ML Anthology

Cutting the Black Box: Conceptual Interpretation of a Deep Neural Net with Multi-Modal Embeddings and Multi-Criteria Decision Aid

Nicolas Atienza, Roman Bresson, Cyriaque Rousselot, Philippe Caillou, Johanne Cohen, Christophe Labreuche, Michèle Sebag
IJCAI 2024 pp. 3669-3678
doi:10.24963/ijcai.2024/406 /ijcai/2024/atienza2024ijcai-cutting/

Abstract

Graph anomaly detection (GAD), with its ability to accurately identify anomalous patterns in graph data, plays a vital role in areas such as network security, social media platforms, and fraud detection. Graph autoencoder-based methods are widely used for GAD due to their efficiency and effectiveness in capturing complex patterns and learning meaningful representations. However, the above methods are constrained by hardware memory, hindering the detection for large-scale graph data. In this paper, we propose a Memory-Efficient framework for large-scale attributed Graph Anomaly Detection (MEGAD). Specifically, MEGAD first generates node embeddings and then refines them through a lightweight joint optimization model, ensuring minimal memory overhead. The optimized embeddings are subsequently fed into a detector to compute anomaly scores. Extensive experiments demonstrate that our framework achieves comparable accuracy to state-of-the-art methods across multiple datasets while significantly reducing memory consumption on large-scale graphs.

PDF IJCAI Semantic Scholar

Cite

Text

Atienza et al. "Cutting the Black Box: Conceptual Interpretation of a Deep Neural Net with Multi-Modal Embeddings and Multi-Criteria Decision Aid." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/406

Markdown

[Atienza et al. "Cutting the Black Box: Conceptual Interpretation of a Deep Neural Net with Multi-Modal Embeddings and Multi-Criteria Decision Aid." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/atienza2024ijcai-cutting/) doi:10.24963/ijcai.2024/406

BibTeX

@inproceedings{atienza2024ijcai-cutting,
  title     = {{Cutting the Black Box: Conceptual Interpretation of a Deep Neural Net with Multi-Modal Embeddings and Multi-Criteria Decision Aid}},
  author    = {Atienza, Nicolas and Bresson, Roman and Rousselot, Cyriaque and Caillou, Philippe and Cohen, Johanne and Labreuche, Christophe and Sebag, Michèle},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {3669-3678},
  doi       = {10.24963/ijcai.2024/406},
  url       = {https://mlanthology.org/ijcai/2024/atienza2024ijcai-cutting/}
}