Margin Discrepancy-based Adversarial Training for Multi-Domain Text Classification
This work addresses a theoretical gap in MDTC algorithms, which is important for researchers in domain adaptation and text classification, though it is incremental as it builds on existing adversarial training and shared-private paradigms.
The paper tackles the lack of theoretical guarantees in multi-domain text classification (MDTC) by providing a theoretical analysis based on margin discrepancy and Rademacher complexity, and proposes a margin discrepancy-based adversarial training (MDAT) method that outperforms state-of-the-art baselines on two benchmarks.
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 provide a theoretical analysis of MDTC by decomposing the MDTC task into multiple domain adaptation tasks. We incorporate the margin discrepancy as the measure of domain divergence and establish a new generalization bound based on Rademacher complexity. Subsequently, we propose a margin discrepancy-based adversarial training (MDAT) approach for MDTC, in accordance with our theoretical analysis. To validate the efficacy of the proposed MDAT method, we conduct empirical studies on two MDTC benchmarks. The experimental results demonstrate that our MDAT approach surpasses state-of-the-art baselines on both datasets.