Bo Yang

Stream-based Particle Swarm Optimization for data migration decision

2015

As the load in the cloud environment is always changing, data migration become a key technology to realize the load balance of clusters. A good migration decision can make data migration more efficiency. To realize …

On the Effectiveness of Packet Sampling for Early Stage Traffic Identification

2016

Recent years, increasing studies have focused on finding effective machine learning models to identify traffics with the packets at the early stage. Capturing and processing the full packet sequence in a high speed network are …

Enhanced Network Embedding with Text Information

2018

Network embedding aims at learning the low-dimensional and continuous vector representation for each node in networks, which is useful in many real applications. While most existing network embedding methods only focus on the network structure, …

Attention-based Bidirectional Long Short-Term Memory Networks for Relation Classification Using Knowledge Distillation from BERT

2020

Relation classification is an important task in the field of natural language processing. Today the best-performing models often use huge, transformer-based neural architectures like BERT and XLNet and have hundreds of millions of network parameters. …

Study on Reconstruction and Feature Tracking of Silicone Heart 3D Surface

2021 · Sensors

At present, feature-based 3D reconstruction and tracking technology is widely applied in the medical field. In minimally invasive surgery, the surgeon can achieve three-dimensional reconstruction through the images obtained by the endoscope in the human …

Rotation Transformation: A Method to Improve the Transferability of Adversarial Examples

2021

Convolutional neural network models are fragile to adversarial examples. Adding disturbances that humans cannot observe in clean images can make the model classification error. Among the adversarial attack methods, white-box attacks have achieved a high …

OPT-GAN: A Broad-Spectrum Global Optimizer for Black-Box Problems by Learning Distribution

2023 · Proceedings of the AAAI Conference on Artificial Intelligence

Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details. Most classical methods for such problems are based on strong and fixed a priori assumptions, such as Gaussianity. …

Fine-Grained Prototypes Distillation for Few-Shot Object Detection

2024 · arXiv (Cornell University)

Few-shot object detection (FSOD) aims at extending a generic detector for novel object detection with only a few training examples. It attracts great concerns recently due to the practical meanings. Meta-learning has been demonstrated to …

Conditional Uncertainty Quantification for Tensorized Topological Neural Networks

2024 · arXiv (Cornell University)

Graph Neural Networks (GNNs) have become the de facto standard for analyzing graph-structured data, leveraging message-passing techniques to capture both structural and node feature information. However, recent studies have raised concerns about the statistical reliability …