Influence functions efficiently estimate the effect of removing a single training data point on a model's learned parameters. While influence estimates align well with leave-one-out …
The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to …
Good models require good training data. For overparameterized deep models, the causal relationship between training data and model predictions is increasingly opaque and poorly …
Although mainstream unsupervised anomaly detection (AD) algorithms perform well in academic datasets, their performance is limited in practical application due to the ideal …
Y Kwon, E Wu, K Wu, J Zou - arXiv preprint arXiv:2310.00902, 2023 - arxiv.org
Quantifying the impact of training data points is crucial for understanding the outputs of machine learning models and for improving the transparency of the AI pipeline. The …
Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing task-specific knowledge of the test task, rely only on few-labeled support …
Y Zeng, M Pan, H Jahagirdar, M Jin, L Lyu… - 32nd USENIX Security …, 2023 - usenix.org
External data sources are increasingly being used to train machine learning (ML) models as the data demand increases. However, the integration of external data into training poses …
L Wang, G Jia, N Jiang, H Wu, J Yang - Proceedings of the 30th ACM …, 2022 - dl.acm.org
Facial Expression Recognition (FER) plays a crucial role in the real-world applications. However, large-scale FER datasets collected in the wild usually contain noises. More …
Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because models can easily overfit them. There are many types of label noise, such as symmetric …