Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
PL4XGL: A Programming Language Approach to Explainable Graph Learning
Proceedings of the ACM on Programming Languages (PACMPL), Volume 8, Issue PLDIArticle No.: 234, Pages 2148–2173https://doi.org/10.1145/3656464In this article, we present a new, language-based approach to explainable graph learning. Though graph neural networks (GNNs) have shown impressive performance in various graph learning tasks, they have severe limitations in explainability, hindering ...
Compiling Probabilistic Programs for Variable Elimination with Information Flow
Proceedings of the ACM on Programming Languages (PACMPL), Volume 8, Issue PLDIArticle No.: 218, Pages 1755–1780https://doi.org/10.1145/3656448A key promise of probabilistic programming is the ability to specify rich models using an expressive program- ming language. However, the expressive power that makes probabilistic programming languages enticing also poses challenges to inference, so much ...
Input-Relational Verification of Deep Neural Networks
Proceedings of the ACM on Programming Languages (PACMPL), Volume 8, Issue PLDIArticle No.: 147, Pages 1–27https://doi.org/10.1145/3656377We consider the verification of input-relational properties defined over deep neural networks (DNNs) such as robustness against universal adversarial perturbations, monotonicity, etc. Precise verification of these properties requires reasoning about ...
- research-articleApril 2024
Verification of Neural Networks’ Global Robustness
Proceedings of the ACM on Programming Languages (PACMPL), Volume 8, Issue OOPSLA1Article No.: 130, Pages 1010–1039https://doi.org/10.1145/3649847Neural networks are successful in various applications but are also susceptible to adversarial attacks. To show the safety of network classifiers, many verifiers have been introduced to reason about the local robustness of a given input to a given ...
Quarl: A Learning-Based Quantum Circuit Optimizer
Proceedings of the ACM on Programming Languages (PACMPL), Volume 8, Issue OOPSLA1Article No.: 114, Pages 555–582https://doi.org/10.1145/3649831Optimizing quantum circuits is challenging due to the very large search space of functionally equivalent circuits and the necessity of applying transformations that temporarily decrease performance to achieve a final performance improvement. This paper ...
-
- research-articleApril 2024
Evaluating the Effectiveness of Deep Learning Models for Foundational Program Analysis Tasks
Proceedings of the ACM on Programming Languages (PACMPL), Volume 8, Issue OOPSLA1Article No.: 112, Pages 500–528https://doi.org/10.1145/3649829While deep neural networks provide state-of-the-art solutions to a wide range of programming language tasks, their effectiveness in dealing with foundational program analysis tasks remains under explored. In this paper, we present an empirical study that ...
- research-articleApril 2024
A Learning-Based Approach to Static Program Slicing
Proceedings of the ACM on Programming Languages (PACMPL), Volume 8, Issue OOPSLA1Article No.: 97, Pages 83–109https://doi.org/10.1145/3649814Traditional program slicing techniques are crucial for early bug detection and manual/automated debugging of online code snippets. Nevertheless, their inability to handle incomplete code hinders their real-world applicability in such scenarios. To ...
- research-articleJanuary 2024
ReLU Hull Approximation
Proceedings of the ACM on Programming Languages (PACMPL), Volume 8, Issue POPLArticle No.: 75, Pages 2260–2287https://doi.org/10.1145/3632917Convex hulls are commonly used to tackle the non-linearity of activation functions in the verification of neural networks. Computing the exact convex hull is a costly task though. In this work, we propose a fast and precise approach to over-approximating ...
- research-articleOctober 2023
Perception Contracts for Safety of ML-Enabled Systems
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue OOPSLA2Article No.: 299, Pages 2196–2223https://doi.org/10.1145/3622875We introduce a novel notion of perception contracts to reason about the safety of controllers that interact with an environment using neural perception. Perception contracts capture errors in ground-truth estimations that preserve invariants when systems ...
Turaco: Complexity-Guided Data Sampling for Training Neural Surrogates of Programs
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue OOPSLA2Article No.: 280, Pages 1648–1676https://doi.org/10.1145/3622856Programmers and researchers are increasingly developing surrogates of programs, models of a subset of the observable behavior of a given program, to solve a variety of software development challenges. Programmers train surrogates from measurements of ...
- research-articleOctober 2023
An Explanation Method for Models of Code
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue OOPSLA2Article No.: 250, Pages 801–827https://doi.org/10.1145/3622826This paper introduces a novel method, called WheaCha, for explaining the predictions of code models. Similar to attribution methods, WheaCha seeks to identify input features that are responsible for a particular prediction that models make. On the ...
- research-articleOctober 2023
Run-Time Prevention of Software Integration Failures of Machine Learning APIs
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue OOPSLA2Article No.: 231, Pages 264–291https://doi.org/10.1145/3622806Due to the under-specified interfaces, developers face challenges in correctly integrating machine learning (ML) APIs in software. Even when the ML API and the software are well designed on their own, the resulting application misbehaves when the API ...
Formal Specification and Testing for Reinforcement Learning
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue ICFPArticle No.: 193, Pages 125–158https://doi.org/10.1145/3607835The development process for reinforcement learning applications is still exploratory rather than systematic. This exploratory nature reduces reuse of specifications between applications and increases the chances of introducing programming errors. This ...
Register Tiling for Unstructured Sparsity in Neural Network Inference
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue PLDIArticle No.: 188, Pages 1995–2020https://doi.org/10.1145/3591302Unstructured sparse neural networks are an important class of machine learning (ML) models, as they compact model size and reduce floating point operations. The execution time of these models is frequently dominated by the sparse matrix multiplication ...
- research-articleJune 2023
One Pixel Adversarial Attacks via Sketched Programs
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue PLDIArticle No.: 187, Pages 1970–1994https://doi.org/10.1145/3591301Neural networks are successful in various tasks but are also susceptible to adversarial examples. An adversarial example is generated by adding a small perturbation to a correctly-classified input with the goal of causing a network classifier to ...
Prompting Is Programming: A Query Language for Large Language Models
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue PLDIArticle No.: 186, Pages 1946–1969https://doi.org/10.1145/3591300Large language models have demonstrated outstanding performance on a wide range of tasks such as question answering and code generation. On a high level, given an input, a language model can be used to automatically complete the sequence in a ...
Incremental Verification of Neural Networks
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue PLDIArticle No.: 185, Pages 1920–1945https://doi.org/10.1145/3591299Complete verification of deep neural networks (DNNs) can exactly determine whether the DNN satisfies a desired trustworthy property (e.g., robustness, fairness) on an infinite set of inputs or not. Despite the tremendous progress to improve the ...
Scallop: A Language for Neurosymbolic Programming
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue PLDIArticle No.: 166, Pages 1463–1487https://doi.org/10.1145/3591280We present Scallop, a language which combines the benefits of deep learning and logical reasoning. Scallop enables users to write a wide range of neurosymbolic applications and train them in a data- and compute-efficient manner. It achieves these ...
Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networks
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue PLDIArticle No.: 138, Pages 786–810https://doi.org/10.1145/3591252We present a new abstract interpretation framework for the precise over-approximation of numerical fixpoint iterators. Our key observation is that unlike in standard abstract interpretation (AI), typically used to over-approximate all reachable ...
Architecture-Preserving Provable Repair of Deep Neural Networks
Proceedings of the ACM on Programming Languages (PACMPL), Volume 7, Issue PLDIArticle No.: 124, Pages 443–467https://doi.org/10.1145/3591238Deep neural networks (DNNs) are becoming increasingly important components of software, and are considered the state-of-the-art solution for a number of problems, such as image recognition. However, DNNs are far from infallible, and incorrect ...