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

Constraint Programming (CP) has been successfully used to model and solve complex combinatorial problems. However, modeling is often not trivial and requires expertise, which is a bottleneck to wider adoption. In Constraint Acquisition…

Testing of deep learning models is challenging due to the excessive number and complexity of computations involved. As a result, test data selection is performed manually and in an ad hoc way. This raises the question of how we can…

In supervised classification tasks, models are trained to predict a label for each data point. In real-world datasets, these labels are often noisy due to annotation errors. While the impact of label noise on the performance of deep…

Concept Bottleneck Models (CBMs) use a set of human-interpretable concepts to predict the final task label, enabling domain experts to not only validate the CBM's predictions, but also intervene on incorrect concepts at test time. However,…

Statistical decision algorithms are increasingly deployed in domains where ground-truth labels are hard to obtain, such as hiring, university admissions, and content moderation. In these settings, models are typically trained on historical…

There are several approaches for encoding source code in the input vectors of neural models. These approaches attempt to include various syntactic and semantic features of input programs in their encoding. In this paper, we investigate…

Programs offer compactness and structure that makes them an attractive representation for visual data. We explore how code rewriting can be used to improve systems for inferring programs from visual data. We first propose Sparse…

Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…

Proprietary and closed APIs are becoming increasingly common to process natural language, and are impacting the practical applications of natural language processing, including few-shot classification. Few-shot classification involves…

Supervised learning can be viewed as distilling relevant information from input data into feature representations. This process becomes difficult when supervision is noisy as the distilled information might not be relevant. In fact, recent…

Comments in software are critical for maintenance and reuse. But apart from prescriptive advice, there is little practical support or quantitative understanding of what makes a comment useful. In this paper, we introduce the task of…

Predictive coding has emerged as an influential normative model of neural computation, with numerous extensions and applications. As such, much effort has been put into mapping PC faithfully onto the cortex, but there are issues that remain…

Data-driven software engineering processes, such as vulnerability prediction heavily rely on the quality of the data used. In this paper, we observe that it is infeasible to obtain a noise-free security defect dataset in practice. Despite…

Feature selection aims to identify the optimal feature subset for enhancing downstream models. Effective feature selection can remove redundant features, save computational resources, accelerate the model learning process, and improve the…

Neural network approaches have recently shown to be effective in several information retrieval (IR) tasks. However, neural approaches often require large volumes of training data to perform effectively, which is not always available. To…

Feature discovery from complex unstructured data is fundamentally a reasoning problem: it requires identifying abstractions that are predictive of a target outcome while avoiding leakage, proxies, and post-outcome signals. With the…

When learning an input-output mapping from very few examples, is it better to first infer a latent function that explains the examples, or is it better to directly predict new test outputs, e.g. using a neural network? We study this…

In many wireless application scenarios, acquiring labeled data can be prohibitively costly, requiring complex optimization processes or measurement campaigns. Semi-supervised learning leverages unlabeled samples to augment the available…

We consider scenarios where a very accurate (often small) predictive model using restricted features is available when training a full-featured (often larger) model. This restricted model may be thought of as side-information'', and can…

Binary analysis of software is a critical step in cyber forensics applications such as program vulnerability assessment and malware detection. This involves interpreting instructions executed by software and often necessitates converting…