BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Dongxiao He

Dongxiao He appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Social and Information Networksphysics.soc-phMachine Learningcond-mat.stat-mechArtificial IntelligenceComputation and Language

Catalog footprint

What is connected

12works
6topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

12 published item(s)

preprint2026arXiv

CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts

Heterogeneous Graph Prompt Learning (HGPL)has emerged as a promising paradigm for bridging the gap between the objectives of pre-training foundation models and their downstream applications in heterogeneous graph settings. However, existing HGPL methods are primarily designed for in-domain scenarios, whereas real-world deployments often span multiple domains, and the data used for pre-training and downstream tasks may originate from different distributions. Consequently, the applicability of current HGPL approaches is limited to in-domain settings, and their performance typically degrades when application domains shift. To address this serious limitation, we develop CHoE, a cross-domain HGPL method built upon an expert network. During pre-training, we introduce and train structure-conditioned experts, and during prompt tuning, we adopt a structure-aware expert routing and load balancing mechanism to select structurally compatible experts for each meta-path view. In addition, we design a prompt-based semantic fusion module to integrate representations across multiple views for downstream prediction. Extensive experiments show that CHoE consistently improves performance in few-shot cross-domain applications, outperforming all baseline approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Compositional Multi-hop Factual Error Correction via Decomposition-and-Injection

Factual Error Correction (FEC) aims to revise inaccurate text into statements that are factually consistent with external evidence. Although recent methods perform well on single-hop correction, they often treat claims as atomic units and struggle with multi-hop cases that require compositional reasoning across multiple evidence sources. This challenge is further amplified by limited paired data and difficulties in locating semantic errors within complex reasoning chains. We present CECoR (Compositional Error Correction via Reasoning-aware Synthesis), a reasoning-aware framework that introduces a Decomposition and Injection paradigm for compositional error correction. CECoR decomposes multi-hop claims into interpretable reasoning steps and injects controlled perturbations to synthesize high-quality training pairs. A two-stage learning strategy combining supervised fine-tuning and reinforcement learning improves factual accuracy and robustness. Comprehensive evaluations show that CECoR achieves strong performance on multi-hop benchmarks, outperforming both distantly supervised methods and few-shot LLM baselines. It also generalizes effectively to single-hop correction and remains stable under noisy evidence, demonstrating its versatility for real-world factual correction.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

RAW-GNN: RAndom Walk Aggregation based Graph Neural Network

Graph-Convolution-based methods have been successfully applied to representation learning on homophily graphs where nodes with the same label or similar attributes tend to connect with one another. Due to the homophily assumption of Graph Convolutional Networks (GCNs) that these methods use, they are not suitable for heterophily graphs where nodes with different labels or dissimilar attributes tend to be adjacent. Several methods have attempted to address this heterophily problem, but they do not change the fundamental aggregation mechanism of GCNs because they rely on summation operators to aggregate information from neighboring nodes, which is implicitly subject to the homophily assumption. Here, we introduce a novel aggregation mechanism and develop a RAndom Walk Aggregation-based Graph Neural Network (called RAW-GNN) method. The proposed approach integrates the random walk strategy with graph neural networks. The new method utilizes breadth-first random walk search to capture homophily information and depth-first search to collect heterophily information. It replaces the conventional neighborhoods with path-based neighborhoods and introduces a new path-based aggregator based on Recurrent Neural Networks. These designs make RAW-GNN suitable for both homophily and heterophily graphs. Extensive experimental results showed that the new method achieved state-of-the-art performance on a variety of homophily and heterophily graphs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

TrustGNN: Graph Neural Network based Trust Evaluation via Learnable Propagative and Composable Nature

