This paper proposes a novel framework for modeling social networks based on the principles of empathetic computation. Traditional social network models primarily focus on structural aspects and relationships, often neglecting the crucial role of emotions and behaviors in shaping social interactions. This research introduces an empathetic dimension into the modeling process, leveraging machine learning algorithms to learn and represent emotional relationships and behavioral patterns within networks. The core claim is to build a framework capable of simulating human interactions by incorporating emotional factors, thereby facilitating a deeper understanding of complex phenomena observed in social networks. The methodology involves constructing a network where nodes represent individuals and edges represent connections, but crucially, these edges are augmented with associated emotional states and behavioral probabilities. We utilize machine learning techniques – specifically, recurrent neural networks (RNNs) and graph neural networks (GNNs) – to learn the dynamics of these emotional and behavioral relationships. The resulting model can then be used to simulate network behavior, predict individual actions, and explore emergent social phenomena. This approach offers a significant advancement over existing network models by providing a more nuanced and realistic representation of human social dynamics. The research aims to provide a foundation for understanding and predicting social behavior, with potential applications in areas such as social influence, crisis management, and community resilience.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper proposes a novel probabilistic inference network designed to leverage the correlations inherent within multi-modal data. The core idea is to construct a network architecture that explicitly models and utilizes relationships between different data modalities. This is achieved through the application of Graph Neural Networks (GNNs), which are employed to process the multi-modal data represented as a graph. Nodes in the graph represent individual data instances or features, and edges represent the learned associations between them. This approach allows the network to perform probabilistic inference by propagating information across related nodes, ultimately leading to more accurate and reliable predictions. The key innovation lies in the explicit incorporation of multi-modal associations into the GNN framework, moving beyond traditional GNN applications focused solely on single-modality data. We demonstrate the effectiveness of this approach through theoretical analysis and outline its potential for applications in domains requiring sophisticated probabilistic reasoning from diverse data sources.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper proposes a novel approach to decentralized learning utilizing Federated Graph Neural Networks (FedGNNs). The core idea is to facilitate collaborative knowledge discovery across a network of devices by employing locally maintained graph representations and periodically synchronized Graph Neural Networks (GNNs). This framework addresses the limitations of traditional federated learning, particularly when dealing with graph-structured data, where raw data sharing poses significant privacy concerns. The system avoids direct data exchange by allowing devices to collaboratively learn through the exchange of model updates, preserving data privacy while enabling effective knowledge transfer. The proposed FedGNN architecture consists of local graphs and locally trained GNNs, synchronized via a novel aggregation mechanism. We demonstrate the feasibility and effectiveness of this approach through a theoretical analysis and outline the key components required for implementation. The system is designed to be scalable and adaptable to various decentralized network topologies. This work represents a significant step towards privacy-preserving collaborative learning in complex, graph-based environments.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Neuro-Symbolic Reasoning via Dynamic Graph Construction (NSRC-DG) presents a novel approach to reasoning that integrates the strengths of neural networks and symbolic reasoning. Traditional reasoning systems often struggle with complex, nuanced inferences requiring deep understanding and logical deduction. This work introduces NSRC-DG, a system designed to dynamically construct and refine logical inferences based on observed data, leveraging neural networks to generate initial graph structures and then iteratively refining them through symbolic deduction. The core mechanism focuses on creating a layered graph structure where nodes represent concepts and edges represent relationships, allowing for efficient exploration and refinement of reasoning paths. This approach contrasts with reactive systems, offering a proactive and adaptable framework for enhanced reasoning capabilities. The system's success will be demonstrated through a series of benchmark problems designed to test its ability to generalize and reason effectively.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Temporal Topology Modeling for Signal Processing addresses the limitations of traditional signal processing methods by introducing a novel temporal topology model. This model leverages the combined power of recurrent neural networks and graph theory to effectively capture the evolution of signal patterns over time. The core mechanism involves establishing and maintaining a dynamic graph structure that represents the temporal dependencies within a signal, enabling more accurate and robust analysis. The proposed approach offers a significant advancement in signal processing, particularly for complex and long-term signal characteristics.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper introduces a novel approach to graph embedding that explicitly incorporates temporal dynamics and relational causality. Existing graph embedding methods often treat graphs as static structures, neglecting the evolving nature of relationships and the underlying causal mechanisms that govern them. We propose a Temporal Graph Embedding (TGE) framework that combines graph structure with temporal sequence data. The core of our method is a modified Graph Neural Network (GNN) augmented with a "causal influence propagation" module. This module learns directional dependencies within the graph based on observed temporal transitions, utilizing Bayesian inference to quantify uncertainty in these causal links. The resulting embeddings capture not only the node connections but also the temporal evolution and causal relationships driving those connections. We demonstrate the effectiveness of the TGE framework through theoretical analysis and a conceptual outline, highlighting its potential for applications requiring a deeper understanding of dynamic graph systems.