Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations
This addresses the challenge of zero-shot generalization in dense retrieval for information retrieval systems, offering an incremental improvement over existing methods.
The paper tackled the problem of dense retrieval models generalizing poorly to new domains without training data by proposing MoDIR, a method that learns domain-invariant representations, resulting in over 10% relative gains on sensitive datasets in the BEIR benchmark.
Dense retrieval (DR) methods conduct text retrieval by first encoding texts in the embedding space and then matching them by nearest neighbor search. This requires strong locality properties from the representation space, i.e, the close allocations of each small group of relevant texts, which are hard to generalize to domains without sufficient training data. In this paper, we aim to improve the generalization ability of DR models from source training domains with rich supervision signals to target domains without any relevant labels, in the zero-shot setting. To achieve that, we propose Momentum adversarial Domain Invariant Representation learning (MoDIR), which introduces a momentum method in the DR training process to train a domain classifier distinguishing source versus target, and then adversarially updates the DR encoder to learn domain invariant representations. Our experiments show that MoDIR robustly outperforms its baselines on 10+ ranking datasets from the BEIR benchmark in the zero-shot setup, with more than 10% relative gains on datasets with enough sensitivity for DR models' evaluation. Source code of this paper will be released.