Cross-Loss Influence Functions to Explain Deep Network Representations
As machine learning is increasingly deployed in the real world, it is paramount that we develop the tools necessary to analyze the decision-making of the models we train and deploy to end-users. Recently, researchers have shown that influence functions, a statistical measure of sample impact, can approximate the effects of training samples on classification accuracy for deep neural networks. However, this prior work only applies to supervised learning, where training and testing share an objective function. No approaches currently exist for estimating the influence of unsupervised training examples for deep learning models. To bring explainability to unsupervised and semi-supervised training regimes, we derive the first theoretical and empirical demonstration that influence functions can be extended to handle mismatched training and testing (i.e., "cross-loss") settings. Our formulation enables us to compute the influence in an unsupervised learning setup, explain cluster memberships, and identify and augment biases in language models. Our experiments show that our cross-loss influence estimates even exceed matched-objective influence estimation relative to ground-truth sample impact.
Code (1)
Tasks
Decision MakingLanguage ModellingSelf-Supervised LearningSimilar Papers 제목 키워드 기반
Distance Metric Learning Loss Functions in Few-Shot Scenarios of Supervised Language Models Fine-Tuning
This paper presents an analysis regarding an influence of the Distance Metric Learning (DML) loss functions on the supervised fine-tuning of the language models for classification tasks. We experimented with known datase…
Metric LearningRevisiting the Fragility of Influence Functions
In the last few years, many works have tried to explain the predictions of deep learning models. Few methods, however, have been proposed to verify the accuracy or faithfulness of these explanations. Recently, influence …
Where Did Your Model Learn That? Label-free Influence for Self-supervised Learning
Self-supervised learning (SSL) has revolutionized learning from large-scale unlabeled datasets, yet the intrinsic relationship between pretraining data and the learned representations remains poorly understood. Tradition…
FairnessSelf-Supervised LearningTraceable Spectral Inference via Influence Functions: Efficient Data Attribution and Error Proxies for the Ariel Mission
Interpretability is critical for machine learning models deployed in scientific space missions such as ESA's Ariel, where ground truth is unavailable during operations and physical plausibility must be assessed. While mo…
Targeted Fine-Tuning of DNN-Based Receivers via Influence Functions
We present the first use of influence functions for deep learning-based wireless receivers. Applied to DeepRx, a fully convolutional receiver, influence analysis reveals which training samples drive bit predictions, enab…