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper introduces a novel self-adaptive grammar rule engine based on graph neural networks. The engine leverages a graph representation of the input text to automatically infer grammatical rules and generate more accurate translations. We propose a method that dynamically adjusts the graph structure based on contextual information, enabling the engine to learn and optimize rules for improved translation quality. The core mechanism involves a graph neural network (GNN) that transforms text into a graph representation, allows for reasoning and prediction, and iteratively refines the graph structure to achieve optimal results. The proposed approach offers a significant advancement over existing methods, providing a flexible and adaptable grammar rule system capable of handling complex linguistic structures. We demonstrate the engine's effectiveness through a series of benchmark tests focusing on natural language translation, capturing both syntactic and semantic nuances. The results showcase the engine's ability to produce translations that closely match human-generated outputs while exhibiting improved accuracy and fluency.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper investigates the application of neuromorphic computing architectures for real-time graph processing. Traditional graph processing relies on von Neumann architectures, which suffer from inherent bottlenecks due to the separation of processing and memory. We propose a novel approach utilizing spiking neural networks (SNNs) and memristor-based systems to mimic the efficiency and parallelism of biological brains. The core idea is to directly map graph algorithms onto the inherent dynamics of these systems, leading to significant reductions in power consumption and latency. Specifically, we explore architectures designed to efficiently handle graph traversals, shortest path algorithms, and community detection. The implemented models demonstrate a potential for substantial performance gains compared to conventional approaches, particularly for large, dynamic graphs. The architecture presented offers a fundamentally different paradigm for graph processing, moving away from the centralized processing model and embracing a distributed, event-driven system.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Existing graph embedding techniques predominantly focus on static graph structures, neglecting the crucial aspect of temporal dynamics inherent in many real-world networks. This paper introduces a novel approach – Temporal Graph Embedding with Relational Dynamics – that addresses this limitation. Our method leverages a recurrent neural network (RNN) to model the evolution of graph relationships over time. The RNN is trained to predict future graph states based on past states and node attributes, effectively creating a dynamic representation of the graph. The resulting hidden state representation from the RNN is then utilized as the graph embedding. This approach allows for the capture and learning of temporal relational dependencies, providing a richer and more accurate representation of the graph compared to static embedding methods. The core of our method is the integration of dynamic graph modeling with RNNs, explicitly capturing the evolving nature of relationships within the graph. The proposed method demonstrates improved performance in downstream tasks that rely on understanding temporal graph patterns.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper introduces a novel dynamic graph neural network (D-GNN) architecture, termed "Adaptive Dynamic Graph Neural Network," designed to optimize the learning process of GNNs through dynamic adjustment of the graph's structure and parameters. Traditional GNN approaches often rely on fixed graph structures, limiting their adaptability to diverse datasets. This work proposes a mechanism that continuously refines the graph structure during training, enabling the network to better capture complex relationships within the data. We demonstrate the effectiveness of our approach through extensive experiments on benchmark datasets, showcasing significant improvements in both accuracy and convergence speed compared to existing GNN methods. The core of our design lies in a novel dynamic adjustment strategy that leverages a reinforcement learning component to guide the graph's evolution. The resulting D-GNN exhibits improved generalization performance and robustness to variations in input data. Finally, we discuss potential future research directions and limitations of this approach.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
This paper introduces a novel approach to modeling social network dynamics using Hypergraph Neural Networks (HNNs). Traditional Graph Neural Networks (GNNs) struggle to accurately represent and propagate information through networks exhibiting higher-order relationships, a common characteristic of social structures. HNNs overcome this limitation by explicitly constructing hypergraphs, which represent sets of vertices connected by multiple edges. This allows for the direct modeling of complex interactions and dependencies beyond the pairwise connections considered in standard GNNs. We propose a framework for designing and training HNNs specifically tailored for social network analysis, focusing on predicting behavioral patterns and social influence. The core contribution lies in leveraging hypergraph structures to capture and propagate information across multiple connected nodes simultaneously, leading to improved accuracy in modeling dynamic social systems. The proposed method is demonstrated through a theoretical analysis and conceptual framework, highlighting the potential for future research and applications.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
Assistant Professor Pat Pataranutaporn describes a new interface that lets everyday users glimpse inside an AI's neural network before their chatbot ever says a word.
MIT News · Artificial Intelligence· news.mit.eduJul 6, 2026
PhD student Rachel Sava, winner of the Envisioning the Future of Computing Prize, explores transformative improvements and dystopian risks of neural technology.
