← Back to all news
arXiv Machine Learning By Wu S. Zihan, Ariane Delrocq, Wulfram Gerstner, Guillaume Bellec

Can Local Learning Match Self-Supervised Backpropagation?

Read the original on arXiv Machine Learning →

arXiv:2601. 21683v2 Announce Type: replace Abstract: 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 to build functional representations in deep neural networks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computer Vision
Sep 4

Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization

The study evaluates self‑supervised learning (SSL) models pretrained on ImageNet‑1k and the Human Protein Atlas (HPA) Field‑of‑View (FOV) for protein localization in microscopy images. DINO‑based Vision Transformer backbones pretrained on either dataset transfer well to the OpenCell dataset, achieving strong performance even without fine‑tuning and improving further when fine‑tuned (0.704 ± 0.027 macro F1 on 17 classes). At the single‑cell level, the HPA‑pretrained model outperforms others in k‑nearest‑neighbor classification across all neighborhood sizes (macro F1 ≥ 0.515).

By Ben Isselmann, Dilara G\"oksu, Heinz Neumann, Andreas Weinmann
ragfine-tuning
More like this →
arXiv AI
Sep 18

Pre-train to Gain: Robust Learning Without Clean Labels

The paper proposes a method that first pre‑trains a feature extractor on the target dataset using in‑domain self‑supervised learning (SSL) without labels, then performs standard supervised training on the same noisy dataset. This two‑stage approach eliminates the need for a clean label subset and consistently improves classification accuracy and label‑error detection across synthetic and real‑world noise, especially as noise rates increase. Experiments show that the method matches or surpasses ImageNet and DinoV2 pre‑training, particularly under high noise conditions.

By David Szczecina, Nicholas Pellegrino, Paul Fieguth
More like this →