Using Contrastive Learning with Generative Similarity to Learn Spaces that Capture Human Inductive Biases
- URL: http://arxiv.org/abs/2405.19420v1
- Date: Wed, 29 May 2024 18:01:58 GMT
- Title: Using Contrastive Learning with Generative Similarity to Learn Spaces that Capture Human Inductive Biases
- Authors: Raja Marjieh, Sreejan Kumar, Declan Campbell, Liyi Zhang, Gianluca Bencomo, Jake Snell, Thomas L. Griffiths,
- Abstract summary: Humans rely on strong inductive biases to learn from few examples and abstract useful information from sensory data.
We introduce a notion of generative similarity whereby two datapoints are considered similar if they are likely to have been sampled from the same distribution.
We show that generative similarity can be used to define a contrastive learning objective even when its exact form is intractable.
- Score: 9.63129238638334
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Humans rely on strong inductive biases to learn from few examples and abstract useful information from sensory data. Instilling such biases in machine learning models has been shown to improve their performance on various benchmarks including few-shot learning, robustness, and alignment. However, finding effective training procedures to achieve that goal can be challenging as psychologically-rich training data such as human similarity judgments are expensive to scale, and Bayesian models of human inductive biases are often intractable for complex, realistic domains. Here, we address this challenge by introducing a Bayesian notion of generative similarity whereby two datapoints are considered similar if they are likely to have been sampled from the same distribution. This measure can be applied to complex generative processes, including probabilistic programs. We show that generative similarity can be used to define a contrastive learning objective even when its exact form is intractable, enabling learning of spatial embeddings that express specific inductive biases. We demonstrate the utility of our approach by showing how it can be used to capture human inductive biases for geometric shapes, and to better distinguish different abstract drawing styles that are parameterized by probabilistic programs.
Related papers
- Latent Traversals in Generative Models as Potential Flows [113.4232528843775]
We propose to model latent structures with a learned dynamic potential landscape.
Inspired by physics, optimal transport, and neuroscience, these potential landscapes are learned as physically realistic partial differential equations.
Our method achieves both more qualitatively and quantitatively disentangled trajectories than state-of-the-art baselines.
arXiv Detail & Related papers (2023-04-25T15:53:45Z) - Masked prediction tasks: a parameter identifiability view [49.533046139235466]
We focus on the widely used self-supervised learning method of predicting masked tokens.
We show that there is a rich landscape of possibilities, out of which some prediction tasks yield identifiability, while others do not.
arXiv Detail & Related papers (2022-02-18T17:09:32Z) - Predicting Human Similarity Judgments Using Large Language Models [13.33450619901885]
We propose an efficient procedure for predicting similarity judgments based on text descriptions.
The number of descriptions required grows only linearly with the number of stimuli, drastically reducing the amount of data required.
We test this procedure on six datasets of naturalistic images and show that our models outperform previous approaches based on visual information.
arXiv Detail & Related papers (2022-02-09T21:09:25Z) - Exploring Alignment of Representations with Human Perception [47.53970721813083]
We show that inputs that are mapped to similar representations by the model should be perceived similarly by humans.
Our approach yields a measure of the extent to which a model is aligned with human perception.
We find that various properties of a model like its architecture, training paradigm, training loss, and data augmentation play a significant role in learning representations that are aligned with human perception.
arXiv Detail & Related papers (2021-11-29T17:26:50Z) - Discriminative Attribution from Counterfactuals [64.94009515033984]
We present a method for neural network interpretability by combining feature attribution with counterfactual explanations.
We show that this method can be used to quantitatively evaluate the performance of feature attribution methods in an objective manner.
arXiv Detail & Related papers (2021-09-28T00:53:34Z) - Understanding Robustness in Teacher-Student Setting: A New Perspective [42.746182547068265]
Adrial examples are machine learning models where bounded adversarial perturbation could mislead the models to make arbitrarily incorrect predictions.
Extensive studies try to explain the existence of adversarial examples and provide ways to improve model robustness.
Our studies could shed light on the future exploration about adversarial examples, and enhancing model robustness via principled data augmentation.
arXiv Detail & Related papers (2021-02-25T20:54:24Z) - Distilling Interpretable Models into Human-Readable Code [71.11328360614479]
Human-readability is an important and desirable standard for machine-learned model interpretability.
We propose to train interpretable models using conventional methods, and then distill them into concise, human-readable code.
We describe a piecewise-linear curve-fitting algorithm that produces high-quality results efficiently and reliably across a broad range of use cases.
arXiv Detail & Related papers (2021-01-21T01:46:36Z) - Few-shot Visual Reasoning with Meta-analogical Contrastive Learning [141.2562447971]
We propose to solve a few-shot (or low-shot) visual reasoning problem, by resorting to analogical reasoning.
We extract structural relationships between elements in both domains, and enforce them to be as similar as possible with analogical learning.
We validate our method on RAVEN dataset, on which it outperforms state-of-the-art method, with larger gains when the training data is scarce.
arXiv Detail & Related papers (2020-07-23T14:00:34Z) - Plausible Counterfactuals: Auditing Deep Learning Classifiers with
Realistic Adversarial Examples [84.8370546614042]
Black-box nature of Deep Learning models has posed unanswered questions about what they learn from data.
Generative Adversarial Network (GAN) and multi-objectives are used to furnish a plausible attack to the audited model.
Its utility is showcased within a human face classification task, unveiling the enormous potential of the proposed framework.
arXiv Detail & Related papers (2020-03-25T11:08:56Z) - On Contrastive Learning for Likelihood-free Inference [20.49671736540948]
Likelihood-free methods perform parameter inference in simulator models where evaluating the likelihood is intractable.
One class of methods for this likelihood-free problem uses a classifier to distinguish between pairs of parameter-observation samples.
Another popular class of methods fits a conditional distribution to the parameter posterior directly, and a particular recent variant allows for the use of flexible neural density estimators.
arXiv Detail & Related papers (2020-02-10T13:14:01Z)
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.