Copertina

Why pre-training is beneficial for downstream classification tasks?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jiang, Xin, Cheng, Xu, Li, Zechao
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Provable unlearning in topic modeling and downstream tasks
di: Wei, Stanley, et al.
Pubblicazione: (2024)

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

Early-stopping for Transformer model training
di: He, Jing, et al.
Pubblicazione: (2025)

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

Aviary: training language agents on challenging scientific tasks
di: Narayanan, Siddharth, et al.
Pubblicazione: (2024)

A new training approach for text classification in Mental Health: LatentGLoss
di: Sevinç, Korhan
Pubblicazione: (2025)

pUniFind: a unified large pre-trained deep learning model pushing the limit of mass spectra interpretation
di: Zhao, Jiale, et al.
Pubblicazione: (2025)

Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training
di: Barakat, Anas, et al.
Pubblicazione: (2026)

Cross-domain Random Pre-training with Prototypes for Reinforcement Learning
di: Liu, Xin, et al.
Pubblicazione: (2023)

Language models scale reliably with over-training and on downstream tasks
di: Gadre, Samir Yitzhak, et al.
Pubblicazione: (2024)

Target noise: A pre-training based neural network initialization for efficient high resolution learning
di: Wang, Shaowen, et al.
Pubblicazione: (2026)

TSEML: A task-specific embedding-based method for few-shot classification of cancer molecular subtypes
di: Su, Ran, et al.
Pubblicazione: (2024)

An Electrocardiogram Multi-task Benchmark with Comprehensive Evaluations and Insightful Findings
di: Xu, Yuhao, et al.
Pubblicazione: (2025)

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

Curriculum reinforcement learning with measurable task representation learning
di: Wen, Yongyan, et al.
Pubblicazione: (2026)

EXGnet: a single-lead explainable-AI guided multiresolution network with train-only quantitative features for trustworthy ECG arrhythmia classification
di: Showrav, Tushar Talukder, et al.
Pubblicazione: (2025)

A dynamical clipping approach with task feedback for Proximal Policy Optimization
di: Zhang, Ziqi, et al.
Pubblicazione: (2023)

Graph Generative Pre-trained Transformer
di: Chen, Xiaohui, et al.
Pubblicazione: (2025)

TSFM in-context learning for time-series classification of bearing-health status
di: Tokic, Michel, et al.
Pubblicazione: (2025)

The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
di: Yin, Chenlong, et al.
Pubblicazione: (2025)

Heterogeneous Graph Pre-training Based Model for Secure and Efficient Prediction of Default Risk Propagation among Bond Issuers
di: Li, Xurui, et al.
Pubblicazione: (2025)

Small transformer architectures for task switching
di: Gros, Claudius
Pubblicazione: (2025)

A Pre-trained Reaction Embedding Descriptor Capturing Bond Transformation Patterns
di: Liu, Weiqi, et al.
Pubblicazione: (2026)

AsyCo: An Asymmetric Dual-task Co-training Model for Partial-label Learning
di: Li, Beibei, et al.
Pubblicazione: (2024)

Efficiency optimization of large-scale language models based on deep learning in natural language processing tasks
di: Mei, Taiyuan, et al.
Pubblicazione: (2024)

Energy-Aware LLMs: A step towards sustainable AI for downstream applications
di: Tran, Nguyen Phuc, et al.
Pubblicazione: (2025)

GraphGPT: Generative Pre-trained Graph Eulerian Transformer
di: Zhao, Qifang, et al.
Pubblicazione: (2023)

EnECG: Efficient Ensemble Learning for Electrocardiogram Multi-task Foundation Model
di: Xu, Yuhao, et al.
Pubblicazione: (2025)

Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks
di: Fan, Tianyu, et al.
Pubblicazione: (2024)

Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework
di: Yi, Zhongchao, et al.
Pubblicazione: (2024)

Auxiliary task discovery through generate-and-test
di: Rafiee, Banafsheh, et al.
Pubblicazione: (2022)

Why and How Auxiliary Tasks Improve JEPA Representations
di: Yu, Jiacan, et al.
Pubblicazione: (2025)

Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?
di: Nielsen, Jacob, et al.
Pubblicazione: (2025)

Why mask diffusion does not work
di: Sun, Haocheng, et al.
Pubblicazione: (2025)

TrackGPT -- A generative pre-trained transformer for cross-domain entity trajectory forecasting
di: Stroh, Nicholas
Pubblicazione: (2024)

ProdRev: A DNN framework for empowering customers using generative pre-trained transformers
di: Gupta, Aakash, et al.
Pubblicazione: (2025)

Neural Dynamics-Informed Pre-trained Framework for Personalized Brain Functional Network Construction
di: Jiang, Hongjie, et al.
Pubblicazione: (2026)

Offline Multi-task Transfer RL with Representational Penalization
di: Bose, Avinandan, et al.
Pubblicazione: (2024)

Conflict-Averse Gradient Descent for Multi-task Learning
di: Liu, Bo, et al.
Pubblicazione: (2021)

LENS: Large Pre-trained Transformer for Exploring Financial Time Series Regularities
di: Xu, Yuanjian, et al.
Pubblicazione: (2024)