Exploring $\ell_0$ Sparsification for Inference-free Sparse Retrievers
This addresses efficiency challenges in information retrieval for real-world applications, though it is incremental as it builds on existing sparse retrieval paradigms.
The paper tackles the problem of sparsification for inference-free sparse retrieval models, which lack efficient methods, by exploring an ℓ₀-inspired approach. It achieves state-of-the-art performance among inference-free models on the BEIR benchmark and is comparable to leading Siamese models.
With increasing demands for efficiency, information retrieval has developed a branch of sparse retrieval, further advancing towards inference-free retrieval where the documents are encoded during indexing time and there is no model-inference for queries. Existing sparse retrieval models rely on FLOPS regularization for sparsification, while this mechanism was originally designed for Siamese encoders, it is considered to be suboptimal in inference-free scenarios which is asymmetric. Previous attempts to adapt FLOPS for inference-free scenarios have been limited to rule-based methods, leaving the potential of sparsification approaches for inference-free retrieval models largely unexplored. In this paper, we explore $\ell_0$ inspired sparsification manner for inference-free retrievers. Through comprehensive out-of-domain evaluation on the BEIR benchmark, our method achieves state-of-the-art performance among inference-free sparse retrieval models and is comparable to leading Siamese sparse retrieval models. Furthermore, we provide insights into the trade-off between retrieval effectiveness and computational efficiency, demonstrating practical value for real-world applications.