Learning Faster without Deeper Networks: A*-Inspired Batch Selection for Efficient CNN Training

📅 2026-07-17
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Traditional CNN training relies on random mini-batch sampling, which often leads to rapid saturation of learning signals as most samples quickly become “easy,” thereby slowing convergence. This work proposes A*-inspired Batch Selection (A*-BS), the first approach to integrate A* search into batch selection, introducing a dynamic scoring mechanism that jointly considers sample loss difficulty and reuse penalties to adaptively select informative and diverse batches. Without modifying network architecture or optimizer, A*-BS achieves superior performance on lightweight CNNs across half of the MedMNIST-v2 benchmark tasks, outperforming ResNet-18/50 in both accuracy and AUC—by up to 15% relatively—while significantly accelerating training. These results demonstrate that intelligent batch sequencing can partially substitute for model depth.
📝 Abstract
Common practice when training Convolutional Neural Networks (CNNs) is to use randomly shuffled mini-batches. This creates two limitations: slower convergence, and a diminishing learning signal, since many samples are quickly classified as easy during training. We address these inefficiencies with A*-Inspired Batch Selection (A*-BS), a lightweight, model-agnostic strategy that formulates mini-batch scheduling as a heuristic search problem. Each batch is treated as a node in a search space and ranked using an A*-like score combining a loss-based difficulty measure with a reuse penalty. This encourages informative gradient updates and batch diversity throughout training, without modifying network architectures or optimization algorithms, so it integrates seamlessly into existing pipelines. We evaluate A*-BS on the twelve 2D classification tasks of the MedMNIST-v2 benchmark, using a deliberately simple architecture of approximately 2.25x10^5 parameters, compared against the ResNet-18 and ResNet-50 baselines reported by the benchmark. On half of these tasks, the lightweight model with A*-BS reaches higher accuracy and AUC than both ResNet baselines, with relative gains of up to 15%. An ablation under identical architecture and hyperparameters shows A*-BS outperforms random batch shuffling on all twelve tasks. Wall-clock measurements further show the lightweight CNN with A*-BS trains substantially faster than ResNet-18 and ResNet-50 on identical hardware. These results indicate that intelligent batch ordering can partially compensate for reduced architectural complexity, offering a computationally efficient alternative to deeper models, with reliability reinforced by strong performance even against deeper, more sophisticated architectures.
Problem

Research questions and friction points this paper is trying to address.

CNN training
mini-batch selection
convergence speed
learning signal
training efficiency
Innovation

Methods, ideas, or system contributions that make the work stand out.

A*-inspired batch selection
efficient CNN training
mini-batch scheduling
model-agnostic optimization
heuristic search
🔎 Similar Papers
No similar papers found.
A
Anxhelo Shehu
AI Laboratory, University Metropolitan Tirana, Tirana, Albania
E
Enes Stastoli
AI Laboratory, University Metropolitan Tirana, Tirana, Albania
A
Arben Cela
AI Laboratory, University Metropolitan Tirana, Tirana, Albania; Laboratory of Images Signals and Intelligent Systems, ESIEE Paris, Paris, France