Bin Yang

Optimizing AspectJ Dynamic Advices Weaving Based on Aspect-Oriented Call Graph

2015

Abstract: This paper firstly presents an aspect-oriented call graph (ACG for short), then introduces an AspectJ dynamic advices weaving optimizing method based on the ACG (aspect-oriented call graph) of AspectJ programs. Our method firstly solves …

Entropy-based Sample Selection for Online Continual Learning

2020

Deep neural networks (DNNs) suffer from catastrophic forgetting, a rapid decrease in performance when trained on a sequence of tasks where only data of the most recent task is available. Most previous research has focused …

Anomaly Detection Based on Selection and Weighting in Latent Space

2021

With the high requirements of automation in the era of Industry 4.0, anomaly detection plays an increasingly important role in high safety and reliability in the production and manufacturing industry. Recently, autoencoders have been widely …

Spectral Batch Normalization: Normalization in the Frequency Domain

2023

Regularization is a set of techniques that are used to improve the generalization ability of deep neural networks. In this paper, we introduce spectral batch normalization (SBN), a novel effective method to improve generalization by …

RetroGraph: Retrosynthetic Planning with Graph Search

2023 · VBN Forskningsportal (Aalborg Universitet)

The data and checkpoint for "RetroGraph: Retrosynthetic Planning with Graph Search"

Vulnerability Name Prediction Based on Enhanced Multi-Source Domain Adaptation

2023

Software products have brought convenience to modern society but also pose significant security risks due to various types of vulnerabilities. Identifying vulnerability names is vital for program repair and software maintenance, but the lack of …

Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Model

2024 · arXiv (Cornell University)

In practice, domain shifts are likely to occur between training and test data, necessitating domain adaptation (DA) to adjust the pre-trained source model to the target domain. Recently, universal domain adaptation (UniDA) has gained attention …

Assessing Pre-Trained Models for Transfer Learning Through Distribution of Spectral Components

2024 · arXiv (Cornell University)

Pre-trained model assessment for transfer learning aims to identify the optimal candidate for the downstream tasks from a model hub, without the need of time-consuming fine-tuning. Existing advanced works mainly focus on analyzing the intrinsic …

FDAGCL:Feature Discrepancy-Aware Graph Contrastive Learning

2026 · Neural Processing Letters

In recent years, Graph Contrastive Learning (GCL) has emerged as a key research direction for learning representations of unlabeled graph data, focusing on the self-supervised learning of efficient representations for both graphs and nodes. However, …