The ACM TOIS journal is planning a special issue in 2023 on efficiency on neural information retrieval. The deadline for submissions is 31 December 2022
To quote from the ACM announcement
“The aim of this Special Section is to engage with researchers in Information Retrieval, Natural Language Processing, and related areas and gather insight into the core challenges in measuring, reporting, and optimizing all facets of efficiency in Neural Information Retrieval (NIR) systems, including time-, space-, resource-, sample- and energy efficiency, among other factors. While researchers in the field have assiduously explored the Pareto frontier in quality and efficiency in other contexts for decades, we believe that the neural dimension introduces new hurdles. This special section solicits perspectives from active researchers to advance our understanding of and to overcome efficiency challenges in NIR. In particular, researchers are encouraged to examine the ever-growing model complexity through appropriate empirical analysis, to propose models that require less data, computational resources, and energy for training and fine-tuning with similarly efficient inference, to ask if there are meaningful simplifications of the existing training processes or model architectures that lead to comparable quality, and explore a multi-faceted evaluation of NIR models from quality to all dimensions of efficiency with standardized metrics.”
Martin White