相关论文: Code Structure Guided Transformer for Source Code …

Models need appropriate inductive biases to effectively learn from small amounts of data and generalize systematically outside of the training distribution. While Transformers are highly versatile and powerful, they can still benefit from…

Source code representations are key in applying machine learning techniques for processing and analyzing programs. A popular approach in representing source code is neural source code embeddings that represents programs with…

Electronic Health Records (EHR) systematically organize patient health data through standardized medical codes, serving as a comprehensive and invaluable source for predictive modeling. Graph neural networks (GNNs) have demonstrated…

Many software analysis methods have come to rely on machine learning approaches. Code segmentation - the process of decomposing source code into meaningful blocks - can augment these methods by featurizing code, reducing noise, and limiting…

In recent years, deep learning models have shown great potential in source code modeling and analysis. Generally, deep learning-based approaches are problem-specific and data-hungry. A challenging issue of these approaches is that they…

Transformers have offered a new methodology of designing neural networks for visual recognition. Compared to convolutional networks, Transformers enjoy the ability of referring to global features at each stage, yet the attention module…

Text encoding is one of the most important steps in Natural Language Processing (NLP). It has been done well by the self-attention mechanism in the current state-of-the-art Transformer encoder, which has brought about significant…

We consider the task of building compact deep learning pipelines suitable for deployment on storage and power constrained mobile devices. We propose a unified framework to learn a broad family of structured parameter matrices that are…

(Source) code summarization is the task of automatically generating natural language summaries (also called comments) for given code snippets. Recently, with the successful application of large language models (LLMs) in numerous fields,…

We study the problem of building generative models of natural source code (NSC); that is, source code written and understood by humans. Our primary contribution is to describe a family of generative models for NSC that have three key…

Transfer learning aims to enhance performance on a target task by using knowledge from related tasks. However, when the source and target tasks are not closely aligned, it can lead to reduced performance, known as negative transfer. Unlike…

In recommender systems, most graph-based methods focus on positive user feedback, while overlooking the valuable negative feedback. Integrating both positive and negative feedback to form a signed graph can lead to a more comprehensive…

Transformer structure, stacked by a sequence of encoder and decoder network layers, achieves significant development in neural machine translation. However, vanilla Transformer mainly exploits the top-layer representation, assuming the…

Graph Neural Networks (GNNs) are widely used in graph data mining tasks. Traditional GNNs follow a message passing scheme that can effectively utilize local and structural information. However, the phenomena of over-smoothing and…

Bidirectional Encoder Representations from Transformers (BERT) represents the latest incarnation of pretrained language models which have recently advanced a wide range of natural language processing tasks. In this paper, we showcase how…

Code LLMs have become extremely popular recently for modeling source code across a variety of tasks, such as generation, translation, and summarization. However, transformer-based models are limited in their capabilities to reason through…

Incorporating hierarchical structures like constituency trees has been shown to be effective for various natural language processing (NLP) tasks. However, it is evident that state-of-the-art (SOTA) sequence-based models like the Transformer…

The presence of software vulnerabilities is an ever-growing issue in software development. In most cases, it is desirable to detect vulnerabilities as early as possible, preferably in a just-in-time manner, when the vulnerable piece is…

Representation learning on text-attributed graphs (TAGs) is vital for real-world applications, as they combine semantic textual and contextual structural information. Research in this field generally consist of two main perspectives:…

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…