Cross Domain Regularization for Neural Ranking Models Using Adversarial Learning
This addresses the domain generalization issue in neural ranking models, which is incremental as it applies an existing adversarial method to a specific bottleneck.
The paper tackles the problem of neural ranking models overfitting to training domains and generalizing poorly to unseen domains, and shows that using adversarial learning as a cross-domain regularizer improves performance on held-out domains, with gains of up to 30% in precision@1.
Unlike traditional learning to rank models that depend on hand-crafted features, neural representation learning models learn higher level features for the ranking task by training on large datasets. Their ability to learn new features directly from the data, however, may come at a price. Without any special supervision, these models learn relationships that may hold only in the domain from which the training data is sampled, and generalize poorly to domains not observed during training. We study the effectiveness of adversarial learning as a cross domain regularizer in the context of the ranking task. We use an adversarial discriminator and train our neural ranking model on a small set of domains. The discriminator provides a negative feedback signal to discourage the model from learning domain specific representations. Our experiments show consistently better performance on held out domains in the presence of the adversarial discriminator---sometimes up to 30% on precision@1.