# Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning

arXiv: https://arxiv.org/abs/2605.18804 · HTML: https://mlsanity.com/paper/2605.18804/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 15 of 15)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [The Forward-Forward Algorithm: Some Preliminary Investigations](https://mlsanity.com/paper/2212.13345/) (2022)
- [Recent Trends in Deep Learning Based Natural Language Processing](https://mlsanity.com/paper/1708.02709/) (2017)
- [Direct Feedback Alignment Provides Learning in Deep Neural Networks](https://mlsanity.com/paper/1609.01596/) (2016)
- [Towards an integration of deep learning and neuroscience](https://mlsanity.com/paper/1606.03813/) (2016)
- [Towards deep learning with segregated dendrites](https://mlsanity.com/paper/1610.00161/) (2016)
- [Scalable, High-Quality Object Detection](https://mlsanity.com/paper/1412.1441/) (2014)
- [SMOOT: Saliency Guided Mask Optimized Online Training](https://mlsanity.com/paper/2310.00772/) (2023)
- [FFCL: Forward-Forward Net with Cortical Loops, Training and Inference on Edge Without Backpropagation](https://mlsanity.com/paper/2405.12443/) (2024)
- [Saliency Assisted Quantization for Neural Networks](https://mlsanity.com/paper/2411.05858/) (2024)
- [Novel Saliency Analysis for the Forward Forward Algorithm](https://mlsanity.com/paper/2409.15365/) (2024)
- [Quantized and Interpretable Learning Scheme for Deep Neural Networks in Classification Task](https://mlsanity.com/paper/2412.03915/) (2024)
- [Enhancing Polyp Segmentation via Encoder Attention and Dynamic Kernel Update](https://mlsanity.com/paper/2509.23502/) (2025)
- [Resource-efficient medical image classification for edge devices](https://mlsanity.com/paper/2512.17515/) (2025)
- [NetworkFF: Unified Layer Optimization in Forward-Only Neural Networks](https://mlsanity.com/paper/2512.17531/) (2025)

## Abstract (arXiv)

We propose Adaptive Multi-Scale Goodness Aggregation (AMSGA), a novel extension of the Forward-Forward (FF) algorithm designed to improve stability, robustness, and generalization in local-learning neural networks. AMSGA addresses several limitations of the original FF framework by introducing multi-scale goodness aggregation across local, intermediate, and global representations; adaptive curriculum-guided hard negative mining; layer-dependent adaptive thresholds; and a warm-up cosine annealing learning-rate schedule for improved optimization stability. Together, these modifications strengthen the FF paradigm while preserving its biologically plausible and memory-efficient properties. Experiments on MNIST and Fashion-MNIST demonstrate consistent performance improvements over the baseline FF algorithm, achieving up to +1.45% improvement on MNIST and +1.50% improvement on Fashion-MNIST without significant computational overhead. Our results suggest that local learning methods can become substantially more competitive when goodness estimation and training dynamics are carefully designed.