Knowledge Transfer and Task Specialization
FT (full)
In brief — site editorial, not from the paper
Continues training every weight in the model on new task data — maximum flexibility, maximum cost, and no part of the model left unchanged.
Definition
Full FT is the maximally expressive parametric realization of TL: GD (Parametric Update) applies to every model layer without exception, producing a Whole-Model footprint that carries the highest structural validation burden in the taxonomy. The unrestricted update surface structurally necessitates the Large Labeled data regime—with all parameters free to drift, the optimization landscape has sufficient degrees of freedom to overfit or catastrophically corrupt prior knowledge unless constrained by large-scale supervision [108]. The Task Specialization goal draws the sharpest coordinate boundary with Retraining: both are mechanistically identical across D1 (Mechanism), D4 (Persistence), and D5 (Scope), yet retraining targets Drift Remediation on a fixed behavioral envelope rather than reshaping that envelope for a new task. Compared to Partial FT, Full FT sacrifices the reduced testing surface (D5 (Scope) contracts from Whole-Model to Partial) in exchange for broader update expressiveness; compared to PEFT, it eliminates the Modular isolation boundary that permits component-level rollback, replacing it with whole-model entanglement. Because Full FT modifies the entire parameter space with no modular isolation boundary, rollback requires complete checkpoint restoration rather than targeted component substitution, and the validation obligation extends to full-system behavioral regression testing across all previously certified behavioral boundaries before any re-deployment.
Verbatim from the paper — Knowledge Transfer and Task Specialization
Related techniques
- umbrella PEFT (LoRA, adapters) — PEFT is a specialisation within the fine-tuning family
Full FT is the maximally expressive parametric realization of TL
Appendix C, Knowledge Transfer and Task Specialization
Nearest profiles
MTL (0.17), Training (0.20), Adversarial Training (0.21), DP-FT (0.33), FT (partial) (0.33)
Computed from the taxonomy data (Gower distance over all six dimensions)
References
- [108] James Kirkpatrick et al. 2017. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences
Numbered as in the paper
Cite this row
FT (full) — six-dimensional profile D1: parametric-update D2: task-specialization D3: large-labeled D4: ad-hoc-permanent, scheduled-permanent D5: whole-model D6: dl, fm, llm, mllm Source: arXiv:2608.06246Compare with another technique Find in the explorer