Paper is on arxiv.org/abs/2601.21683. This work is done together with my fantastic colleagues: @bellecguill.bsky.social, Ariane Delrocq, and Wulfram Gerstner. We thank members of LCN (@gerstnerlab.bsky.social), Bernd Illing, Xing Chen, and reviewers for their insightful discussions.
While end-to-end self-supervised learning with backpropagation (global BP-SSL) has become central for training modern AI systems, theories of local self-supervised learning (local-SSL) have struggled ...
In supervised setups, many local learning algorithms are proposed to approximate the gradient of BP in theory and approach BP performance on benchmarks. However, for self-supervised learning, the performance gap is larger, and we miss a theory to compare gradients between local-SSL and BP.
Zihan Wu
Can we match self-supervised backpropagation using local learning rules? We show it is possible in our new paper accepted by ICML. We achieve:
1. theoretical equivalence to BP in a controlled setup
2. new SOTA for local learning across image datasets
3. same performance as BP on multiple datasets
For the comp neuro readers:
CLAPP++ is still a three-factor Hebbian plasticity rule:
plasticity = (neuromodulator) × (dendritic prediction) × (Hebbian term)
When there is direct feedback, the dendritic prediction comes from the top layer — matching findings in neuroscience experiments.
