Pre-trained Prompt-driven Semi-supervised Local Community Detection

• URL: http://arxiv.org/abs/2505.12304v2
• Date: Fri, 30 May 2025 06:17:36 GMT
• Title: Pre-trained Prompt-driven Semi-supervised Local Community Detection
• Authors: Li Ni, Hengkai Xu, Lin Mu, Yiwen Zhang, Wenjian Luo,
• Abstract summary: Pre-trained Prompt-driven Semi-supervised Local community detection method (PPSL)<n>PPSL consists of three main components: node encoding, sample generation, and prompt-driven fine-tuning.<n> Experimental results on five real-world datasets demonstrate that PPSL outperforms baselines in both community quality and efficiency.
• Score: 6.120128190130239
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semi-supervised local community detection aims to leverage known communities to detect the community containing a given node. Although existing semi-supervised local community detection studies yield promising results, they suffer from time-consuming issues, highlighting the need for more efficient algorithms. Therefore, we apply the "pre-train, prompt" paradigm to semi-supervised local community detection and propose the Pre-trained Prompt-driven Semi-supervised Local community detection method (PPSL). PPSL consists of three main components: node encoding, sample generation, and prompt-driven fine-tuning. Specifically, the node encoding component employs graph neural networks to learn the representations of nodes and communities. Based on representations of nodes and communities, the sample generation component selects known communities that are structurally similar to the local structure of the given node as training samples. Finally, the prompt-driven fine-tuning component leverages these training samples as prompts to guide the final community prediction. Experimental results on five real-world datasets demonstrate that PPSL outperforms baselines in both community quality and efficiency.

