Margin Discrepancy-based Adversarial Training for Multi-Domain Text Classification

arXiv:2403.00888v1 Announce Type: cross
Abstract: Multi-domain text classification (MDTC) endeavors to harness available resources from correlated domains to enhance the classification accuracy of the target domain. Presently, most MDTC approaches that embrace adversarial training and the shared-private paradigm exhibit cutting-edge performance. Unfortunately, these methods face a non-negligible challenge: the absence of theoretical guarantees in the design of MDTC algorithms. The dearth of theoretical underpinning poses a substantial impediment to the advancement of MDTC algorithms. To tackle this problem, we first …

abstract accuracy adversarial adversarial training arxiv challenge classification cs.cl cs.lg domain domains edge face harness paradigm performance resources text text classification training type