Research map / Large language models / Instruction and fine-tuning
Non-transferable Pruning
Ruyi Ding, Lili Su, A. Adam Ding, Yunsi Fei
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace NTL/CUTI with ADMM-based pruning plus Fisher space regularization (NTP) | VGG-11 digits transfer · Source USPS -> target MNIST | SLC-AUC: 0.42 -> -0.47 (vs NTL), 0.89 -> -0.47 (vs CUTI) | Improved |
| use NTP on highly similar RGB digit datasets SYN and SVHN | NTP VGG-11 · Source SYN -> target SVHN | SLC-AUC: 1.52 -> 0.51 (NTL vs NTP) | Mixed |
| use NTP versus NTL and CUTI under full fine-tuning across learning rates | NTP VGG-11 · MNIST -> USPS, full fine-tuning, 10% data | target accuracy: 0.96 -> 0.21 (CUTI vs NTP, lr 1e-5) | Improved |
| use NTP versus CUTI under linear probing at lr 1e-3 | NTP VGG-11 · MNIST -> USPS, linear probing | target accuracy: 0.18 -> 0.28 (CUTI vs NTP) | Hurt |
| apply NTP instead of keeping the original pretrained model on source accuracy | NTP VGG-11 · Source SVHN accuracy | source accuracy change: 4.10% down (NTP) vs 0.17% up (CUTI) | Hurt |
| add NTP to self-supervised models | SimCLR, MoCo-v1, MoCo-v2 ResNet-50 · STL-10 transferability (LogME) | LogME: 6.19 -> -1.11 (MoCo-v2) | Improved |
| apply NTP to self-supervised versus supervised models | MoCo-v1 and MoCo-v2 · CIFAR-10 -> STL-10 fine-tuning | non-transferability after fine-tuning | Mixed |
| increase sparsity of the NTP-pruned model (ablation) | NTP ResNet-18 and VGG-11 · CIFAR-10 -> STL-10 | SLC-AUC / transfer performance | Improved |
| increase ADMM weight-update epochs from 1 to 20 (ablation) | NTP ResNet-18 · CIFAR-10 -> STL-10 | SLC-AUC | No clear effect |
| increase the amount of training data used in ADMM pruning (ablation) | NTP ResNet-18 · CIFAR-10 -> STL-10 | non-transferability | Improved |
| apply one-shot magnitude pruning at high sparsity | USPS-pretrained ResNet-18 · USPS -> various targets | SLC-AUC | Mixed |
Closest papers by meaning
- Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning (CVPR 2024 · similarity 0.89)
- Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising (CVPR 2025 · similarity 0.87)
- MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection (CVPR 2024 · similarity 0.86)
- Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization (NeurIPS 2026 · similarity 0.85)
- Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation (AAAI 2025 · similarity 0.84)
- Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model (ICLR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
