COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
- URL: http://arxiv.org/abs/2403.11348v1
- Date: Sun, 17 Mar 2024 21:23:45 GMT
- Title: COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
- Authors: Mintong Kang, Nezihe Merve Gürel, Linyi Li, Bo Li,
- Abstract summary: Conformal prediction has shown spurring performance in constructing statistically rigorous prediction sets for arbitrary black-box machine learning models.
We propose a certifiably robust learning-reasoning conformal prediction framework (COLEP) via probabilistic circuits.
We show that COLEP achieves 12% up to improvement in certified coverage on GTSRB, 9% on CIFAR-10, and 14% on AwA2.
- Score: 21.140271657387903
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Conformal prediction has shown spurring performance in constructing statistically rigorous prediction sets for arbitrary black-box machine learning models, assuming the data is exchangeable. However, even small adversarial perturbations during the inference can violate the exchangeability assumption, challenge the coverage guarantees, and result in a subsequent decline in empirical coverage. In this work, we propose a certifiably robust learning-reasoning conformal prediction framework (COLEP) via probabilistic circuits, which comprise a data-driven learning component that trains statistical models to learn different semantic concepts, and a reasoning component that encodes knowledge and characterizes the relationships among the trained models for logic reasoning. To achieve exact and efficient reasoning, we employ probabilistic circuits (PCs) within the reasoning component. Theoretically, we provide end-to-end certification of prediction coverage for COLEP in the presence of bounded adversarial perturbations. We also provide certified coverage considering the finite size of the calibration set. Furthermore, we prove that COLEP achieves higher prediction coverage and accuracy over a single model as long as the utilities of knowledge models are non-trivial. Empirically, we show the validity and tightness of our certified coverage, demonstrating the robust conformal prediction of COLEP on various datasets, including GTSRB, CIFAR10, and AwA2. We show that COLEP achieves up to 12% improvement in certified coverage on GTSRB, 9% on CIFAR-10, and 14% on AwA2.
Related papers
- The Penalized Inverse Probability Measure for Conformal Classification [0.5172964916120902]
The work introduces the Penalized Inverse Probability (PIP) nonconformity score, and its regularized version RePIP, that allow the joint optimization of both efficiency and informativeness.
The work shows how PIP-based conformal classifiers exhibit precisely the desired behavior in comparison with other nonconformity measures and strike a good balance between informativeness and efficiency.
arXiv Detail & Related papers (2024-06-13T07:37:16Z) - Robust Conformal Prediction Using Privileged Information [17.886554223172517]
We develop a method to generate prediction sets with a guaranteed coverage rate that is robust to corruptions in the training data.
Our approach builds on conformal prediction, a powerful framework to construct prediction sets that are valid under the i.i.d assumption.
arXiv Detail & Related papers (2024-06-08T08:56:47Z) - Certifiably Byzantine-Robust Federated Conformal Prediction [49.23374238798428]
We introduce a novel framework Rob-FCP, which executes robust federated conformal prediction effectively countering malicious clients.
We empirically demonstrate the robustness of Rob-FCP against diverse proportions of malicious clients under a variety of Byzantine attacks.
arXiv Detail & Related papers (2024-06-04T04:43:30Z) - Conformal Prediction with Learned Features [22.733758606168873]
We propose Partition Learning Conformal Prediction (PLCP) to improve conditional validity of prediction sets.
We implement PLCP efficiently with gradient alternating descent, utilizing off-the-shelf machine learning models.
Our experimental results over four real-world and synthetic datasets show the superior performance of PLCP.
arXiv Detail & Related papers (2024-04-26T15:43:06Z) - Conformal Predictive Systems Under Covariate Shift [2.9310590399782788]
Conformal Predictive Systems (CPS) offer a versatile framework for constructing predictive distributions.
We propose weighted CPS, akin to weighted Conformal Prediction (WCP)
We present theoretical underpinnings and conjectures regarding the validity and efficacy of WCPS.
arXiv Detail & Related papers (2024-04-23T13:23:27Z) - Federated Conformal Predictors for Distributed Uncertainty
Quantification [83.50609351513886]
Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning.
In this paper, we extend conformal prediction to the federated learning setting.
We propose a weaker notion of partial exchangeability, better suited to the FL setting, and use it to develop the Federated Conformal Prediction framework.
arXiv Detail & Related papers (2023-05-27T19:57:27Z) - Evaluating Probabilistic Classifiers: The Triptych [62.997667081978825]
We propose and study a triptych of diagnostic graphics that focus on distinct and complementary aspects of forecast performance.
The reliability diagram addresses calibration, the receiver operating characteristic (ROC) curve diagnoses discrimination ability, and the Murphy diagram visualizes overall predictive performance and value.
arXiv Detail & Related papers (2023-01-25T19:35:23Z) - CC-Cert: A Probabilistic Approach to Certify General Robustness of
Neural Networks [58.29502185344086]
In safety-critical machine learning applications, it is crucial to defend models against adversarial attacks.
It is important to provide provable guarantees for deep learning models against semantically meaningful input transformations.
We propose a new universal probabilistic certification approach based on Chernoff-Cramer bounds.
arXiv Detail & Related papers (2021-09-22T12:46:04Z) - Trust but Verify: Assigning Prediction Credibility by Counterfactual
Constrained Learning [123.3472310767721]
Prediction credibility measures are fundamental in statistics and machine learning.
These measures should account for the wide variety of models used in practice.
The framework developed in this work expresses the credibility as a risk-fit trade-off.
arXiv Detail & Related papers (2020-11-24T19:52:38Z) - Robust Validation: Confident Predictions Even When Distributions Shift [19.327409270934474]
We describe procedures for robust predictive inference, where a model provides uncertainty estimates on its predictions rather than point predictions.
We present a method that produces prediction sets (almost exactly) giving the right coverage level for any test distribution in an $f$-divergence ball around the training population.
An essential component of our methodology is to estimate the amount of expected future data shift and build robustness to it.
arXiv Detail & Related papers (2020-08-10T17:09:16Z) - Evaluating probabilistic classifiers: Reliability diagrams and score
decompositions revisited [68.8204255655161]
We introduce the CORP approach, which generates provably statistically Consistent, Optimally binned, and Reproducible reliability diagrams in an automated way.
Corpor is based on non-parametric isotonic regression and implemented via the Pool-adjacent-violators (PAV) algorithm.
arXiv Detail & Related papers (2020-08-07T08:22:26Z)
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.