PUMA: Performance Unchanged Model Augmentation for Training Data Removal
Preserving the performance of a trained model while removing unique characteristics of marked training data points is challenging. Recent research usually suggests retraining a model from scratch with remaining training data or refining the model by reverting the model optimization on the marked data points. Unfortunately, aside from their computational inefficiency, those approaches inevitably hurt the resulting model's generalization ability since they remove not only unique characteristics but also discard shared (and possibly contributive) information. To address the performance degradation problem, this paper presents a novel approach called Performance Unchanged Model Augmentation~(PUMA). The proposed PUMA framework explicitly models the influence of each training data point on the model's generalization ability with respect to various performance criteria. It then complements the negative impact of removing marked data by reweighting the remaining data optimally. To demonstrate the effectiveness of the PUMA framework, we compared it with multiple state-of-the-art data removal techniques in the experiments, where we show the PUMA can effectively and efficiently remove the unique characteristics of marked training data without retraining the model that can 1) fool a membership attack, and 2) resist performance degradation. In addition, as PUMA estimates the data importance during its operation, we show it could serve to debug mislabelled data points more efficiently than existing approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
Model OptimizationSimilar Papers 제목 키워드 기반
Update 3.0 to “PuMA: The Porous Microstructure Analysis software”
A major update of the Porous Microstructure Analysis (PuMA) software is presented. PuMA is a framework for computing effective material properties and response based on material microstructures. Version 3.0 of the softwa…
Computed Tomography (CT)Physical SimulationsPUMA: margin-based data pruning
Deep learning has been able to outperform humans in terms of classification accuracy in many tasks. However, to achieve robustness to adversarial perturbations, the best methodologies require to perform adversarial train…
PUMA: Empowering Unified MLLM with Multi-granular Visual Generation
Recent advancements in multimodal foundation models have yielded significant progress in vision-language understanding. Initial attempts have also explored the potential of multimodal large language models (MLLMs) for vi…
DiversityImage GenerationImage ManipulationText to Image Generation+1Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training
Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces. By generating sequences in any order and allowing for parallel decoding, they enable fast inference and stro…
PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensation
When handling streaming graphs, existing graph representation learning models encounter a catastrophic forgetting problem, where previously learned knowledge of these models is easily overwritten when learning with newly…
Continual LearningGraph LearningGraph Representation LearningNode Classification+1