DynaMo: Dynamic Community Detection by Incrementally Maximizing Modularity

@article{Zhuang2021DynaMoDC,
  title={DynaMo: Dynamic Community Detection by Incrementally Maximizing Modularity},
  author={Di Zhuang and J. Morris Chang and Mingchen Li},
  journal={IEEE Transactions on Knowledge and Data Engineering},
  year={2021},
  volume={33},
  pages={1934-1945}
}
Community detection is of great importance for online social network analysis. The volume, variety and velocity of data generated by today's online social networks are advancing the way researchers analyze those networks. For instance, real-world networks, such as Facebook, LinkedIn and Twitter, are inherently growing rapidly and expanding aggressively over time. However, most of the studies so far have been focusing on detecting communities on the static networks. It is computationally… 
Robust Dynamic Clustering for Temporal Networks
TLDR
Experimental results on six artificial datasets and four real-world dynamic network datasets indicate that RTSC performs better than six state-of-the-art algorithms for dynamic clustering in temporal networks.
Metaheuristic Multi-Objective Method to Detect Communities on Dynamic Social Networks
TLDR
A novel method is presented to identify communities in dynamic social networks, based on a multi-objective metaheuristic algorithm using label propagation technique, in order to detect communities incrementally, which outperforms the state-of-the-art algorithms with respect to modularity and normalized mutual information (NMI) objectives.
Delta-Screening: A Fast and Efficient Technique to Update Communities in Dynamic Graphs
TLDR
This paper presents a new technique called Delta-Screening, generic to be incorporated into any of the existing modularity-optimizing clustering algorithms, and test using two state-of-the-art clustering implementations, namely, Louvain and SLM.
Multi-Layer Feature Fusion-Based Community Evolution Prediction
TLDR
An algorithm called multi-layer feature fusion-based community evolution prediction, which obtains features from the community layer and node layer and trains a classifier through these features and uses them in community evolution Prediction.
Locally Differentially Private Distributed Deep Learning via Knowledge Distillation
TLDR
This work proposes LDP-DL, a privacy-preserving distributed deep learning framework via local differential privacy and knowledge distillation, where each data owner learns a teacher model using its own (local) private dataset, and the data user learns a student model to mimic the output of the ensemble of the teacher models.
Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation
CS-AF: A Cost-sensitive Multi-classifier Active Fusion Framework for Skin Lesion Classification
Theory of preference modelling for communities in scale-free networks
TLDR
A fuzzy based approach for overlapping community detection using a local fitness function for a community to identify the community structures and applies the preference implication of continuous-valued logic.
Time-Topology Analysis
TLDR
A new metric named T-cohesiveness is proposed to evaluate the cohesiveness of a temporal subgraph, and two time-topology analysis methods are proposed to improve the efficiency of combo searching and the pruning strategy.
ESAI: Efficient Split Artificial Intelligence via Early Exiting Using Neural Architecture Search
TLDR
A new framework for deploying on IoT devices has been proposed which can take advantage of both the cloud and the on-device models by extracting the meta-information from each sample's classification result and evaluating the classification’s performance for the necessity of sending the sample to the server.
...
...

References

SHOWING 1-10 OF 40 REFERENCES
On the evolution of user interaction in Facebook
TLDR
It is found that links in the activity network tend to come and go rapidly over time, and the strength of ties exhibits a general decreasing trend of activity as the social network link ages.
Measurement and analysis of online social networks
TLDR
This paper examines data gathered from four popular online social networks: Flickr, YouTube, LiveJournal, and Orkut, and reports that the indegree of user nodes tends to match the outdegree; the networks contain a densely connected core of high-degree nodes; and that this core links small groups of strongly clustered, low-degree node at the fringes of the network.
An incremental batch technique for community detection
TLDR
This paper discusses the inadequacies of previous techniques as well as justify the need for a new class of techniques that can handle complex batch changes in networks and proposes one such incremental technique that is much more efficient in scenarios where a network evolves significantly while maintaining a high level of accuracy.
A Real-Time Detecting Algorithm for Tracking Community Structure of Dynamic Networks
TLDR
The experimental results show that the proposed modularity based algorithm can keep track of community structure in time and outperform the well known CNM algorithm in terms of modularity.
Tiles: an online algorithm for community discovery in dynamic social networks
TLDR
This work proposes Tiles, an algorithm that extracts overlapping communities and tracks their evolution in time following an online iterative procedure, and compares it with state-of-the-art community detection algorithms on both synthetic and real world networks having annotated community structure.
Evolutionary Nonnegative Matrix Factorization Algorithms for Community Detection in Dynamic Networks
  • Xiaoke Ma, Di Dong
  • Computer Science
    IEEE Transactions on Knowledge and Data Engineering
  • 2017
TLDR
This paper proves the equivalence relationship between ENMF and optimization of evolutionary modularity density, and proposes a semi-supervised ENMF (sE-NMF), which is not only more accurate but also more robust than the state-of-the-art approaches.
Tracking dynamic community evolution in social networks
  • Zeineb Dhouioui, J. Akaichi
  • Computer Science
    2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014)
  • 2014
TLDR
This work presents a study on social networks across the time axis i.e. temporal social networks and proposes an algorithm classifying changes and based on indicators, and also integrates data warehouse layer in order to have an over-view of all possible changes helpful for future analysis.
Predicting community evolution based on time series modeling
  • N. Ilhan, Ş. Öğüdücü
  • Computer Science
    2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
  • 2015
TLDR
This paper proposed a new approach for predicting events by estimating feature values related to the communities in a given network and event prediction using forecasted feature values substantially match up with actual events.
...
...