Graph-Relational Domain Adaptation

Abstract

Existing domain adaptation methods tend to treat every domain equally and align them all perfectly. Such uniform alignment ignores topological structures among different domains; therefore it may be beneficial for nearby domains, but not necessarily for distant domains. In this work, we relax such uniform alignment by using a domain graph to encode domain adjacency, e.g., a graph of states in the US with each state as a domain and each edge indicating adjacency, thereby allowing domains to align flexibly based on the graph structure. We generalize the existing adversarial learning framework with a novel graph discriminator using encodingconditioned graph embeddings. Theoretical analysis shows that at equilibrium, our method recovers classic domain adaptation when the graph is a clique, and achieves non-trivial alignment for other types of graphs. Empirical results show that our approach successfully generalizes uniform alignment, naturally incorporates domain information represented by graphs, and improves upon existing domain adaptation methods on both synthetic and real-world datasets 1 .

A Survey on Deep Transfer Learning and Beyond

“…Dual-stream architectures [59][60][61][62][63][64][65][66][67][68][69][70][71][72] and approaches that operate directly on image features [73][74][75] are representative ways to perform discrepancy-based DTL. In addition, optimizing the network architecture [99] and improving the feature alignment [100][101][102][103] have also received attention from researchers in recent years. The essence of the above approaches is to minimize the feature differences between the source and target domain datasets.…”

“…L2M is a versatile framework that has shown excellent performance in the application of transfer of pneumonia to COVID-19 chest X-ray images. [100] proposed to use topology to accomplish domain adaptation. This approach reduces the effect of uniform alignment by using domain maps to encode neighboring domains.…”

Weighted Domain Adaptation Using the Graph-Structured Dataset Representation for Machinery Fault Diagnosis under Varying Operating Conditions

“…These DA methods for fault diagnosis have shown their feasibility in dealing with varying operating conditions. However, existing DA methods tend to treat all domains equally and align them all perfectly [ 12 ]. Several works [ 13 , 14 , 15 ] attempted to demonstrate that the domain weighting schemes used on different source domains could enhance the generalizing ability to the target domain and ensemble models can handle the weights dynamically for the target [ 16 , 17 ].…”

“…Consequently, the setting values of operating parameters are typically managed and stored as metadata with the datasets. Although recent studies [ 12 , 18 ] have shown that leveraging the metadata could improve the domain adaptation, this approach remains relatively unexplored in the field of fault diagnosis.…”