REVISTING NEGATIVE TRANSFER USING ADVERSARIAL LEARNING
An unintended consequence of feature sharing is the model fitting to correlated tasks within the dataset, termed negative transfer. In this paper, we revisit the problem of negative transfer in multitask setting and find that its corrosive effects are applicable to a wide range of linear and non-linear models, including neural networks. We first study the effects of negative transfer in a principled way and show that previously proposed counter-measures are insufficient, particularly for trainable features. We propose an adversarial training approach to mitigate the effects of negative transfer by viewing the problem in a domain adaptation setting. Finally, empirical results on attribute prediction multi-task on AWA and CUB datasets further validate the need for correcting negative sharing in an end-to-end manner.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeDomain AdaptationSimilar Papers 제목 키워드 기반
A Unified Approach to Interpreting and Boosting Adversarial Transferability
In this paper, we use the interaction inside adversarial perturbations to explain and boost the adversarial transferability. We discover and prove the negative correlation between the adversarial transferability and the …
Towards A Unified Understanding and Improving of Adversarial Transferability
In this paper, we use the interaction inside adversarial perturbations to explain and boost the adversarial transferability. We discover and prove the negative correlation between the adversarial transferability and the …
Partial Transfer Learning with Selective Adversarial Networks
Adversarial learning has been successfully embedded into deep networks to learn transferable features, which reduce distribution discrepancy between the source and target domains. Existing domain adversarial networks ass…
Transfer LearningCharacterizing and Avoiding Negative Transfer
When labeled data is scarce for a specific target task, transfer learning often offers an effective solution by utilizing data from a related source task. However, when transferring knowledge from a less related source, …
Transfer LearningDiscriminative Partial Domain Adversarial Network
Domain adaptation (DA) has been a fundamental building block for Transfer Learning (TL) which assumes that source and target domain share the same label space. A more general and realistic setting is that the label space…
Domain AdaptationPartial Domain AdaptationTransfer Learning