CUAL: Continual Uncertainty-aware Active Learner

• URL: http://arxiv.org/abs/2412.09701v1
• Date: Thu, 12 Dec 2024 19:49:09 GMT
• Title: CUAL: Continual Uncertainty-aware Active Learner
• Authors: Amanda Rios, Ibrahima Ndiour, Parual Datta, Jerry Sydir, Omesh Tickoo, Nilesh Ahuja,
• Abstract summary: A deployed AI agent is continuously provided with unlabeled data that may contain not only unseen samples of known classes but also samples from novel (unknown) classes. We present a comprehensive solution to this complex problem with our model "CUAL" (Continual Uncertainty-aware Active Learner) CUAL leverages an uncertainty estimation algorithm to prioritize active labeling of ambiguous (uncertain) predicted novel class samples while also simultaneously pseudo-labeling the most certain predictions of each class.
• Score: 5.678185894553588
• License:
• Abstract: AI deployed in many real-world use cases should be capable of adapting to novelties encountered after deployment. Here, we consider a challenging, under-explored and realistic continual adaptation problem: a deployed AI agent is continuously provided with unlabeled data that may contain not only unseen samples of known classes but also samples from novel (unknown) classes. In such a challenging setting, it has only a tiny labeling budget to query the most informative samples to help it continuously learn. We present a comprehensive solution to this complex problem with our model "CUAL" (Continual Uncertainty-aware Active Learner). CUAL leverages an uncertainty estimation algorithm to prioritize active labeling of ambiguous (uncertain) predicted novel class samples while also simultaneously pseudo-labeling the most certain predictions of each class. Evaluations across multiple datasets, ablations, settings and backbones (e.g. ViT foundation model) demonstrate our method's effectiveness. We will release our code upon acceptance.

Related papers

• Uncertainty Quantification in Continual Open-World Learning [5.268548403469063]
  In the field of continual learning, the reliance on novelty and labeling oracles is commonplace albeit unrealistic. We propose our method COUQ "Continual Open-world Uncertainty Quantification", an iterative uncertainty estimation algorithm tailored for learning. We demonstrate the effectiveness of our method across multiple datasets, ablations, backbones and performance superior to state-of-the-art.
  arXiv  Detail & Related papers  (2024-12-21T00:09:20Z)
• Probably Approximately Precision and Recall Learning [62.912015491907994]
  Precision and Recall are foundational metrics in machine learning. One-sided feedback--where only positive examples are observed during training--is inherent in many practical problems. We introduce a PAC learning framework where each hypothesis is represented by a graph, with edges indicating positive interactions.
  arXiv  Detail & Related papers  (2024-11-20T04:21:07Z)
• Evaluating the Efficacy of Instance Incremental vs. Batch Learning in Delayed Label Environments: An Empirical Study on Tabular Data Streaming for Fraud Detection [0.13980986259786224]
  In real-world scenarios, such as fraud detection or credit scoring, labels may be delayed. batch incremental algorithms are widely used in many real-world tasks. Our findings indicate that instance incremental learning is not the superior option.
  arXiv  Detail & Related papers  (2024-09-16T09:20:01Z)
• Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels [63.16824565919966]
  This paper proposes to use confusing samples proactively without label correction. A Virtual Category (VC) is assigned to each confusing sample in such a way that it can safely contribute to the model optimisation. Our intriguing findings highlight the usage of VC learning in dense vision tasks.
  arXiv  Detail & Related papers  (2023-12-02T16:23:52Z)
• Overcoming Overconfidence for Active Learning [1.2776312584227847]
  We present two novel methods to address the problem of overconfidence that arises in the active learning scenario. The first is an augmentation strategy named Cross-Mix-and-Mix (CMaM), which aims to calibrate the model by expanding the limited training distribution. The second is a selection strategy named Ranked Margin Sampling (RankedMS), which prevents choosing data that leads to overly confident predictions.
  arXiv  Detail & Related papers  (2023-08-21T09:04:54Z)
• ASPEST: Bridging the Gap Between Active Learning and Selective Prediction [56.001808843574395]
  Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. Active learning aims to lower the overall labeling effort, and hence human dependence, by querying the most informative examples. In this work, we introduce a new learning paradigm, active selective prediction, which aims to query more informative samples from the shifted target domain.
  arXiv  Detail & Related papers  (2023-04-07T23:51:07Z)
• Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery [76.63807209414789]
  We challenge the status quo in class-iNCD and propose a learning paradigm where class discovery occurs continuously and truly unsupervisedly. We propose simple baselines, composed of a frozen PTM backbone and a learnable linear classifier, that are not only simple to implement but also resilient under longer learning scenarios.
  arXiv  Detail & Related papers  (2023-03-28T13:47:16Z)
• Low-Regret Active learning [64.36270166907788]
  We develop an online learning algorithm for identifying unlabeled data points that are most informative for training. At the core of our work is an efficient algorithm for sleeping experts that is tailored to achieve low regret on predictable (easy) instances.
  arXiv  Detail & Related papers  (2021-04-06T22:53:45Z)
• Deep Active Learning via Open Set Recognition [0.0]
  In many applications, data is easy to acquire but expensive and time-consuming to label prominent examples. We formulate active learning as an open-set recognition problem. Unlike current active learning methods, our algorithm can learn tasks without the need for task labels.
  arXiv  Detail & Related papers  (2020-07-04T22:09:17Z)
• Progressive Identification of True Labels for Partial-Label Learning [112.94467491335611]
  Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label. Most existing methods elaborately designed as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data. This paper proposes a novel framework of classifier with flexibility on the model and optimization algorithm.
  arXiv  Detail & Related papers  (2020-02-19T08:35:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.