Related papers: Extracting Label-specific Key Input Features for N…

Artificial intelligence techniques are increasingly being applied to solve control problems, but often rely on black-box methods without transparent output generation. To improve the interpretability and transparency in control systems,…

Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for learning features relevant to discriminative tasks.…

Low-frequency terms are a recurring challenge for information retrieval models, especially neural IR frameworks struggle with adequately capturing infrequently observed words. While these terms are often removed from neural models - mainly…

In this paper, we propose a novel approach for mining different program features by analysing the internal behaviour of a deep neural network trained on source code. Using an unlabelled dataset of Java programs and three different embedding…

Leveraging privileged information (PI), or features available during training but not at test time, has recently been shown to be an effective method for addressing label noise. However, the reasons for its effectiveness are not well…

There has been considerable recent interest in interpretable concept-based models such as Concept Bottleneck Models (CBMs), which first predict human-interpretable concepts and then map them to output classes. To reduce reliance on…

Instruction-tuned large language models (LLMs) excel at many tasks but often fail to use external tools due to complicated and unfamiliar syntax constraints. While extensive fine-tuning and prompting can mitigate the issue, these approaches…

Machine-learning-based code vulnerability detection (CVD) has progressed rapidly, from deep program representations to pretrained code models and LLM-centered pipelines. Yet dependable vulnerability labeling remains expensive, noisy, and…

In the past years, software reverse engineering dealt with source code understanding. Nowadays, it is levered to software requirements abstract level, supported by feature model notations, language independent, and simpler than the source…

Generative AI enables students to produce plausible code quickly. Producing working code is therefore no longer a reliable indicator of understanding. This is particularly problematic in non-computer-science programmes, where time…

Program semantics learning is the core and fundamental for various code intelligent tasks e.g., vulnerability detection, clone detection. A considerable amount of existing works propose diverse approaches to learn the program semantics for…

One of the most significant challenges in the field of software code auditing is the presence of vulnerabilities in software source code. Every year, more and more software flaws are discovered, either internally in proprietary code or…

Learning neural program embeddings is key to utilizing deep neural networks in program languages research --- precise and efficient program representations enable the application of deep models to a wide range of program analysis tasks.…

Label smoothing is a regularization technique for neural networks. Normally neural models are trained to an output distribution that is a vector with a single 1 for the correct prediction, and 0 for all other elements. Label smoothing…

Structured output prediction problems (e.g., sequential tagging, hierarchical multi-class classification) often involve constraints over the output label space. These constraints interact with the learned models to filter infeasible…

The availability of machine learning systems that can effectively perform arbitrary tasks has led to synthetic labels from these systems being used in applications of statistical inference, such as data analysis or model evaluation. The…

Weakly-supervised anomaly detection aims at learning an anomaly detector from a limited amount of labeled data and abundant unlabeled data. Recent works build deep neural networks for anomaly detection by discriminatively mapping the normal…

Concept Bottleneck Models (CBMs) have garnered increasing attention due to their ability to provide concept-based explanations for black-box deep learning models while achieving high final prediction accuracy using human-like concepts.…

Type systems designed for information-flow control commonly use a program-counter label to track the sensitivity of the context and rule out data leakage arising from effectful computation in a sensitive context. Currently, type-system…

Deep learning models have achieved remarkable success in different areas of machine learning over the past decade; however, the size and complexity of these models make them difficult to understand. In an effort to make them more…