2020/07/02 by Avinash Madasu, Madasu, Avinash, Vijjini Anvesh Rao +1
Computer Science · Mathematics · Psychology · #Adaptation (eye) #Artificial intelligence #Classifier (UML) #Cognitive psychology #Computation and Language (cs.CL) #Computer science #Consolidation (business) #Convolutional neural network #Domain (mathematical analysis) #Domain Adaptation and Few-Shot Learning #Domain adaptation #FOS: Computer and information sciences #Forgetting #Leverage (statistics) #Machine learning #Mathematics #Psychology #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2007.01189
Accepted at 25th International Conference on Pattern Recognition, January 2021, Milan, Italy
openalex publication_date 2020/07/02 · arxiv created 2020/07/19 · arxiv updated 2020/07/21 · openalex created_date 2022/07/26 · openalex updated_date 2026/08/06
Elastic Weight Consolidation (EWC) is a technique used in overcoming\ncatastrophic forgetting between successive tasks trained on a neural network.\nWe use this phenomenon of information sharing between tasks for domain\nadaptation. Training data for tasks such as sentiment analysis (SA) may not be\nfairly represented across multiple domains. Domain Adaptation (DA) aims to\nbuild algorithms that leverage information from source domains to facilitate\nperformance on an unseen target domain. We propose a model-independent\nframework - Sequential Domain Adaptation (SDA). SDA draws on EWC for training\non successive source domains to move towards a general domain solution, thereby\nsolving the problem of domain adaptation. We test SDA on convolutional,\nrecurrent, and attention-based architectures. Our experiments show that the\nproposed framework enables simple architectures such as CNNs to outperform\ncomplex state-of-the-art models in domain adaptation of SA. In addition, we\nobserve that the effectiveness of a harder first Anti-Curriculum ordering of\nsource domains leads to maximum performance.\n