiveness of the proposed NRDNN. Experimental results demonstrated that the proposed NRDNN can achieve state-of-the-art performance by leveraging the structural information.

show abstract

, in which p linearly changes from 0 to 1, η 0 = 1 e − 3, α = 10, and β = 0.75. Besides, the parameter r is set to 2 in the region-attention network.…”

Section: Methodsmentioning

confidence: 99%

Nuclear Norm Regularized Deep Neural Network for EEG-Based Emotion Recognition

Liang

Yin²,

Huang³

et al. 2022

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…Other non-federated learning works also employ multiple generators or discriminators to improve learning stability (Hoang et al 2018;Durugkar, Gemp, and Mahadevan 2016) or prevent mode collapse (Ghosh et al 2018). Pei et al (2018) proposed multi-class discriminators structure, which is used to improve the classification performance cross multiple domains. Liu and Tuzel (2016) proposed to learn the joint distribution of multi-domain images by using multiple pairs of GANs.…”

Section: Related Workmentioning

confidence: 99%

Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models

Chen

Bose

Cheng

et al. 2022

AAAI

View full text Add to dashboard Cite

Realistic fine-grained multi-agent simulation of real-world complex systems is crucial for many downstream tasks such as reinforcement learning. Recent work has used generative models (GANs in particular) for providing high-fidelity simulation of real-world systems. However, such generative models are often monolithic and miss out on modeling the interaction in multi-agent systems. In this work, we take a first step towards building multiple interacting generative models (GANs) that reflects the interaction in real world. We build and analyze a hierarchical set-up where a higher-level GAN is conditioned on the output of multiple lower-level GANs. We present a technique of using feedback from the higher-level GAN to improve performance of lower-level GANs. We mathematically characterize the conditions under which our technique is impactful, including understanding the transfer learning nature of our set-up. We present three distinct experiments on synthetic data, time series data, and image domain, revealing the wide applicability of our technique.

show abstract

“…Competitive baselines: We not only explore the state-of-theart domain adaptation methods including DAN (Long et al 2015), JAN (Long et al 2017), MADA (Pei et al 2018) 2020), DADA (Tang, Chen, and Jia 2020) but also combine network backbones (CDAN and DANN) with multi-norm strategies: BN (Long et al 2018) and TN (Wang et al 2019a) as baselines. We follow the standard protocols operated with CDAN and DANN to evaluate the effectiveness of our proposed normalization technique.…”

Section: Empirical Analysismentioning

confidence: 99%

Cross-Domain Collaborative Normalization via Structural Knowledge

Xia

Ding

2022

AAAI

View full text Add to dashboard Cite

Batch Normalization (BN) as an important component assists Deep Neural Networks in achieving promising performance for extensive learning tasks by scaling distribution of feature representations within mini-batches. However, the application of BN suffers from performance degradation under the scenario of Unsupervised Domain Adaptation (UDA), since the estimated statistics fail to concurrently describe two different domains. In this paper, we develop a novel normalization technique, named Collaborative Normalization (CoN), for eliminating domain discrepancy and accelerating the model training of neural networks for UDA. Unlike typical strategies only exploiting domain-specific statistics during normalization, our CoN excavates cross-domain knowledge and simultaneously scales features from various domains by mimicking the merits of collaborative representation. Our CoN can be easily plugged into popular neural network backbones for cross-domain learning. On the one hand, theoretical analysis guarantees that models with CoN promote discriminability of feature representations and accelerate convergence rate; on the other hand, empirical study verifies that replacing BN with CoN in popular network backbones effectively improves classification accuracy in most learning tasks across three cross-domain visual benchmarks.

show abstract

Multi-Adversarial Domain Adaptation

Cited by 602 publications

References 15 publications

Nuclear Norm Regularized Deep Neural Network for EEG-Based Emotion Recognition

Nuclear Norm Regularized Deep Neural Network for EEG-Based Emotion Recognition

Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models

Cross-Domain Collaborative Normalization via Structural Knowledge

Contact Info

Product

Resources

About