CVJun 17, 2024

Neural Lineage

arXiv:2406.11129v17 citations
Originality Incremental advance
AI Analysis

This addresses the problem of model provenance and accountability in machine learning, but it is incremental as it builds on existing similarity metrics and fine-tuning concepts.

The paper tackles the problem of identifying lineage relationships between neural networks, specifically determining which parent model a child model was fine-tuned from, and shows that their proposed learning-free and learning-based methods outperform baselines in various settings and can trace cross-generational lineage.

Given a well-behaved neural network, is possible to identify its parent, based on which it was tuned? In this paper, we introduce a novel task known as neural lineage detection, aiming at discovering lineage relationships between parent and child models. Specifically, from a set of parent models, neural lineage detection predicts which parent model a child model has been fine-tuned from. We propose two approaches to address this task. (1) For practical convenience, we introduce a learning-free approach, which integrates an approximation of the finetuning process into the neural network representation similarity metrics, leading to a similarity-based lineage detection scheme. (2) For the pursuit of accuracy, we introduce a learning-based lineage detector comprising encoders and a transformer detector. Through experimentation, we have validated that our proposed learning-free and learning-based methods outperform the baseline in various learning settings and are adaptable to a variety of visual models. Moreover, they also exhibit the ability to trace cross-generational lineage, identifying not only parent models but also their ancestors.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes