Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning
Authors: Salar Beigzad, Vansh Verma
Summary
arXiv:2605. 18804v1 Announce Type: new Abstract: 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.
Relevance
Read next because Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning overlaps with clean result "Coupling evil personas with wrong answers fails to protect Qwen2.5-7B from EM-induced alignment collapse — and the apparent capability ordering across coupling conditions is mostly eval contamination (LOW confidence)", clean result "The marker is a representational handle, not a behavioural one — sharing it between a villain persona and the assistant transfers no misalignment (HIGH confidence)", experiment "Add C2 control arm (donor sees marker_B without marker_A) to disambiguate paired-marker binding from marker_B leaking alone". Matching terms: good, line, rate, without, full. Source: arxiv cs.LG (Machine Learning).
Threat model
Potential threat/caveat for clean result "Coupling evil personas with wrong answers fails to protect Qwen2.5-7B from EM-induced alignment collapse — and the apparent capability ordering across coupling conditions is mostly eval contamination (LOW confidence)": this item discusses limitation, limitations, negative, robustness.
Abstract
arXiv:2605.18804v1 Announce Type: new Abstract: 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.