Evaluating Data Influence in Meta Learning
As one of the most fundamental models, meta learning aims to effectively address few-shot learning challenges. However, it still faces significant issues related to the training data, such as training inefficiencies due to numerous low-contribution tasks in large datasets and substantial noise from incorrect labels. Thus, training data attribution methods are needed for meta learning. However, the dual-layer structure of mata learning complicates the modeling of training data contributions because of the interdependent influence between meta-parameters and task-specific parameters, making existing data influence evaluation tools inapplicable or inaccurate. To address these challenges, based on the influence function, we propose a general data attribution evaluation framework for meta-learning within the bilevel optimization framework. Our approach introduces task influence functions (task-IF) and instance influence functions (instance-IF) to accurately assess the impact of specific tasks and individual data points in closed forms. This framework comprehensively models data contributions across both the inner and outer training processes, capturing the direct effects of data points on meta-parameters as well as their indirect influence through task-specific parameters. We also provide several strategies to enhance computational efficiency and scalability. Experimental results demonstrate the framework's effectiveness in training data evaluation via several downstream tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Bilevel OptimizationComputational EfficiencyFew-Shot LearningMeta-LearningSimilar Papers 제목 키워드 기반
Meta-material Sensor Based Internet of Things: Design, Optimization, and Implementation
For many applications envisioned for the Internet of Things (IoT), it is expected that the sensors will have very low costs and zero power, which can be satisfied by meta-material sensor based IoT, i.e., meta-IoT. As the…
Unleashing GPT on the Metaverse: Savior or Destroyer?
Incorporating artificial intelligence (AI) technology, particularly large language models (LLMs), is becoming increasingly vital for developing immersive and interactive metaverse experiences. GPT, a representative LLM d…
Language ModellingLarge Language ModelBeyond Accuracy: How AI Metacognitive Sensitivity improves AI-assisted Decision Making
In settings where human decision-making relies on AI input, both the predictive accuracy of the AI system and the reliability of its confidence estimates influence decision quality. We highlight the role of AI metacognit…
Decision MakingEvaluating SAM2's Role in Camouflaged Object Detection: From SAM to SAM2
The Segment Anything Model (SAM), introduced by Meta AI Research as a generic object segmentation model, quickly garnered widespread attention and significantly influenced the academic community. To extend its applicatio…
Image Segmentationobject-detectionObject DetectionSegmentation+1Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations
Spurious correlations in real-world datasets cause machine learning models to rely on irrelevant patterns, undermining reliability, generalization, and fairness. Active learning offers a promising way to address this fai…
Active Learning