We study offline model-based optimization to maximize a black-box object...
Volumetric video, which offers immersive viewing experiences, is gaining...
Although Deep neural networks (DNNs) have shown a strong capacity to sol...
Global urbanization has underscored the significance of urban microclima...
Autonomous individuals establish a structural complex system through pai...
Digital twins have shown a great potential in supporting the development...
With the continuous growth in communication network complexity and traff...
In cellular networks, User Equipment (UE) handoff from one Base Station ...
Detecting illicit nodes on blockchain networks is a valuable task for
st...
Robust, high-precision global localization is fundamental to a wide rang...
Inference time, model size, and accuracy are critical for deploying deep...
Our work examines the way in which large language models can be used for...
Representation learning has been a critical topic in machine learning. I...
Radio Access Networks (RANs) for telecommunications represent large
aggl...
Click-through prediction (CTR) models transform features into latent vec...
Offline model-based optimization aims to maximize a black-box objective
...
Molecular fingerprints are significant cheminformatics tools to map mole...
Diversifying search results is an important research topic in retrieval
...
Model quantization enables the deployment of deep neural networks under
...
Most existing pruning works are resource-intensive, requiring retraining...
Most of the existing works use projection functions for ternary quantiza...
Magnetic Resonance Imaging (MRI) has become an important technique in th...
Under the Autonomous Mobile Clinics (AMCs) initiative, we are developing...
To offer accurate and diverse recommendation services, recent methods us...
Although Deep Neural Networks (DNNs) have shown a strong capacity to sol...
Graph embedding provides a feasible methodology to conduct pattern
class...
In offline model-based optimization, we strive to maximize a black-box
o...
This paper investigates a multi-pair device-to-device (D2D) communicatio...
Learning embedding table plays a fundamental role in Click-through rate(...
Implicit feedback is frequently used for developing personalized
recomme...
Bi-level optimization, especially the gradient-based category, has been
...
The blockchain technology empowers secure, trustless, and privacy-preser...
Implicit feedback is widely leveraged in recommender systems since it is...
Prior research on exposure fairness in the context of recommender system...
Protein representation learning methods have shown great potential to yi...
In recent years, the prevalent online services generate a sheer volume o...
Public policies that supply public goods, especially those involve
colla...
Label noise and class imbalance are two major issues coexisting in real-...
We propose pruning ternary quantization (PTQ), a simple, yet effective,
...
The Graph Convolutional Networks (GCNs) proposed by Kipf and Welling are...
Two-sided marketplaces are an important component of many existing Inter...
Most existing popular methods for learning graph embedding only consider...
Personalized recommender systems are increasingly important as more cont...
Personalized recommender systems are playing an increasingly important r...
Saving lives or economy is a dilemma for epidemic control in most cities...
The graph structure is a commonly used data storage mode, and it turns o...
Building compact convolutional neural networks (CNNs) with reliable
perf...
In this paper, we study the problem of out-of-distribution detection in ...
The chronological order of user-item interactions can reveal time-evolvi...
We propose an approach that connects recurrent networks with different o...