More Like this

1. SemCluster: Clustering of Imperative Programming Assignments based on Quantitative Semantic Features

   https://doi.org/10.1145/3314221.3314629  

   Perry, David M.; Kim, Dohyeong; Samanta, Roopsha; Zhang, Xiangyu (June 2019, Programming Language Design and Implementation)

   A fundamental challenge in automated reasoning about programming assignments at scale is clustering student submissions based on their underlying algorithms. State-of-the-art clustering techniques are sensitive to control structure variations, cannot cluster buggy solutions with similar correct solutions, and either require expensive pair-wise program analyses or training efforts. We propose a novel technique that can cluster small imperative programs based on their algorithmic essence: (A) how the input space is partitioned into equivalence classes and (B) how the problem is uniquely addressed within individual equivalence classes. We capture these algorithmic aspects as two quantitative semantic program features that are merged into a program's vector representation. Programs are then clustered using their vector representations. The computation of our first semantic feature leverages model counting to identify the number of inputs belonging to an input equivalence class. The computation of our second semantic feature abstracts the program's data flow by tracking the number of occurrences of a unique pair of consecutive values of a variable during its lifetime. The comprehensive evaluation of our tool SemCluster on benchmarks drawn from solutions to small programming assignments shows that SemCluster (1) generates far fewer clusters than other clustering techniques, (2) precisely identifies distinct solution strategies, and (3) boosts the performance of clustering-based program repair, all within a reasonable amount of time. 

   more » « less
2. Automatically Extracting OWL Versions of FOL Ontologies

   Hahmann, Torsten; Powell, Robert (October 2021, International Semantic Web Conference (ISWC 2021))

   null (Ed.)

   While OWL and RDF are by far the most popular logic-based languages for Semantic Web Ontologies, some well-designed ontologies are only available in languages with a much richer expressivity, such as first-order logic (FOL) or the ISO standard Common Logic. This inhibits reuse of these ontologies by the wider Semantic Web Community. While converting OWL ontologies to FOL is straightforward, the reverse problem of finding the closest OWL approximation of an FOL ontology is undecidable. However, for most practical purposes, a ``good enough'' OWL approximation need not be perfect to enable wider reuse by the Semantic Web Community. This paper outlines such a conversion approach by first normalizing FOL sentences into a function-free prenex conjunctive normal (FF-PCNF) that strips away minor syntactic differences and then applying a pattern-based approach to identify common OWL axioms. It is tested on the over 2,000 FOL ontologies from the Common Logic Ontology Repository. 

   more » « less
3. Multi-layered self-attention mechanism for weakly supervised semantic segmentation

   https://doi.org/10.1016/j.cviu.2023.103886  

   Yaganapu, Avinash; Kang, Mingon (February 2024, Computer Vision and Image Understanding)

   Weakly Supervised Semantic Segmentation (WSSS) provides efficient solutions for semantic image segmentation using image-level annotations. WSSS requires no pixel-level labeling that Fully Supervised Semantic Segmentation (FSSS) does, which is time-consuming and label-intensive. Most WSSS approaches have leveraged Class Activation Maps (CAM) or Self-Attention (SA) to generate pseudo pixel-level annotations to perform semantic segmentation tasks coupled with fully supervised approaches (e.g., Fully Convolutional Network). However, those approaches often provides incomplete supervision that mainly includes discriminative regions from the last convolutional layer. They may fail to capture regions of low- or intermediate-level features that may not be present in the last convolutional layer. To address the issue, we proposed a novel Multi-layered Self-Attention (Multi-SA) method that applies a self-attention module to multiple convolutional layers, and then stack feature maps from the self-attention layers to generate pseudo pixel-level annotations. We demonstrated that integrated feature maps from multiple self-attention layers produce higher coverage in semantic segmentation than using only the last convolutional layer through intensive experiments using standard benchmark datasets. 

   more » « less
4. NNV2.0: The neural network verification tool

   Diego Manzanas Lopez; Sung Woo Choi; Hoang-Dung Tran; Taylor T. Johnson (July 2023, The 35th International Conference on Computer-Aided Verification)

   This manuscript presents the updated version of the Neural Network Verification (NNV) tool. NNV is a formal verification software tool for deep learning models and cyber-physical systems with neural network components. NNV was first introduced as a verification framework for feedforward and convolutional neural networks, as well as for neural network control systems. Since then, numerous works have made significant improvements in the verification of new deep learning models, as well as tackling some of the scalability issues that may arise when verifying complex models. In this new version of NNV, we introduce verification support for multiple deep learning models, including neural ordinary differential equations, semantic segmentation networks and recurrent neural networks, as well as a collection of reachability methods that aim to reduce the computation cost of reachability analysis of complex neural networks. We have also added direct support for standard input verification formats in the community such as VNNLIB (verification properties), and ONNX (neural networks) formats. We present a collection of experiments in which NNV verifies safety and robustness properties of feedforward, convolutional, semantic segmentation and recurrent neural networks, as well as neural ordinary differential equations and neural network control systems. Furthermore, we demonstrate the capabilities of NNV against a commercially available product in a collection of benchmarks from control systems, semantic segmentation, image classification, and time-series data. 

   more » « less
5. Global ecotypes in the ubiquitous marine clade SAR86

   https://doi.org/10.1038/s41396-019-0516-7  

   Hoarfrost, Adrienne; Nayfach, Stephen; Ladau, Joshua; Yooseph, Shibu; Arnosti, Carol; Dupont, Chris L.; Pollard, Katherine S. (October 2019, The ISME Journal)

   Abstract SAR86 is an abundant and ubiquitous heterotroph in the surface ocean that plays a central role in the function of marine ecosystems. We hypothesized that despite its ubiquity, different SAR86 subgroups may be endemic to specific ocean regions and functionally specialized for unique marine environments. However, the global biogeographical distributions of SAR86 genes, and the manner in which these distributions correlate with marine environments, have not been investigated. We quantified SAR86 gene content across globally distributed metagenomic samples and modeled these gene distributions as a function of 51 environmental variables. We identified five distinct clusters of genes within the SAR86 pangenome, each with a unique geographic distribution associated with specific environmental characteristics. Gene clusters are characterized by the strong taxonomic enrichment of distinct SAR86 genomes and partial assemblies, as well as differential enrichment of certain functional groups, suggesting differing functional and ecological roles of SAR86 ecotypes. We then leveraged our models and high-resolution, remote sensing-derived environmental data to predict the distributions of SAR86 gene clusters across the world’s oceans, creating global maps of SAR86 ecotype distributions. Our results reveal that SAR86 exhibits previously unknown, complex biogeography, and provide a framework for exploring geographic distributions of genetic diversity from other microbial clades. 

   more » « less