DRAMA: Domain Retrieval using Adaptive Module Allocation

2026-02-16

AI Summary

This work addresses the challenges faced by current neural information retrieval models in multi-domain scenarios, including parameter redundancy, high computational costs, limited cross-domain generalization, and substantial environmental impact. To overcome these limitations, the authors propose a parameter- and energy-efficient modular retrieval framework that leverages lightweight domain adapters and a dynamic gating mechanism to adaptively activate the most relevant domain-specific module for each query. This approach enables flexible integration of new domains without requiring full-model retraining. Evaluated on multiple web retrieval benchmarks, the method achieves performance comparable to domain-specialized models while utilizing only a fraction of their parameters and computational resources, thereby significantly enhancing model scalability, sustainability, and deployment efficiency.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Image and Video Retrieval
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Neural models are increasingly used in Web-scale Information Retrieval (IR). However, relying on these models introduces substantial computational and energy requirements, leading to increasing attention toward their environmental cost and the sustainability of large-scale deployments. While neural IR models deliver high retrieval effectiveness, their scalability is constrained in multi-domain scenarios, where training and maintaining domain-specific models is inefficient and achieving robust cross-domain generalisation within a unified model remains difficult. This paper introduces DRAMA (Domain Retrieval using Adaptive Module Allocation), an energy- and parameter-efficient framework designed to reduce the environmental footprint of neural retrieval. DRAMA integrates domain-specific adapter modules with a dynamic gating mechanism that selects the most relevant domain knowledge for each query. New domains can be added efficiently through lightweight adapter training, avoiding full model retraining. We evaluate DRAMA on multiple Web retrieval benchmarks covering different domains. Our extensive evaluation shows that DRAMA achieves comparable effectiveness to domain-specific models while using only a fraction of their parameters and computational resources. These findings show that energy-aware model design can significantly improve scalability and sustainability in neural IR.

Problem

• neural information retrieval
• multi-domain retrieval
• scalability
• sustainability
• cross-domain generalization

Innovation

• adaptive module allocation
• domain-specific adapters
• dynamic gating
• parameter-efficient retrieval
• sustainable neural IR