arXiv subjects

Yinglong Zhang

Publications and source records attributed to Yinglong Zhang.

8 recordsLinked to original sources

arXiv2025

Dual Refinement Cycle Learning: Unsupervised Text Classification of Mamba and Community Detection on Text Attributed Graph

Pretrained language models offer strong text understanding capabilities but remain difficult to deploy in real-world text-attributed networks due to their heavy dependence on labeled data. Meanwhile, community detection methods typically ignore textual semantics, limiting their usefulness in downstream applications such as content organization, recommendation, and risk monitoring. To overcome these limitations, we present Dual Refinement Cycle Learning (DRCL), a fully unsupervised framework designed for practical scenarios where no labels or category definitions are available. DRCL integrates structural and semantic information through a warm-start initialization and a bidirectional refinement cycle between a GCN-based Community Detection Module (GCN-CDM) and a Text Semantic Modeling Module (TSMM). The two modules iteratively exchange pseudo-labels, allowing semantic cues to enhance structural clustering and structural patterns to guide text representation learning without manual supervision. Across several text-attributed graph datasets, DRCL consistently improves the structural and semantic quality of discovered communities. Moreover, a Mamba-based classifier trained solely from DRCL's community signals achieves accuracy comparable to supervised models, demonstrating its potential for deployment in large-scale systems where labeled data are scarce or costly. The code is available at https://github.com/wuanghoong/DRCL.git.

cs.LG↗

arXiv2025

Odin: Oriented Dual-module Integration for Text-rich Network Representation Learning

Text-attributed graphs require models to effectively combine strong textual understanding with structurally informed reasoning. Existing approaches either rely on GNNs--limited by over-smoothing and hop-dependent diffusion--or employ Transformers that overlook graph topology and treat nodes as isolated sequences. We propose Odin (Oriented Dual-module INtegration), a new architecture that injects graph structure into Transformers at selected depths through an oriented dual-module mechanism. Unlike message-passing GNNs, Odin does not rely on multi-hop diffusion; instead, multi-hop structures are integrated at specific Transformer layers, yielding low-, mid-, and high-level structural abstraction aligned with the model's semantic hierarchy. Because aggregation operates on the global [CLS] representation, Odin fundamentally avoids over-smoothing and decouples structural abstraction from neighborhood size or graph topology. We further establish that Odin's expressive power strictly contains that of both pure Transformers and GNNs. To make the design efficient in large-scale or low-resource settings, we introduce Light Odin, a lightweight variant that preserves the same layer-aligned structural abstraction for faster training and inference. Experiments on multiple text-rich graph benchmarks show that Odin achieves state-of-the-art accuracy, while Light Odin delivers competitive performance with significantly reduced computational cost. Together, Odin and Light Odin form a unified, hop-free framework for principled structure-text integration. The source code of this model has been released at https://github.com/hongkaifeng/Odin.

cs.CL↗

arXiv2025

Parameter-Free Structural-Diversity Message Passing for Graph Neural Networks

Graph Neural Networks (GNNs) have shown remarkable performance in structured data modeling tasks such as node classification. However, mainstream approaches generally rely on a large number of trainable parameters and fixed aggregation rules, making it difficult to adapt to graph data with strong structural heterogeneity and complex feature distributions. This often leads to over-smoothing of node representations and semantic degradation. To address these issues, this paper proposes a parameter-free graph neural network framework based on structural diversity, namely SDGNN (Structural-Diversity Graph Neural Network). The framework is inspired by structural diversity theory and designs a unified structural-diversity message passing mechanism that simultaneously captures the heterogeneity of neighborhood structures and the stability of feature semantics, without introducing additional trainable parameters. Unlike traditional parameterized methods, SDGNN does not rely on complex model training, but instead leverages complementary modeling from both structure-driven and feature-driven perspectives, thereby effectively improving adaptability across datasets and scenarios. Experimental results show that on eight public benchmark datasets and an interdisciplinary PubMed citation network, SDGNN consistently outperforms mainstream GNNs under challenging conditions such as low supervision, class imbalance, and cross-domain transfer. This work provides a new theoretical perspective and general approach for the design of parameter-free graph neural networks, and further validates the importance of structural diversity as a core signal in graph representation learning. To facilitate reproducibility and further research, the full implementation of SDGNN has been released at: https://github.com/mingyue15694/SGDNN/tree/main

cs.LG↗

arXiv2025

Less is More: Simple yet Effective Heuristic Community Detection with Graph Convolution Network

