Social network generation finds numerous applications in various fields, such as epidemic modeling, social media simulations, and understanding social phenomena like polarization. Creating realistic social networks is crucial when real networks cannot be directly observed due to privacy concerns or other constraints. These generated networks are vital for accurately modeling interactions and predicting outcomes in…
Large language models (LLMs) have significantly progressed in various domains, including natural language understanding and code generation. These models can generate coherent text and solve complex tasks. However, LLMs face challenges when applied to more specialized areas such as competitive programming and code generation. This field focuses on improving the models’ ability to generate diverse,…
Graph neural networks (GNNs) have emerged as powerful tools for capturing complex interactions in real-world entities and finding applications across various business domains. These networks excel at generating effective graph entity embeddings by encoding both node features and structural insights, making them invaluable for numerous downstream tasks. GNNs have succeeded in node-level financial fraud detection,…
Artificial intelligence (AI) and database management systems have increasingly converged, with significant potential to improve how users interact with large datasets. Recent advancements aim to allow users to pose natural language questions directly to databases and retrieve detailed, complex answers. However, current tools are limited in addressing real-world demands. Traditional AI models, such as language…
Mixture-of-experts (MoE) architectures are becoming significant in the rapidly developing field of Artificial Intelligence (AI), allowing for the creation of systems that are more effective, scalable, and adaptable. MoE optimizes computing power and resource utilization by employing a system of specialized sub-models, or experts, that are selectively activated based on the input data. Because of…
Large language models (LLMs) have become fundamental tools for tasks such as question-answering (QA) and text summarization. These models excel at processing long and complex texts, with capacities reaching over 100,000 tokens. As LLMs are popular for handling large-context tasks, ensuring their reliability and accuracy becomes more pressing. Users rely on LLMs to sift through…
Graph Neural Networks (GNNs) have emerged as the leading approach for graph learning tasks across various domains, including recommender systems, social networks, and bioinformatics. However, GNNs have shown vulnerability to adversarial attacks, particularly structural attacks that modify graph edges. These attacks pose significant challenges in scenarios where attackers have limited access to entity relationships. Despite…
The paper “MemLong: Memory-Augmented Retrieval for Long Text Modeling” addresses a critical limitation regarding the ability to process long contexts in the field of Large Language Models (LLMs). While LLMs have shown remarkable success in various applications, they struggle with long-sequence tasks due to traditional attention mechanisms’ quadratic time and space complexity. The increasing memory…
The dynamics governing multi-agent systems (MAS) are complicated and frequently unknown, making the identification of their underlying graph structures a considerable difficulty. Numerous real-world applications, from robotic swarms to distributed sensor networks, use multi-agent systems, which are made up of autonomous agents interacting in a network. Comprehending the network architecture of these systems is essential…
The primary challenge in scaling large-scale AI systems is achieving efficient decision-making while maintaining performance. Distributed AI, particularly multi-agent reinforcement learning (MARL), offers potential by decomposing complex tasks and distributing them across collaborative nodes. However, real-world applications face limitations due to high communication and data requirements. Traditional methods, like model predictive control (MPC), require precise…