Multi Task Learning Python Packages

torchjd

Library for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning).

tasksource

Datasets collection and preprocessings framework for NLP extreme multitask learning

bert-multitask-learning

BERT for Multitask Learning

eqtransformer

EQTransformer, a python package for earthquake signal detection and phase picking using AI.

emmental

A deep learning framework for building multimodal multi-task learning systems.

mmsa

MMSA is a unified framework for Multimodal Sentiment Analysis.

bert-classifier

A repository for training transformer based models

rec-pangu

rec_pangu is a flexible open-source project for recommendation systems. It incorporates diverse AI models like ranking algorithms, sequence recall, multi-interest models, and graph-based techniques. Designed for both beginners and advanced users, it enables rapid construction of efficient, custom recommendation engines.

nlp-models

A repository for training transformer based models

ice-learn

A high-level Deep Learning framework that extends PyTorch and PyCUDA.

phonlp

PhoNLP: A BERT-based multi-task learning model for part-of-speech tagging, named entity recognition and dependency parsing (NAACL 2021)

pai-easy-rec

A framework for large scale recommendation algorithms.

easy-cs-rec-custommodel

A framework for large scale recommendation algorithms.

libmtl

A PyTorch Library for Multi-Task Learning

paddlepalm

a Fast, Flexible, Extensible and Easy-to-use NLP Large-scale Pretraining and Multi-task Learning Framework.

mad-fw

MAD: A Multi-task Aggression Detection Framework

scmmt

Multi-task deep learning for cell annotation, surface-protein prediction, and joint scRNA-seq/CITE-seq embeddings.

min2net

End-to-End Multi-Task Learning for Subject-Independent Motor Imagery EEG Classification (IEEE Transactions on Biomedical Engineering)

mtrec

A simple package about multi-task recommendation

toploss

Topological Loss Engineering: optimizer-free PyTorch regularizers (SASP, CVP, NGER, SBMP, DMTA) that embed 2024-2026 optimizer breakthroughs directly into the loss.

multi-task-nmt-lawhy

The Pytorch implementation of the Multi-task Neural Machine Transliteration system.

m3tl

BERT for Multitask Learning