Triplet adversarial Learning-driven graph architecture search network augmented with Probsparse-attention mechanism for fault diagnosis under Few-shot & Domain-shift

Abstract

The consistent probability distribution between training & testing data is one of the prerequisites for valid intelligent diagnosis models. Nevertheless, the ineluctable distribution discrepancies produced by variable working conditions cause intense conflicts with the above. Besides, many existing models fail to explicitly characterize the correlation between data, which makes them difficult to mine discriminative features in limited samples. Fortunately, the proposal of graph neural networks provides a potential solution to overcome the above issues. Inspired by this, this paper creatively proposes a graph architecture search network (GASN) for cross-domain fault diagnosis. Its main framework consists of graph-feature extraction modules, graph-architecture search modules and differentiated classifiers, which can effectively reduce the computational complexity and accelerate the inferential efficiency of GASN, with two distinctive characteristics: (1) Specially designed search module utilizes multi-head probsparse-attention mechanism to search the optimal graph-architecture, thus suppressing the redundancy and exclusivity among candidate graph-data; (2) Triplet loss-driven domain adversarial training strategy is proposed to enhance the domain adaptability of GASN, which can assist itself to achieve fine-grained adaptation of distinguishable architectures in response to unknown domains. Comparative results on four case studies indicate that the GASN can achieve superior performance to existing state-of-art models even under imbalanced data.