Supervised Learning with Evolving Tasks and Performance Guarantees
Multiple supervised learning scenarios are composed by a sequence of classification tasks. For instance, multi-task learning and continual learning aim to learn a sequence of tasks that is either fixed or grows over time. Existing techniques for learning tasks that are in a sequence are tailored to specific scenarios, lacking adaptability to others. In addition, most of existing techniques consider situations in which the order of the tasks in the sequence is not relevant. However, it is common that tasks in a sequence are evolving in the sense that consecutive tasks often have a higher similarity. This paper presents a learning methodology that is applicable to multiple supervised learning scenarios and adapts to evolving tasks. Differently from existing techniques, we provide computable tight performance guarantees and analytically characterize the increase in the effective sample size. Experiments on benchmark datasets show the performance improvement of the proposed methodology in multiple scenarios and the reliability of the presented performance guarantees.
Code (2)
Tasks
Continual LearningMulti-Task LearningSimilar Papers 제목 키워드 기반
Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees
For a sequence of classification tasks that arrive over time, it is common that tasks are evolving in the sense that consecutive tasks often have a higher similarity. The incremental learning of a growing sequence of tas…
Continual LearningIncremental LearningSEKD: Self-Evolving Keypoint Detection and Description
Researchers have attempted utilizing deep neural network (DNN) to learn novel local features from images inspired by its recent successes on a variety of vision tasks. However, existing DNN-based algorithms have not achi…
Homography EstimationKeypoint DetectionPose EstimationSEVerA: Verified Synthesis of Self-Evolving Agents
Recent advances have shown the effectiveness of self-evolving LLM agents on tasks such as program repair and scientific discovery. In this paradigm, a planner LLM synthesizes an agent program that invokes parametric mode…
Code GenerationProgram RepairUniversum GANs: Improving GANs through contradictions
Limited availability of labeled-data makes any supervised learning problem challenging. Alternative learning settings like semi-supervised and universum learning alleviate the dependency on labeled data, but still requir…
Synthetic Data GenerationTiGer: Self-Supervised Purification for Time-evolving Graphs
Time-evolving graphs, such as social and citation networks, often contain noise that distorts structural and temporal patterns, adversely affecting downstream tasks, such as node classification. Existing purification met…
Node Classification