Cross Validation Framework to Choose amongst Models and Datasets for Transfer Learning

Zhong, Erheng; Wang, Fan; Yang, Qiang; Verscheure, Olivier; Ren, Jiangtao

doi:10.1007/978-3-642-15939-8_35

Cited by 116 publications

(82 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We fix λ = 1, batchsize = 32 in DAAN all the time. Other Hyperparameters are tuned via transfer cross validation [44]. Following [26], [41], classification accuracy is used as the evaluation metric.…”

Section: Implementation Detailsmentioning

confidence: 99%

Transfer Learning with Dynamic Adversarial Adaptation Network

Wang

Chen

et al. 2019

2019 IEEE International Conference on Data Mining (ICDM)

248

View full text Add to dashboard Cite

The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain adaptation methods either learn a single domain discriminator to align the global source and target distributions, or pay attention to align subdomains based on multiple discriminators. However, in real applications, the marginal (global) and conditional (local) distributions between domains are often contributing differently to the adaptation. There is currently no method to dynamically and quantitatively evaluate the relative importance of these two distributions for adversarial learning. In this paper, we propose a novel Dynamic Adversarial Adaptation Network (DAAN) to dynamically learn domain-invariant representations while quantitatively evaluate the relative importance of global and local domain distributions. To the best of our knowledge, DAAN is the first attempt to perform dynamic adversarial distribution adaptation for deep adversarial learning. DAAN is extremely easy to implement and train in real applications. We theoretically analyze the effectiveness of DAAN, and it can also be explained in an attention strategy. Extensive experiments demonstrate that DAAN achieves better classification accuracy compared to stateof-the-art deep and adversarial methods. Results also imply the necessity and effectiveness of the dynamic distribution adaptation in adversarial transfer learning.

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

Transfer Learning with Dynamic Adversarial Adaptation Network

Wang

Chen

et al. 2019

2019 IEEE International Conference on Data Mining (ICDM)

248

View full text Add to dashboard Cite

show abstract

“…In our experimental analysis, we did not perform hyperparameter optimization, but just used default settings of Keras. It is interesting to investigate whether LAD performance could be further improved by applying procedures for tuning hyperparameters in a transfer learning setting, like (Zhong et al, 2010).…”

Section: Resultsmentioning

confidence: 99%

Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation

Manders

Laarhoven

Marchiori

2019

Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adaptation reduces to aligning source and target domain at class prediction uncertainty level. We tackle this problem by introducing a method based on adversarial learning which forces the label uncertainty predictions on the target domain to be indistinguishable from those on the source domain. Pre-trained deep neural networks are used to generate deep features having high transferability across related domains. We perform an extensive experimental analysis of the proposed method over a wide set of publicly available pre-trained deep neural networks. Results of our experiments on domain adaptation tasks for image classification show that class prediction uncertainty alignment with features extracted from pre-trained deep neural networks provides an efficient, robust and effective method for domain adaptation.

show abstract

“…The second one makes the modeling process more appropriate, as in reality, a user behavior can happen due to either the user's own decision or neighbors' influences. Finally, we observe that the improvement of ComSoc-Adap to ComSoc-RTM is not very significant; thus, for a given task, one can user cross-validation techniques [Zhong et al 2010] to select the most useful models.…”

Section: Performance Comparisonsmentioning

confidence: 99%

“…On the other hand, when K exceeds a threshold (e.g., 50, the default value in the experiment), the model is complex enough to handle the data. At this point, it is less helpful to improve the model performance by increasing K. In practice, K can be tuned through cross-validation techniques [Zhong et al 2010]. …”

Section: Performance Analysismentioning

confidence: 99%

User behavior learning and transfer in composite social networks

Zhong

Wang

Yang

2014

ACM Trans. Knowl. Discov. Data

Self Cite

View full text Add to dashboard Cite

Accurate prediction of user behaviors is important for many social media applications, including social marketing, personalization, and recommendation. A major challenge lies in that although many previous works model user behavior from only historical behavior logs, the available user behavior data or interactions between users and items in a given social network are usually very limited and sparse (e.g., ≥99.9% empty), which makes models overfit the rare observations and fail to provide accurate predictions. We observe that many people are members of several social networks in the same time, such as Facebook, Twitter, and Tencent's QQ. Importantly, users' behaviors and interests in different networks influence one another. This provides an opportunity to leverage the knowledge of user behaviors in different networks by considering the overlapping users in different networks as bridges, in order to alleviate the data sparsity problem, and enhance the predictive performance of user behavior modeling. Combining different networks "simply and naively" does not work well. In this article, we formulate the problem to model multiple networks as "adaptive composite transfer" and propose a framework called ComSoc. ComSoc first selects the most suitable networks inside a composite social network via a hierarchical Bayesian model, parameterized for individual users. It then builds topic models for user behavior prediction using both the relationships in the selected networks and related behavior data. With different relational regularization, we introduce different implementations, corresponding to different ways to transfer knowledge from composite social relations. To handle big data, we have implemented the algorithm using Map/Reduce. We demonstrate that the proposed composite network-based user behavior models significantly improve the predictive accuracy over a number of existing approaches on several real-world applications, including a very large social networking dataset from Tencent Inc.

show abstract

Cross Validation Framework to Choose amongst Models and Datasets for Transfer Learning

Cited by 116 publications

References 11 publications

Transfer Learning with Dynamic Adversarial Adaptation Network

Transfer Learning with Dynamic Adversarial Adaptation Network

Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation

User behavior learning and transfer in composite social networks

Contact Info

Product

Resources

About