TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data

Abstract

Machine learning practitioners often have access to a spectrum of data: labeled data for the target task (which is often limited), unlabeled data, and auxiliary data, the many available labeled datasets for other tasks. We describe TAGLETS, a system built to study techniques for automatically exploiting all three types of data and creating high-quality, servable classifiers. The key components of TAGLETS are: (1) auxiliary data organized according to a knowledge graph, (2) modules encapsulating different methods for exploiting auxiliary and unlabeled data, and (3) a distillation stage in which the ensembled modules are combined into a servable model. We compare TAGLETS with state-of-the-art transfer learning and semi-supervised learning methods on four image classification tasks. Our study covers a range of settings, varying the amount of labeled data and the semantic relatedness of the auxiliary data to the target task. We find that the intelligent incorporation of auxiliary and unlabeled data into multiple learning techniques enables TAGLETS to match-and most often significantly surpass-these alternatives. TAGLETS is available as an open-source system at github.com/BatsResearch/taglets.

arXiv commentPaper published at MLSys 2022. It passed the artifact evaluation earning two ACM badges: (1) Artifacts Evaluated Functional v1.1 and (2) Artifacts Available v1.1

References in corpus (17)

• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality
• Distilling the Knowledge in a Neural Network
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Practical Bayesian Optimization of Machine Learning Algorithms
• Prototypical Networks for Few-shot Learning
• Knowledge Distillation: A Survey
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• How transferable are features in deep neural networks?
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
• Snorkel: Rapid Training Data Creation with Weak Supervision
• Big Self-Supervised Models are Strong Semi-Supervised Learners
• An Ensemble Method to Produce High-Quality Word Embeddings (2016)
• TuPAQ: An Efficient Planner for Large-scale Predictive Analytic Queries
• When Semi-Supervised Learning Meets Transfer Learning: Training Strategies, Models and Datasets
• Zero-Shot Learning with Common Sense Knowledge Graphs