Trust evaluation is critical for many applications such as cyber security, social communication and recommender systems. Users and trust relationships among them can be seen as a graph. Graph neural networks (GNNs) show their powerful ability for analyzing graph-structural data. Very recently, existing work attempted to introduce the attributes and asymmetry of edges into GNNs for trust evaluation, while failed to capture some essential properties (e.g., the propagative and composable nature) of trust graphs. In this work, we propose a new GNN based trust evaluation method named TrustGNN, which integrates smartly the propagative and composable nature of trust graphs into a GNN framework for better trust evaluation. Specifically, TrustGNN designs specific propagative patterns for different propagative processes of trust, and distinguishes the contribution of different propagative processes to create new trust. Thus, TrustGNN can learn comprehensive node embeddings and predict trust relationships based on these embeddings. Experiments on some widely-used real-world datasets indicate that TrustGNN significantly outperforms the state-of-the-art methods. We further perform analytical experiments to demonstrate the effectiveness of the key designs in TrustGNN.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

GCN for HIN via Implicit Utilization of Attention and Meta-paths

Heterogeneous information network (HIN) embedding, aiming to map the structure and semantic information in a HIN to distributed representations, has drawn considerable research attention. Graph neural networks for HIN embeddings typically adopt a hierarchical attention (including node-level and meta-path-level attentions) to capture the information from meta-path-based neighbors. However, this complicated attention structure often cannot achieve the function of selecting meta-paths due to severe overfitting. Moreover, when propagating information, these methods do not distinguish direct (one-hop) meta-paths from indirect (multi-hop) ones. But from the perspective of network science, direct relationships are often believed to be more essential, which can only be used to model direct information propagation. To address these limitations, we propose a novel neural network method via implicitly utilizing attention and meta-paths, which can relieve the severe overfitting brought by the current over-parameterized attention mechanisms on HIN. We first use the multi-layer graph convolutional network (GCN) framework, which performs a discriminative aggregation at each layer, along with stacking the information propagation of direct linked meta-paths layer-by-layer, realizing the function of attentions for selecting meta-paths in an indirect way. We then give an effective relaxation and improvement via introducing a new propagation operation which can be separated from aggregation. That is, we first model the whole propagation process with well-defined probabilistic diffusion dynamics, and then introduce a random graph-based constraint which allows it to reduce noise with the increase of layers. Extensive experiments demonstrate the superiority of the new approach over state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

An Ant-Based Algorithm with Local Optimization for Community Detection in Large-Scale Networks

In this paper, we propose a multi-layer ant-based algorithm MABA, which detects communities from networks by means of locally optimizing modularity using individual ants. The basic version of MABA, namely SABA, combines a self-avoiding label propagation technique with a simulated annealing strategy for ant diffusion in networks. Once the communities are found by SABA, this method can be reapplied to a higher level network where each obtained community is regarded as a new vertex. The aforementioned process is repeated iteratively, and this corresponds to MABA. Thanks to the intrinsic multi-level nature of our algorithm, it possesses the potential ability to unfold multi-scale hierarchical structures. Furthermore, MABA has the ability that mitigates the resolution limit of modularity. The proposed MABA has been evaluated on both computer-generated benchmarks and widely used real-world networks, and has been compared with a set of competitive algorithms. Experimental results demonstrate that MABA is both effective and efficient (in near linear time with respect to the size of network) for discovering communities.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Ant Colony Optimization with a New Random Walk Model for Community Detection in Complex Networks

Detecting communities from complex networks has recently triggered great interest. Aiming at this problem, a new ant colony optimization strategy building on the Markov random walks theory, which is named as MACO, is proposed in this paper. The framework of ant colony optimization is taken as the basic framework in this algorithm. In each iteration, a Markov random walk model is employed as heuristic rule; all of the ants local solutions are aggregated to a global one through an idea of clustering ensemble, which then will be used to update a pheromone matrix. The strategy relies on the progressive strengthening of within-community links and the weakening of between-community links. Gradually this converges to a solution where the underlying community structure of the complex network will become clearly visible. The proposed MACO has been evaluated both on synthetic benchmarks and on some real-world networks, and compared with some present competing algorithms. Experimental result has shown that MACO is highly effective for discovering communities.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Discovering link communities in complex networks by exploiting link dynamics

