HCL-FF: Hierarchical and Contrastive Learning for Forward-Forward Algorithm
For researchers seeking biologically plausible alternatives to backpropagation, HCL-FF significantly boosts the performance of the Forward-Forward algorithm, making it more competitive on standard vision benchmarks.
HCL-FF improves the Forward-Forward algorithm by adding hierarchical learning and supervised contrastive objectives, achieving new state-of-the-art accuracy among FF-based methods on CIFAR-10 (+5.46%), CIFAR-100 (+17.00%), and Tiny-ImageNet (+12.51%).
Deep neural networks trained with backpropagation have achieved outstanding performance in vision tasks but remain biologically implausible, computationally demanding, and difficult to interpret. The Forward-Forward (FF) algorithm offers a promising alternative by training each layer independently through local goodness objectives. However, its purely local optimization lacks hierarchical coordination across layers, and the decoupling of goodness from features leaves the representations unconstrained and semantically ambiguous. We propose a Hierarchical and Contrastive Learning FF framework (HCL-FF) to address these limitations. HCL-FF introduces (1) a coarse-to-fine hierarchical learning strategy that guides representations from low-level cues to high-level semantics, and (2) a supervised contrastive objective that enforces class-discriminative alignment after goodness decoupling. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet demonstrate that HCL-FF achieves new state-of-the-art performance among FF-based methods, with notable accuracy gains of +5.46%, +17.00%, and +12.51%, respectively.