Software development plays a crucial role in driving innovation and
effi...
Collaborative filtering (CF) is an important research direction in
recom...
Large Language Models (LLMs) demonstrate exceptional performance in text...
In recent years, attention mechanisms have demonstrated significant pote...
Recently, fine-tuning pre-trained code models such as CodeBERT on downst...
Exploring data is crucial in data analysis, as it helps users understand...
Graph convolutional networks (GCNs) are currently the most promising par...
With the rapid development of the World Wide Web (WWW), heterogeneous gr...
User engagement prediction plays a critical role for designing interacti...
The recent prevalence of pretrained language models (PLMs) has dramatica...
Graph Neural Networks (GNNs) are popular machine learning methods for
mo...
Learning rate is one of the most important hyper-parameters that has a
s...
Graph Neural Networks (GNNs) have shown expressive performance on graph
...
In light of the growing popularity of Exploratory Data Analysis (EDA),
u...
Logical table-to-text generation is a task that involves generating logi...
Third-party libraries (TPLs) are reused frequently in software applicati...
Code search aims to retrieve the most semantically relevant code snippet...
Code search is to search reusable code snippets from source code corpus ...
Commit messages concisely describe the content of code diffs (i.e., code...
Graph Neural Networks (GNNs) have achieved great success on a variety of...
Regularization can mitigate the generalization gap between training and
...
In this paper, we propose FXAM (Fast and eXplainable Additive Model), a
...
Graph Neural Networks (GNNs) are widely used on a variety of graph-based...
Supervised Causal Learning (SCL) aims to learn causal relations from
obs...
Tables store rich numerical data, but numerical reasoning over tables is...
Code summarization aims to generate concise natural language description...
Tables are often created with hierarchies, but existing works on table
r...
Initialization plays a critical role in the training of deep neural netw...
Source code summaries are important for the comprehension and maintenanc...
Commit messages are natural language descriptions of code changes, which...
Recently, deep learning methods have become mainstream in code search si...
Source code summaries are short natural language descriptions of code
sn...
Spreadsheet table detection is the task of detecting all tables on a giv...
Tabular data are ubiquitous for the widespread applications of tables an...
Network Embedding aims to learn a function mapping the nodes to Euclidea...
Tables are widely used with various structures to organize and present d...
It is common for people to create different types of charts to explore a...
Spreadsheets are the most popular end-user programming software, where
f...