TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 45 of its 73 references that are in the map. First posted on arXiv 8 Nov 2021.
Builds on
45 of 73 references.
References · 45
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2015Domain-Adversarial Training of Neural Networkscited by 3,023
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
- 2016Identity Mappings in Deep Residual Networkscited by 1,960
- 2020Knowledge Distillation: A Surveycited by 1,578
33 more
- 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
- 2017Adversarial Discriminative Domain Adaptationcited by 1,309
- 2014How transferable are features in deep neural networks?cited by 1,216
- 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
- 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
- 2021Robust fine-tuning of zero-shot modelscited by 785
- 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
- 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 688
- 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 542
- 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
- 2019Introduction to Multi-Armed Banditscited by 475
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
- 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
- 2020Meta Pseudo Labelscited by 372
- 2017Snorkel: Rapid Training Data Creation with Weak Supervisioncited by 370
- 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
- 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
- 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
- 2017Few-Shot Adversarial Domain Adaptationcited by 111
- 2017Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuningcited by 48
- 2019d-SNE: Domain Adaptation using Stochastic Neighborhood Embeddingcited by 40
- 2019TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learningcited by 39
- 2021Self-Tuning for Data-Efficient Deep Learningcited by 39
- 2021Adaptive Consistency Regularization for Semi-Supervised Transfer Learningcited by 37
- 2020Neural Data Server: A Large-Scale Search Engine for Transfer Learning Datacited by 27
- 2018Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Datacited by 25
- 2020Zero-Shot Learning with Common Sense Knowledge Graphscited by 17
- 2016An Ensemble Method to Produce High-Quality Word Embeddings (2016)cited by 13
- 2019The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Developmentcited by 13
- 2019A Hierarchical Grocery Store Image Dataset with Visual and Semantic Labelscited by 12
- 2018When Semi-Supervised Learning Meets Transfer Learning: Training Strategies, Models and Datasetscited by 9
- 2015TuPAQ: An Efficient Planner for Large-scale Predictive Analytic Queriescited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.