Cover Image

Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lippl, Samuel, Lindsey, Jack W.
Format:	Preprint
Published:	2023
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

An empirical study of task and feature correlations in the reuse of pre-trained models
by: Mohamud, Jama Hussein, et al.
Published: (2025)

A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
by: Anguita, Nicolas, et al.
Published: (2026)

A mathematical theory of balancing relational generalization and memorization
by: Cheng, Luke, et al.
Published: (2026)

When does compositional structure yield compositional generalization? A kernel theory
by: Lippl, Samuel, et al.
Published: (2024)

Inductive biases in deep learning models for weather prediction
by: Thuemmel, Jannik, et al.
Published: (2023)

Task-conditioned adaptation of visual features in multi-task policy learning
by: Marza, Pierre, et al.
Published: (2024)

MTLComb: multi-task learning combining regression and classification tasks for joint feature selection
by: Cao, Han, et al.
Published: (2024)

Task structure and nonlinearity jointly determine learned representational geometry
by: Alleman, Matteo, et al.
Published: (2024)

Regularising NARX models with multi-task learning
by: Bee, Sarah, et al.
Published: (2025)

RL-finetuning LLMs from on- and off-policy data with a single algorithm
by: Tang, Yunhao, et al.
Published: (2025)

On the generalization of language models from in-context learning and finetuning: a controlled study
by: Lampinen, Andrew K., et al.
Published: (2025)

Cross-talk based multi-task learning for fault classification of machine system influenced by multiple variables
by: Yi, Wonjun, et al.
Published: (2026)

Generalizing to any diverse distribution: uniformity, gentle finetuning and rebalancing
by: Loukas, Andreas, et al.
Published: (2024)

On the importance of cross-task features for class-incremental learning
by: Soutif--Cormerais, Albin, et al.
Published: (2021)

Position bias in features
by: Demsyn-Jones, Richard
Published: (2024)

Joint auto-encoders: a flexible multi-task learning framework
by: Epstein, Baruch, et al.
Published: (2017)

Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences
by: Lampinen, Andrew Kyle, et al.
Published: (2025)

Low-rank finetuning for LLMs: A fairness perspective
by: Das, Saswat, et al.
Published: (2024)

Separating the what and how of compositional computation to enable reuse and continual learning
by: Shan, Haozhe, et al.
Published: (2025)

Learned feature representations are biased by complexity, learning order, position, and more
by: Lampinen, Andrew Kyle, et al.
Published: (2024)

ESM-NBR: fast and accurate nucleic acid-binding residue prediction via protein language model feature representation and multi-task learning
by: Zeng, Wenwu, et al.
Published: (2023)

Adaptive multi-gradient methods for quasiconvex vector optimization and applications to multi-task learning
by: Minh, Nguyen Anh, et al.
Published: (2024)

ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
by: Qiu, Ruizhong, et al.
Published: (2026)

Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning
by: Gutheil, Julian, et al.
Published: (2026)

Automatic detection of abnormal clinical EEG: comparison of a finetuned foundation model with two deep learning models
by: Bussalb, Aurore, et al.
Published: (2025)

BadGPT-4o: stripping safety finetuning from GPT models
by: Krupkina, Ekaterina, et al.
Published: (2024)

PreFT: Prefill-only finetuning for efficient inference
by: Lanpouthakoun, Andrew, et al.
Published: (2026)

The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases
by: Romero, David W.
Published: (2024)

Representation Learning by Ranking across multiple tasks
by: Gu, Lifeng
Published: (2021)

From Simulation to Enaction: Post-trained language models recognize and react to their own generations
by: G., Asvin, et al.
Published: (2026)

Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning
by: Malekzadeh, Parvin, et al.
Published: (2023)

Ultra-fast feature learning for the training of two-layer neural networks in the two-timescale regime
by: Barboni, Raphaël, et al.
Published: (2025)

Multitask finetuning and acceleration of chemical pretrained models for small molecule drug property prediction
by: Adrian, Matthew, et al.
Published: (2025)

Continuous-time reinforcement learning for optimal switching over multiple regimes
by: Huang, Yijie, et al.
Published: (2025)

A multi-task deep learning approach for lane-level pavement performance prediction with segment-level data
by: Wang, Bo, et al.
Published: (2024)

Physical formula enhanced multi-task learning for pharmacokinetics prediction
by: Li, Ruifeng, et al.
Published: (2024)

Transformer learns the cross-task prior and regularization for in-context learning
by: Lu, Fei, et al.
Published: (2025)

Dynamic technology impact analysis: A multi-task learning approach to patent citation prediction
by: Seol, Youngjin, et al.
Published: (2024)

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate
by: Bu, Zhiqi, et al.
Published: (2024)

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
by: Betley, Jan, et al.
Published: (2025)