More Like this

1. GALAXY: Graph-based Active Learning at the Extreme

   Zhang, Jifan; Katz-Samuels, Julian; Nowak, Robert (January 2022, International Conference on Machine Learning)

   Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training. In "open world" settings, the classes of interest can make up a small fraction of the overall dataset -- most of the data may be viewed as an out-of-distribution or irrelevant class. This leads to extreme class-imbalance, and our theory and methods focus on this core issue. We propose a new strategy for active learning called GALAXY (Graph-based Active Learning At the eXtrEme), which blends ideas from graph-based active learning and deep learning. GALAXY automatically and adaptively selects more class-balanced examples for labeling than most other methods for active learning. Our theory shows that GALAXY performs a refined form of uncertainty sampling that gathers a much more class-balanced dataset than vanilla uncertainty sampling. Experimentally, we demonstrate GALAXY's superiority over existing state-of-art deep active learning algorithms in unbalanced vision classification settings generated from popular datasets. 

   more » « less
2. EQUI-VOCAL: Synthesizing Queries for Compositional Video Events from Limited User Interactions

   https://doi.org/10.14778/3611479.3611482  

   Zhang, Enhao; Daum, Maureen; He, Dong; Haynes, Brandon; Krishna, Ranjay; Balazinska, Magdalena (July 2023, Proceedings of the VLDB Endowment)

   We introduce EQUI-VOCAL: a new system that automatically synthesizes queries over videos from limited user interactions. The user only provides a handful of positive and negative examples of what they are looking for. EQUI-VOCAL utilizes these initial examples and additional ones collected through active learning to efficiently synthesize complex user queries. Our approach enables users to find events without database expertise, with limited labeling effort, and without declarative specifications or sketches. Core to EQUI-VOCAL's design is the use of spatio-temporal scene graphs in its data model and query language and a novel query synthesis approach that works on large and noisy video data. Our system outperforms two baseline systems---in terms of F1 score, synthesis time, and robustness to noise---and can flexibly synthesize complex queries that the baselines do not support. 

   more » « less
3. Deep Reinforcement Learning for Procedural Content Generation of 3D Virtual Environments

   https://doi.org/10.1115/1.4046293  

   López, Christian E.; Cunningham, James; Ashour, Omar; Tucker, Conrad S. (October 2020, Journal of Computing and Information Science in Engineering)

   Abstract This work presents a deep reinforcement learning (DRL) approach for procedural content generation (PCG) to automatically generate three-dimensional (3D) virtual environments that users can interact with. The primary objective of PCG methods is to algorithmically generate new content in order to improve user experience. Researchers have started exploring the use of machine learning (ML) methods to generate content. However, these approaches frequently implement supervised ML algorithms that require initial datasets to train their generative models. In contrast, RL algorithms do not require training data to be collected a priori since they take advantage of simulation to train their models. Considering the advantages of RL algorithms, this work presents a method that generates new 3D virtual environments by training an RL agent using a 3D simulation platform. This work extends the authors’ previous work and presents the results of a case study that supports the capability of the proposed method to generate new 3D virtual environments. The ability to automatically generate new content has the potential to maintain users’ engagement in a wide variety of applications such as virtual reality applications for education and training, and engineering conceptual design. 

   more » « less
4. Direct Acquisition Optimization for Low-Budget Active Learning

   Zhao, Z; Jiang, Y; Chen, Y (December 2024, Workshop on Bayesian Decision-making and Uncertainty, 38th Conference on Neural Information Processing Systems (NeurIPS 2024))

   Active Learning (AL) has gained prominence in integrating data-intensive machine learning (ML) models into domains with limited labeled data. However, its effectiveness diminishes significantly when the labeling budget is low. In this paper, we first empirically observe the performance degradation of existing AL algorithms in the low-budget settings, and then introduce Direct Acquisition Optimization (DAO), a novel AL algorithm that optimizes sample selections based on expected true loss reduction. Specifically, DAO utilizes influence functions to update model parameters and incorporates an additional acquisition strategy to mitigate bias in loss estimation. This approach facilitates a more accurate estimation of the overall error reduction, without extensive computations or reliance on labeled data. Experiments demonstrate DAO's effectiveness in low budget settings, outperforming state-of-the-arts approaches across seven benchmarks. 

   more » « less
5. Similarity Search for Efficient Active Learning and Search of Rare Concepts

   Coleman Cody; Chou, Edward; Katz-Samuels, Julian; Culatana, Sean; Bailis, Peter; Berg, Alexander C.; Nowak, Robert; Sumbaly, Roshan; Zaharia, Matei; Yalniz, I. Zeki (January 2022, Proceedings of the AAAI Conference on Artificial Intelligence)

   Many active learning and search approaches are intractable for large-scale industrial settings with billions of unlabeled examples. Existing approaches search globally for the optimal examples to label, scaling linearly or even quadratically with the unlabeled data. In this paper, we improve the computational efficiency of active learning and search methods by restricting the candidate pool for labeling to the nearest neighbors of the currently labeled set instead of scanning over all of the unlabeled data. We evaluate several selection strategies in this setting on three large-scale computer vision datasets: ImageNet, OpenImages, and a de-identified and aggregated dataset of 10 billion publicly shared images provided by a large internet company. Our approach achieved similar mean average precision and recall as the traditional global approach while reducing the computational cost of selection by up to three orders of magnitude, enabling web-scale active learning. 

   more » « less