Strategies for improving the training and prediction quality of weakly supervised machine learning models vary in how much they are tailored to a specific task or integrated with a specific model architecture. In this work, we introduce Knodle, a software framework that treats weak data annotations, deep learning models, and methods for improving weakly supervised training as separate, modular components. This modularization gives the training process access to fine-grained information such as data set characteristics, matches of heuristic rules, or elements of the deep learning model ultimately used for prediction. Hence, our framework can encompass a wide range of training methods for improving weak supervision, ranging from methods that only look at correlations of rules and output classes (independently of the machine learning model trained with the resulting labels), to those that harness the interplay of neural networks and weakly labeled data. We illustrate the benchmarking potential of the framework with a performance comparison of several reference implementations on a selection of datasets that are already available in Knodle.
The framework is published as an open-source Python package knodle and available at https://github.com/knodle/knodle.
pyFAST: A Modular PyTorch Framework for Time Series Modeling with Multi-source and Sparse Data
College of Computer Engineering, Jimei University(嘉应大学计算机工程学院);Chengyi College, Jimei University(嘉应大学 Chengyi 学院);Department of Technology, Management and Economics, Technical University of Denmark(丹麦技术大学技术、管理与经济系)
torchmil: A PyTorch-based library for deep Multiple Instance Learning
a Department of Computer Science and Artificial Intelligence, University of Granada, Spain(计算机科学与人工智能系,格拉纳达大学);b Research Centre for Information and Communications Technologies, University of Granada, Spain(信息与通信技术研究中心,格拉纳达大学);c Department of Statistics and Operations Research, University of Granada, Spain(统计与运筹学系,格拉纳达大学);d Institute of Mathematics (IMAG), University of Granada, Spain(数学研究所(IMAG),格拉纳达大学)
autrainer: A Modular and Extensible Deep Learning Toolkit for Computer Audition Tasks
Technical University of Munich(慕尼黑工业大学);Imperial College(帝国理工学院);Munich Center for Machine Learning(慕尼黑机器学习中心);Munich Data Science Institute(慕尼黑数据科学研究所)
TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs
Mila - Quebec AI Institute(魁北克AI研究所);School of Computer Science, McGill University(麦吉尔大学计算机科学学院);University of Oxford(牛津大学);Department of computer science, University of Manitoba(曼尼托瓦大学计算机科学系);AITHYRA;Stanford University(斯坦福大学);DIRO, Université de Montréal(蒙特利尔大学DIRO);CIFAR AI Chair(CIFAR人工智能主席)
PrismSSL: One Interface, Many Modalities; A Single-Interface Library for Multimodal Self-Supervised Learning
dept. Computer Engineering University of Isfahan(计算机工程系 哈尔拉克大学);dept. Computer Engineering University of Texas at Dallas(计算机工程系 德克萨斯大学达拉斯分校);dept. Computer Science University of Oxford(计算机科学系 奥克兰大学);dept. Artificial Intelligence University of Isfahan(人工智能系 哈尔拉克大学)