mlsanityData to 7 Oct 2026

Neural Lineage

arXiv 2406.11129 ↗First posted 17 Jun 2024cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 53 of its 73 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

53 of 73 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  6. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  7. 2016Learning without Forgettingcited by 2,465
  8. 2013Describing Textures in the Wildcited by 2,110
  9. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  10. 2020Knowledge Distillation: A Surveycited by 1,578
  11. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  12. 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descentcited by 732
38 more
  1. 2023LLM-Pruner: On the Structural Pruning of Large Language Modelscited by 643
  2. 2020Picking Winning Tickets Before Training by Preserving Gradient Flowcited by 467
  3. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  4. 2018Insights on representational similarity in neural networks with canonical correlationcited by 318
  5. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  6. 2015Convergent Learning: Do different neural networks learn the same representations?cited by 215
  7. 2021Dataset Distillation with Infinitely Wide Convolutional Networkscited by 215
  8. 2017EMNIST: an extension of MNIST to handwritten letterscited by 212
  9. 2023DepGraph: Towards Any Structural Pruningcited by 202
  10. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 168
  11. 2020Entangled Watermarks as a Defense against Model Extractioncited by 144
  12. 2021Generalized Shape Metrics on Neural Representationscited by 109
  13. 2018Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goalscited by 103
  14. 2019Deep Neural Network Fingerprinting by Conferrable Adversarial Examplescited by 90
  15. 2020Bayesian Deep Ensembles via the Neural Tangent Kernelcited by 90
  16. 2019Harnessing the Power of Infinitely Wide Deep Nets on Small-data Taskscited by 87
  17. 2022Deep Model Reassemblycited by 78
  18. 2016Satisfying Real-world Goals with Dataset Constraintscited by 68
  19. 2021Representation Topology Divergence: A Method for Comparing Neural Network Representationscited by 66
  20. 2022On the Symmetries of Deep Learning Models and their Internal Representationscited by 63
  21. 2022Factorizing Knowledge in Neural Networkscited by 59
  22. 2022Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbationscited by 58
  23. 2018Geometry Score: A Method For Comparing Generative Adversarial Networkscited by 56
  24. 2017SGD Learns the Conjugate Kernel Class of the Networkcited by 54
  25. 2021What can linearized neural networks actually say about generalization?cited by 49
  26. 2021Defending against Model Stealing via Verifying Embedded External Featurescited by 44
  27. 2019The Shape of Data: Intrinsic Distance for Data Distributionscited by 38
  28. 2018Digital Watermarking for Deep Neural Networkscited by 37
  29. 2021ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detectioncited by 33
  30. 2020Predicting Training Time Without Trainingcited by 22
  31. 2022Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learningcited by 22
  32. 2022Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learningcited by 20
  33. 2022Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?cited by 18
  34. 2022On the Versatile Uses of Partial Distance Correlation in Deep Learningcited by 18
  35. 2021You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownershipcited by 16
  36. 2022MetaV: A Meta-Verifier Approach to Task-Agnostic Model Fingerprintingcited by 16
  37. 2021A Unified Paths Perspective for Pruning at Initializationcited by 14
  38. 2021Structural Watermarking to Deep Neural Networks via Network Channel Pruningcited by 10

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 6.

9 papers.

  1. 2025We Should Chart an Atlas of All the World's Modelscited by 25
  2. 2025A Model Zoo of Vision Transformerscited by 3
  3. 2025Demystifying Singular Defects in Large Language Modelscited by 1
  4. 2026Attesting Model Lineage by Consisted Knowledge Evolution with Fine-Tuning Trajectorycited by 1
  5. 2026The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoderscited by 0
  6. 2026Stemma: Induced Decision Regions Reveal LLM Provenancecited by 0
  7. 2026Scalable Black-Box Model Attribution for Imagescited by 0
  8. 2026TP-CRIV: A Framework for Third-Party Challenge-Response Identity Verification of AI Modelscited by 0
  9. 2026Witeness Overlap: Directional Provenance Inside Open-Weight Model Familiescited by 0