Search Results

Cloud providers often have resources that are not being fully utilized, and they may offer them at a lower cost to make up for the reduced availability of these resources. However, customers may be hesitant to use such offerings (such as spot VMs) as ...

Graph Neural Networks (GNNs) have shown expressive performance on graph representation learning by aggregating information from neighbors. Recently, some studies have discussed the importance of modeling neighborhood distribution on the graph. However, ...

With a good code search engine, developers can reuse existing code snippets and accelerate software development process. Current code search methods can be divided into two categories: traditional information retrieval (IR) based and deep learning (DL) ...

The recent prevalence of pretrained language models (PLMs) has dramatically shifted the paradigm of semantic parsing, where the mapping from natural language utterances to structured logical forms is now formulated as a Seq2Seq task. Despite the promising ...

Spreadsheets are an important and unique type of business document for data storage, analysis and presentation. The distinction between spreadsheets and most other types of digital documents lies in that spreadsheets provide users with high flexibility of ...

In this paper, we provide a streaming algorithm for the problem of maximizing the sum of a supermodular function and a nonnegative monotone diminishing return submodular (MDR-submodular) function with a knapsack constraint on the integer lattice. ...

This paper considers the capacitated correlation clustering problem with penalties (CCorCwP), which is a new generalization of the correlation clustering problem. In this problem, we are given a complete graph, each edge is either positive or ...$\mathrm{}\mathrm{}\mathrm{}$$\left(\mathrm{},,,\mathrm{},,\mathrm{},,,,\mathrm{},,\right)$$\mathrm{}\mathrm{}\mathrm{}$$\mathrm{}$

Commit messages are natural language descriptions of code changes, which are important for program understanding and maintenance. However, writing commit messages manually is time-consuming and laborious, especially when the code is updated ...

Visualizations themselves have become a data format. Akin to other data formats such as text and images, visualizations are increasingly created, stored, shared, and (re-)used with artificial intelligence (AI) techniques. In this survey, we probe the ...

Regularization can mitigate the generalization gap between training and inference by introducing inductive bias. Existing works have already proposed various inductive biases from diverse perspectives. However, none of them explores inductive bias from ...

Adversarial Training (AT) is one of the most effective defense methods against adversarial examples, in which a model is trained on both clean and adversarial examples. Although AT improves the robustness by smoothing the small neighborhood, it ...

Log parsing, which extracts log templates and parameters, is a critical prerequisite step for automated log analysis techniques. Though existing log parsers have achieved promising accuracy on public log datasets, they still face many challenges when ...

We consider the spherical k-means problem with outliers, an extension of the k-means problem. In this clustering problem, all sample points are on the unit sphere. Given two integers k and z, we can ignore at most z points (outliers) and need to ...

Learning rate is one of the most important hyper-parameters that has significant influence for neural network training. Learning rate schedules are widely used in real practice to adjust the learning rate according to pre-defined schedules for the fast ...

Deep learning-based image embedding methods are typically designed for natural images and may not work for chart images due to their homogeneous regions, which lack variations to hide data both robustly and imperceptibly. In this paper, we propose ...

Spherical k-means clustering as a known NP-hard variant of the k-means problem has broad applications in data mining. In contrast to k-means, it aims to partition a collection of given data distributed on a spherical surface into k sets so as to ...$\mathrm{}\mathrm{}\mathrm{}\mathrm{}$$\mathrm{}\mathrm{}\mathrm{}$

In this paper, we consider the uniform capacitated k-means problem (UC-k-means), an extension of the classical k-means problem (k-means) in machine learning. In the UC-k-means, we are given a set $\mathcal{D}$ of n points in d-dimensional space and an integer ...$\mathcal{}$$\mathcal{}$

Traditional time series prediction methods have shown their outstanding capabilities in time series prediction. However, due to essential differences in volatility characteristics among diverse types of non-stationary multivariate time series (...

In this work, we investigate the problem that maximizes a weakly k-submodular function under the matroid constraint. Different from traditional submodular function maximization, there are k disjoint subsets in k-submodular function optimization, ...$\mathrm{}$$\mathrm{}\mathrm{}$

Causal skeleton learning aims to identify the undirected graph of the underlying causal Bayesian network (BN) from observational data. It plays a pivotal role in causal discovery and many other downstream applications. The methods for causal skeleton ...