Community detection is crucial in data mining. Traditional methods primarily focus on graph structure, often neglecting the significance of attribute features. In contrast, deep learning-based approaches incorporate attribute features and local structural information through contrastive learning, improving detection performance. However, existing algorithms' complex design and joint optimization make them difficult to train and reduce detection efficiency. Additionally, these methods require the number of communities to be predefined, making the results susceptible to artificial interference. To address these challenges, we propose a simple yet effective community detection algorithm that can adaptively detect communities without relying on data augmentation and contrastive optimization. The proposed algorithm first performs community pre-detection to extract global structural information adaptively. It then utilizes GCN to integrate local structures and attribute features. Subsequently, it combines global, local structures and attribute features in the feature space to discover community affiliations. Finally, a modularity maximization method is employed to optimize the communities based on these three types of information, thereby uncovering the community affiliation of each node. We conduct experimental comparisons across various graph datasets, evaluating the proposed algorithm against traditional methods and state-of-the-art community detection algorithms. The experimental results demonstrate that our algorithm achieves greater efficiency and accuracy in terms of both detection speed and effectiveness. The code is available at https://github.com/wuanghoong/Less-is-More.git.

cs.SI↗

arXiv2025

Citation Structural Diversity: A Novel and Concise Metric Combining Structure and Semantics for Literature Evaluation

As academic research becomes increasingly diverse, traditional literature evaluation methods face significant limitations,particularly in capturing the complexity of academic dissemination and the multidimensional impacts of literature. To address these challenges, this paper introduces a novel literature evaluation model of citation structural diversity, with a focus on assessing its feasibility as an evaluation metric. By refining citation network and incorporating both ciation structural features and semantic information, the study examines the influence of the proposed model of citation structural diversity on citation volume and long-term academic impact. The findings reveal that literature with higher citation structural diversity demonstrates notable advantages in both citation frequency and sustained academic influence. Through data grouping and a decade-long citation trend analysis, the potential application of this model in literature evaluation is further validated. This research offers a fresh perspective on optimizing literature evaluation methods and emphasizes the distinct advantages of citation structural diversity in measuring interdisciplinarity.

cs.IR↗

arXiv2024

TANGNN: a Concise, Scalable and Effective Graph Neural Networks with Top-m Attention Mechanism for Graph Representation Learning

In the field of deep learning, Graph Neural Networks (GNNs) and Graph Transformer models, with their outstanding performance and flexible architectural designs, have become leading technologies for processing structured data, especially graph data. Traditional GNNs often face challenges in capturing information from distant vertices effectively. In contrast, Graph Transformer models are particularly adept at managing long-distance node relationships. Despite these advantages, Graph Transformer models still encounter issues with computational and storage efficiency when scaled to large graph datasets. To address these challenges, we propose an innovative Graph Neural Network (GNN) architecture that integrates a Top-m attention mechanism aggregation component and a neighborhood aggregation component, effectively enhancing the model's ability to aggregate relevant information from both local and extended neighborhoods at each layer. This method not only improves computational efficiency but also enriches the node features, facilitating a deeper analysis of complex graph structures. Additionally, to assess the effectiveness of our proposed model, we have applied it to citation sentiment prediction, a novel task previously unexplored in the GNN field. Accordingly, we constructed a dedicated citation network, ArXivNet. In this dataset, we specifically annotated the sentiment polarity of the citations (positive, neutral, negative) to enable in-depth sentiment analysis. Our approach has shown superior performance across a variety of tasks including vertex classification, link prediction, sentiment prediction, graph regression, and visualization. It outperforms existing methods in terms of effectiveness, as demonstrated by experimental results on multiple datasets.

cs.LG↗

arXiv2020

Is the epidemic spread related to GDP? Visualizing the distribution of COVID-19 in Chinese Mainland

In December 2019, COVID-19 were detected in Wuhan City, Hubei Province of China. SARS-CoV-2 rapidly spread to the whole Chinese mainland with the people during the Chinese Spring Festival Travel Rush. As of 19 February 2020, 74576 confirmed cases of COVID-19 had been reported in Chinese Mainland. What kind of cities have more confirmed cases, and is there any relationship between GDP and confirmed cases? In this study, we explored the relationship between the confirmed cases of COVID-19 and GDP at the prefectural-level, found a positive correlation between them. This finding warns high GDP areas should pay more prevention and control efforts when an epidemic outbreak, as they have greater risks than other areas nearby.

q-bio.PE↗

arXiv2018

Asymptotic stability of the phase-homogeneous solution to the Kuramoto-Sakaguchi equation with inertia

We present the global-in-time existence of strong solutions and its large-time behavior for the Kuramoto-Sakaguchi equation with inertia. The equation describes the evolution of the probability density function for a large ensemble of Kuramoto oscillators under the effects of inertia and stochastic noises. We consider a perturbative framework around the equilibrium, which is a Maxwellian type, and use the classical energy method together with our careful analysis on the macro-micro decomposition. We establish the global-in-time existence and uniqueness of strong solutions when the initial data are sufficiently regular, not necessarily close to the equilibrium, and the noise strength is also large enough. For the large-time behavior, we show the exponential decay of solutions towards the equilibrium under the same assumptions as those for the global regularity of solutions.

math.AP↗