Subset Node Anomaly Tracking over Large Dynamic Graphs

Guo, Xingzhi; Zhou, Baojian; Skiena, Steven

doi:10.1145/3534678.3539389

Cited by 9 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These algorithms address time-stamped nodes as queries, which can be represented by their set of incident edges or by the indicator function of such set. DYNANOM [6] uses a short term context to monitor the evolution of PageRank scores. It labels a query as abnormal if its PageRank score drastically changed.…”

Section: Related Workmentioning

confidence: 99%

“…Two for edge anomalies: MIDAS [1] and F-FADE [2]. Two for node anomalies: DynAnom [6] and F-FADE-N [2], the variant of F-FADE proposed by their authors to address node anomalies. Two for graph anomalies: AnomRank [8] and LAD [10].…”

Section: Numerical Experimentsmentioning

confidence: 99%

“…queries, like time-stamped nodes [6,7] or entire graph snapshots [8][9][10][11], have also been proposed. These algorithms also vary in the way they define an anomaly and use the context.…”

Section: Introductionmentioning

confidence: 99%

“…These algorithms also vary in the way they define an anomaly and use the context. Namely, nodes may be deemed abnormal if they suddenly change their centrality [6] or communication counts [7], while graphs may be considered abnormal if they have sudden densifications [9], spectrum changes [10], or community re-configurations [11], to list some examples.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

MAD: Multi-Scale Anomaly Detection in Link Streams

Bautista,

Brisson,

Bothorel

et al. 2024

Proceedings of the 17th ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Numerical Experimentsmentioning

confidence: 99%

“…queries, like time-stamped nodes [6,7] or entire graph snapshots [8][9][10][11], have also been proposed. These algorithms also vary in the way they define an anomaly and use the context.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

MAD: Multi-Scale Anomaly Detection in Link Streams

Bautista,

Brisson,

Bothorel

et al. 2024

Proceedings of the 17th ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

show abstract

Collection and Integration of Event-Centric Information in Cross-Lingual Knowledge Graphs

Gottschalk

2024

Event Analytics Across Languages and Communities

View full text Add to dashboard Cite

Collecting and integrating event information in a knowledge graph enables the analysis of major societal events, their interdependencies with other events and actors and their perception and impact. While existing cross-domain knowledge graphs such as Wikidata and DBpedia also contain event knowledge, they are typically limited regarding the diversity of event representations and types. In this chapter, we first describe EventKG—a knowledge graph of multilingual event-centric information bringing together heterogeneous event information from different sources. Since the thorough understanding of events further demands the availability of context information in different modalities, we then present the Open Event Knowledge Graph (OEKG), which extends the coverage and modality of EventKG by integrating several of the event-related datasets presented in this book and opens up several possibilities for cross-lingual, event-centric open analytics. Through several statistics, example queries and applications, we show the versatility and the applicability of EventKG and OEKG for event analytics across languages and communities.

show abstract

TAAD: Time-varying adversarial anomaly detection in dynamic graphs

Liu,

Zhang,

et al. 2025

Information Processing & Management

View full text Add to dashboard Cite

Subset Node Anomaly Tracking over Large Dynamic Graphs

Cited by 9 publications

References 34 publications

MAD: Multi-Scale Anomaly Detection in Link Streams

MAD: Multi-Scale Anomaly Detection in Link Streams

Collection and Integration of Event-Centric Information in Cross-Lingual Knowledge Graphs

TAAD: Time-varying adversarial anomaly detection in dynamic graphs

Contact Info

Product

Resources

About