An Invisible, Robust Protection Method for DNN-Generated Content

Information Science, Artificial Intelligence,
deep neural networks   invisible perturbation   protection technique   robustness   generated content   image encoding   social media  

Invisible and Robust Protection Method for Content Generated by Deep Neural Networks Academic Background In recent years, with the revolutionary development and widespread application of deep learning models in engineering applications, phenomenon-level applications such as ChatGPT and DALL⋅E 2 have emerged, profoundly impacting people’s daily live...

m𝟐ixkg: Mixing for harder negative samples in knowledge graph

Information Science, Computer Science, Artificial Intelligence,
knowledge graph   negative sampling   embedding   mixing operation   entities  

Academic Report Background A Knowledge Graph (KG) is structured data that records information about entities and relationships, widely used in question-answering systems, information retrieval, machine reading, and other fields. Knowledge Graph Embedding (KGE) technology maps entities and relationships in the graph into a low-dimensional dense vect...

Exploring Adaptive Inter-Sample Relationship in Data-Free Knowledge Distillation

Information Science, Artificial Intelligence,
data-free knowledge distillation   unsupervised representation learning   knowledge distillation   adaptive methods   inter-sample relationship  

In recent years, applications such as privacy protection and large-scale data transmission have posed significant challenges to the inaccessibility of data. Researchers have proposed Data-Free Knowledge Distillation (DFKD) methods to address these issues. Knowledge Distillation (KD) is a method for training a lightweight model (student model) to le...

Modeling Bellman-Error with Logistic Distribution with Applications in Reinforcement Learning

Mathematics, Information Science, Artificial Intelligence,
reinforcement learning   logistic distribution   reward scaling   bellman error  

Background and Research Objectives Reinforcement Learning (RL) has recently become a dynamic and transformative field within artificial intelligence, aiming to maximize cumulative rewards through the interaction between agents and the environment. However, the application of RL faces challenges in optimizing the Bellman Error. This error is particu...

Structure Enhanced Prototypical Alignment for Unsupervised Cross-Domain Node Classification

Information Science, Automation, Artificial Intelligence,
Graph Neural Networks   Node Classification   Graph Domain Adaptation   Transfer Learning   Unsupervised Learning  

Structurally Enhanced Prototype Alignment for Unsupervised Cross-Domain Node Classification Introduction With the advancement of modern information technology, Graph Neural Networks (GNNs) have demonstrated significant success in handling complex network node classification tasks. However, one key challenge is the need for a large amount of high-qu...

Unsupervised Domain Adaptive Segmentation Algorithm Based on Two-Level Category Alignment

Unsupervised Domain Adaptive Segmentation Algorithm Based on Two-Level Category Alignment

Information Science, Automation, Artificial Intelligence,
unsupervised domain adaption   semantic segmentation   two-level category alignment   class activation map   generative adversarial network  

Semantic segmentation aims to predict category labels for each pixel in an image (Liu et al., 2021; Wang et al., 2021) and is widely used in scene understanding, medical image analysis, autonomous driving, geographic information systems, and augmented reality (Strudel et al., 2021; Sun et al., 2023). Although the development of deep neural networks...