Related papers

• A Local Perspective-based Model for Overlapping Community Detection [0.06206748337438322]
  We propose LQ-GCN, an overlapping community detection model from a local community perspective.<n>LQ-GCN employs a Bernoulli-Poisson model to construct a community affiliation matrix and form an end-to-end detection framework.<n>LQ-GCN achieves up to a 33% improvement in Normalized Mutual Information (NMI) and a 26.3% improvement in Recall compared to baseline models.
  arXiv  Detail & Related papers  (2025-03-27T14:43:42Z)
• Enhancing Community Detection in Networks: A Comparative Analysis of Local Metrics and Hierarchical Algorithms [49.1574468325115]
  This study employs the same method to evaluate the relevance of using local similarity metrics for community detection. The efficacy of these metrics was evaluated by applying the base algorithm to several real networks with varying community sizes.
  arXiv  Detail & Related papers  (2024-08-17T02:17:09Z)
• A Unified Framework for Exploratory Learning-Aided Community Detection Under Topological Uncertainty [14.903452009770715]
  META-CODE is a unified framework for detecting overlapping communities in social networks.<n>It consists of three steps: 1) node-level community-affiliation embeddings based on graph neural networks (GNNs) trained by our new reconstruction loss, 2) network exploration via community-affiliation-based node queries, and 3) network inference using an edge connectivity-based Siamese neural network model from the explored network.
  arXiv  Detail & Related papers  (2023-04-10T10:22:21Z)
• CS-TGN: Community Search via Temporal Graph Neural Networks [0.0]
  We propose a query-driven Temporal Graph Convolutional Network (CS-TGN) that can capture flexible community structures. CS-TGN first combines the local query-dependent structure and the global graph embedding in each snapshot of the network. We demonstrate how this model can be used for interactive community search in an online setting.
  arXiv  Detail & Related papers  (2023-03-15T22:23:32Z)
• META-CODE: Community Detection via Exploratory Learning in Topologically Unknown Networks [5.299515147443958]
  META-CODE is an end-to-end solution for detecting overlapping communities in networks with unknown topology. It consists of three steps: 1) initial network inference, 2) node-level community-affiliation embedding based on graph neural networks (GNNs) trained by our new reconstruction loss, and 3) network exploration via community-affiliation-based node queries.
  arXiv  Detail & Related papers  (2022-08-23T15:02:48Z)
• A Variational Edge Partition Model for Supervised Graph Representation Learning [51.30365677476971]
  This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities. We partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs. A variational inference framework is proposed to jointly learn a GNN based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN based predictor that combines community-specific GNNs for the end classification task.
  arXiv  Detail & Related papers  (2022-02-07T14:37:50Z)
• Frequent Itemset-driven Search for Finding Minimum Node Separators in Complex Networks [61.2383572324176]
  We propose a frequent itemset-driven search approach, which integrates the concept of frequent itemset mining in data mining into the well-known memetic search framework. It iteratively employs the frequent itemset recombination operator to generate promising offspring solution based on itemsets that frequently occur in high-quality solutions. In particular, it discovers 29 new upper bounds and matches 18 previous best-known bounds.
  arXiv  Detail & Related papers  (2022-01-18T11:16:40Z)
• Uncovering the Local Hidden Community Structure in Social Networks [20.467702194064525]
  We propose a new method that detects and boosts each layer iteratively on a subgraph sampled from the original network. We theoretically show that our method can avoid some situations that a broken community and the local community are regarded as one community in the subgraph.
  arXiv  Detail & Related papers  (2021-12-08T04:07:19Z)
• An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning [77.72330187258498]
  We propose a novel Entropy-guided Reinforced Partial Convolutional Network (ERPCNet) ERPCNet extracts and aggregates localities based on semantic relevance and visual correlations without human-annotated regions. It not only discovers global-cooperative localities dynamically but also converges faster for policy gradient optimization.
  arXiv  Detail & Related papers  (2021-11-03T11:13:13Z)
• QD-GCN: Query-Driven Graph Convolutional Networks for Attributed Community Search [54.42038098426504]
  QD-GCN is an end-to-end framework that unifies the community structure as well as node attributes to solve the ACS problem. We show that QD-GCN outperforms existing attributed community search algorithms in terms of both efficiency and effectiveness.
  arXiv  Detail & Related papers  (2021-04-08T07:52:48Z)
• Variational Embeddings for Community Detection and Node Representation [5.197034517903854]
  We propose an efficient generative model called VECoDeR for jointly learning Variational Embeddings for Community Detection and node Representation. We demonstrate on several graph datasets that VECoDeR effectively out-performs many competitive baselines on all three tasks.
  arXiv  Detail & Related papers  (2021-01-11T13:36:29Z)
• Amortized Probabilistic Detection of Communities in Graphs [39.56798207634738]
  We propose a simple framework for amortized community detection. We combine the expressive power of GNNs with recent methods for amortized clustering. We evaluate several models from our framework on synthetic and real datasets.
  arXiv  Detail & Related papers  (2020-10-29T16:18:48Z)
• Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method [114.48708191371524]
  Graph Convolutional Network (GCN) is an emerging technique for information retrieval (IR) applications. This work focuses on the local structure discrepancy of testing nodes, which has received little scrutiny. We analyze the working mechanism of GCN with causal graph, estimating the causal effect of a node's local structure for the prediction.
  arXiv  Detail & Related papers  (2020-10-22T15:21:47Z)
• On the use of local structural properties for improving the efficiency of hierarchical community detection methods [77.34726150561087]
  We study how local structural network properties can be used as proxies to improve the efficiency of hierarchical community detection. We also check the performance impact of network prunings as an ancillary tactic to make hierarchical community detection more efficient.
  arXiv  Detail & Related papers  (2020-09-15T00:16:12Z)
• GRADE: Graph Dynamic Embedding [76.85156209917932]
  GRADE is a probabilistic model that learns to generate evolving node and community representations by imposing a random walk prior to their trajectories. Our model also learns node community membership which is updated between time steps via a transition matrix. Experiments demonstrate GRADE outperforms baselines in dynamic link prediction, shows favourable performance on dynamic community detection, and identifies coherent and interpretable evolving communities.
  arXiv  Detail & Related papers  (2020-07-16T01:17:24Z)
• MetricUNet: Synergistic Image- and Voxel-Level Learning for Precise CT Prostate Segmentation via Online Sampling [66.01558025094333]
  We propose a two-stage framework, with the first stage to quickly localize the prostate region and the second stage to precisely segment the prostate. We introduce a novel online metric learning module through voxel-wise sampling in the multi-task network. Our method can effectively learn more representative voxel-level features compared with the conventional learning methods with cross-entropy or Dice loss.
  arXiv  Detail & Related papers  (2020-05-15T10:37:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.