Discovery of communities in complex networks is a fundamental data analysis problem with applications in various domains. Most of the existing approaches have focused on discovering communities of nodes, while recent studies have shown great advantages and utilities of the knowledge of communities of links in networks. From this new perspective, we propose a link dynamics based algorithm, called UELC, for identifying link communities of networks. In UELC, the stochastic process of a link-node-link random walk is employed to unfold an embedded bipartition structure of links in a network. The local mixing properties of the Markov chain underlying the random walk are then utilized to extract two emerged link communities. Further, the random walk and the bipartitioning processes are wrapped in an iterative subdivision strategy to recursively identify link partitions that segregate the network links into multiple subdivisions. We evaluate the performance of the new method on synthetic benchmarks and demonstrate its utility on real-world networks. Our experimental results show that our method is highly effective for discovering link communities in complex networks. As a comparison, we also extend UELC to extracting communities of node, and show that it is effective for node community identification.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Genetic Algorithm with a Local Search Strategy for Discovering Communities in Complex Networks

In order to further improve the performance of current genetic algorithms aiming at discovering communities, a local search based genetic algorithm GALS is here proposed. The core of GALS is a local search based mutation technique. In order to overcome the drawbacks of traditional mutation methods, the paper develops the concept of marginal gene and then the local monotonicity of modularity function Q is deduced from each nodes local view. Based on these two elements, a new mutation method combined with a local search strategy is presented. GALS has been evaluated on both synthetic benchmarks and several real networks, and compared with some presently competing algorithms. Experimental results show that GALS is highly effective and efficient for discovering community structure.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Genetic Algorithm with Ensemble Learning for Detecting Community Structure in Complex Networks

Community detection in complex networks is a topic of considerable recent interest within the scientific community. For dealing with the problem that genetic algorithm are hardly applied to community detection, we propose a genetic algorithm with ensemble learning (GAEL) for detecting community structure in complex networks. GAEL replaces its traditional crossover operator with a multi-individual crossover operator based on ensemble learning. Therefore, GAEL can avoid the problems that are brought by traditional crossover operator which is only able to mix string blocks of different individuals, but not able to recombine clustering contexts of different individuals into new better ones. In addition, the local search strategy, which makes mutated node be placed into the community where most of its neighbors are, is used in mutation operator. At last, a Markov random walk based method is used to initialize population in this paper, and it can provide us a population of accurate and diverse clustering solutions. Those diverse and accurate individuals are suitable for ensemble learning based multi-individual crossover operator. The proposed GAEL is tested on both computer-generated and real-world networks, and compared with current representative algorithms for community detection in complex networks. Experimental results demonstrate that GAEL is highly effective at discovering community structure.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Identification of hybrid node and link communities in complex networks

Identification of communities in complex networks has become an effective means to analysis of complex systems. It has broad applications in diverse areas such as social science, engineering, biology and medicine. Finding communities of nodes and finding communities of links are two popular schemes for network structure analysis. These schemes, however, have inherent drawbacks and are often inadequate to properly capture complex organizational structures in real networks. We introduce a new scheme and effective approach for identifying complex network structures using a mixture of node and link communities, called hybrid node-link communities. A central piece of our approach is a probabilistic model that accommodates node, link and hybrid node-link communities. Our extensive experiments on various real-world networks, including a large protein-protein interaction network and a large semantic association network of commonly used words, illustrated that the scheme for hybrid communities is superior in revealing network characteristics. Moreover, the new approach outperformed the existing methods for finding node or link communities separately.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

Markov random walk under constraint for discovering overlapping communities in complex networks

Detection of overlapping communities in complex networks has motivated recent research in the relevant fields. Aiming this problem, we propose a Markov dynamics based algorithm, called UEOC, which means, 'unfold and extract overlapping communities'. In UEOC, when identifying each natural community that overlaps, a Markov random walk method combined with a constraint strategy, which is based on the corresponding annealed network (degree conserving random network), is performed to unfold the community. Then, a cutoff criterion with the aid of a local community function, called conductance, which can be thought of as the ratio between the number of edges inside the community and those leaving it, is presented to extract this emerged community from the entire network. The UEOC algorithm depends on only one parameter whose value can be easily set, and it requires no prior knowledge on the hidden community structures. The proposed UEOC has been evaluated both on synthetic benchmarks and on some real-world networks, and was compared with a set of competing algorithms. Experimental result has shown that UEOC is highly effective and efficient for discovering overlapping communities.

0 citations0 reviewsNo code linkedOpen access