Active Learning Using Aggregated Acquisition Functions: Accuracy and Sustainability Analysis

2026-02-07

AI Summary

This work addresses key challenges in active learning—namely, the imbalance between exploration and exploitation, inefficiencies in batch selection, and cold-start issues—by proposing six acquisition function aggregation architectures: serial, parallel, hybrid, adaptive feedback, random exploration, and annealed exploration. These frameworks integrate representativeness-based strategies (e.g., K-Centers) with uncertainty-aware methods (e.g., BALD, BADGE) to jointly optimize data selection and decision boundary refinement. The approach effectively mitigates path dependency and consistently reduces both annotation requirements and computational overhead across multiple models and datasets. For instance, a serial combination of K-Centers followed by BALD achieves comparable model accuracy with 12% fewer labeled samples and nearly 50% lower acquisition cost, demonstrating a favorable trade-off between performance and energy efficiency.

Technology Category

• Machine Learning: Active Learning
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Active learning (AL) is a machine learning (ML) approach that strategically selects the most informative samples for annotation during training, aiming to minimize annotation costs. This strategy not only reduces labeling expenses but also results in energy savings during neural network training, thereby enhancing both data and energy efficiency. In this paper, we implement and evaluate various state-of-the-art acquisition functions, analyzing their accuracy and computational costs, while discussing the advantages and disadvantages of each method. Our findings reveal that representativity-based acquisition functions effectively explore the dataset but do not prioritize boundary decisions, whereas uncertainty-based acquisition functions focus on refining boundary decisions already identified by the neural network. This trade-off is known as the exploration-exploitation dilemma. To address this dilemma, we introduce six aggregation structures: series, parallel, hybrid, adaptive feedback, random exploration, and annealing exploration. Our aggregated acquisition functions alleviate common AL pathologies such as batch mode inefficiency and the cold start problem. Additionally, we focus on balancing accuracy and energy consumption, contributing to the development of more sustainable, energy-aware artificial intelligence (AI). We evaluate our proposed structures on various models and datasets. Our results demonstrate the potential of these structures to reduce computational costs while maintaining or even improving accuracy. Innovative aggregation approaches, such as alternating between acquisition functions such as BALD and BADGE, have shown robust results. Sequentially running functions like $K$-Centers followed by BALD has achieved the same performance goals with up to 12\% fewer samples, while reducing the acquisition cost by almost half.

Problem

• active learning
• exploration-exploitation dilemma
• acquisition functions
• energy efficiency
• annotation cost

Innovation

• aggregated acquisition functions
• exploration-exploitation trade-off
• active learning
• energy-efficient AI
• sustainable machine learning