Causal Estimation of Memorisation Profiles

• URL: http://arxiv.org/abs/2406.04327v1
• Date: Thu, 6 Jun 2024 17:59:09 GMT
• Title: Causal Estimation of Memorisation Profiles
• Authors: Pietro Lesci, Clara Meister, Thomas Hofmann, Andreas Vlachos, Tiago Pimentel,
• Abstract summary: Understanding memorisation in language models has practical and societal implications. Memorisation is the causal effect of training with an instance on the model's ability to predict that instance. This paper proposes a new, principled, and efficient method to estimate memorisation based on the difference-in-differences design from econometrics.
• Score: 58.20086589761273
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding memorisation in language models has practical and societal implications, e.g., studying models' training dynamics or preventing copyright infringements. Prior work defines memorisation as the causal effect of training with an instance on the model's ability to predict that instance. This definition relies on a counterfactual: the ability to observe what would have happened had the model not seen that instance. Existing methods struggle to provide computationally efficient and accurate estimates of this counterfactual. Further, they often estimate memorisation for a model architecture rather than for a specific model instance. This paper fills an important gap in the literature, proposing a new, principled, and efficient method to estimate memorisation based on the difference-in-differences design from econometrics. Using this method, we characterise a model's memorisation profile--its memorisation trends across training--by only observing its behaviour on a small set of instances throughout training. In experiments with the Pythia model suite, we find that memorisation (i) is stronger and more persistent in larger models, (ii) is determined by data order and learning rate, and (iii) has stable trends across model sizes, thus making memorisation in larger models predictable from smaller ones.

Related papers

• A Hitchhiker's Guide to Scaling Law Estimation [56.06982415792523]
  Scaling laws predict the loss of a target machine learning model by extrapolating from easier-to-train models with fewer parameters or smaller training sets. We estimate more than 1000 scaling laws, then derive a set of best practices for estimating scaling laws in new model families.
  arXiv  Detail & Related papers  (2024-10-15T17:59:10Z)
• A Dynamical Model of Neural Scaling Laws [79.59705237659547]
  We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization. Our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
  arXiv  Detail & Related papers  (2024-02-02T01:41:38Z)
• Specify Robust Causal Representation from Mixed Observations [35.387451486213344]
  Learning representations purely from observations concerns the problem of learning a low-dimensional, compact representation which is beneficial to prediction models. We develop a learning method to learn such representation from observational data by regularizing the learning procedure with mutual information measures. We theoretically and empirically show that the models trained with the learned causal representations are more robust under adversarial attacks and distribution shifts.
  arXiv  Detail & Related papers  (2023-10-21T02:18:35Z)
• What do larger image classifiers memorise? [64.01325988398838]
  We show that training examples exhibit an unexpectedly diverse set of memorisation trajectories across model sizes. We find that knowledge distillation, an effective and popular model compression technique, tends to inhibit memorisation, while also improving generalisation.
  arXiv  Detail & Related papers  (2023-10-09T01:52:07Z)
• On Memorization in Diffusion Models [46.656797890144105]
  We show that memorization behaviors tend to occur on smaller-sized datasets. We quantify the impact of the influential factors on these memorization behaviors in terms of effective model memorization (EMM) Our study holds practical significance for diffusion model users and offers clues to theoretical research in deep generative models.
  arXiv  Detail & Related papers  (2023-10-04T09:04:20Z)
• Training Trajectories of Language Models Across Scales [99.38721327771208]
  Scaling up language models has led to unprecedented performance gains. How do language models of different sizes learn during pre-training? Why do larger language models demonstrate more desirable behaviors?
  arXiv  Detail & Related papers  (2022-12-19T19:16:29Z)
• Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks [38.153825455980645]
  Recent empirical evidence indicates that the practice of overization not only benefits training large models, but also assists - perhaps counterintuitively - building lightweight models. This paper sheds light on these empirical findings by theoretically characterizing the high-dimensional toolsets of model pruning. We analytically identify regimes in which, even if the location of the most informative features is known, we are better off fitting a large model and then pruning.
  arXiv  Detail & Related papers  (2020-12-16T05:13:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.