# Collaborative Intelligence Orchestration: Inconsistency-Based Fusion of Semi-Supervised Learning and Active Learning

arXiv: https://arxiv.org/abs/2206.03288 · HTML: https://mlsanity.com/paper/2206.03288/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 7 Jun 2022.

## Builds on (most cited first, 22 of 22)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification](https://mlsanity.com/paper/2004.12239/) (2020)
- [Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost](https://mlsanity.com/paper/1910.07153/) (2019)
- [Uncertainty-guided Continual Learning with Bayesian Neural Networks](https://mlsanity.com/paper/1906.02425/) (2019)
- [Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study](https://mlsanity.com/paper/1808.05697/) (2018)
- [Task-Aware Variational Adversarial Active Learning](https://mlsanity.com/paper/2002.04709/) (2020)
- [Distinguish Confusing Law Articles for Legal Judgment Prediction](https://mlsanity.com/paper/2004.02557/) (2020)
- [State-Relabeling Adversarial Active Learning](https://mlsanity.com/paper/2004.04943/) (2020)
- [Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning](https://mlsanity.com/paper/2203.13049/) (2022)
- [Bayesian Generative Active Deep Learning](https://mlsanity.com/paper/1904.11643/) (2019)
- [Adversarial Sampling for Active Learning](https://mlsanity.com/paper/1808.06671/) (2018)
- [Consensus Graph Representation Learning for Better Grounded Image Captioning](https://mlsanity.com/paper/2112.00974/) (2021)
- [MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning](https://mlsanity.com/paper/2112.06558/) (2021)
- [End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding](https://mlsanity.com/paper/2203.08013/) (2022)
- [Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference](https://mlsanity.com/paper/2107.12270/) (2021)
- [Combining MixMatch and Active Learning for Better Accuracy with Fewer Labels](https://mlsanity.com/paper/1912.00594/) (2019)

## Built on by (most cited first, 2 of 2)

- [Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos](https://mlsanity.com/paper/2208.01954/) (2022)
- [Benchmarking of Query Strategies: Towards Future Deep Active Learning](https://mlsanity.com/paper/2312.05751/) (2023)

## Abstract (arXiv)

While annotating decent amounts of data to satisfy sophisticated learning models can be cost-prohibitive for many real-world applications. Active learning (AL) and semi-supervised learning (SSL) are two effective, but often isolated, means to alleviate the data-hungry problem. Some recent studies explored the potential of combining AL and SSL to better probe the unlabeled data. However, almost all these contemporary SSL-AL works use a simple combination strategy, ignoring SSL and AL's inherent relation. Further, other methods suffer from high computational costs when dealing with large-scale, high-dimensional datasets. Motivated by the industry practice of labeling data, we propose an innovative Inconsistency-based virtual aDvErsarial Active Learning (IDEAL) algorithm to further investigate SSL-AL's potential superiority and achieve mutual enhancement of AL and SSL, i.e., SSL propagates label information to unlabeled samples and provides smoothed embeddings for AL, while AL excludes samples with inconsistent predictions and considerable uncertainty for SSL. We estimate unlabeled samples' inconsistency by augmentation strategies of different granularities, including fine-grained continuous perturbation exploration and coarse-grained data transformations. Extensive experiments, in both text and image domains, validate the effectiveness of the proposed algorithm, comparing it against state-of-the-art baselines. Two real-world case studies visualize the practical industrial value of applying and deploying the proposed data sampling algorithm.