Summary of Arc: a Generalist Graph Anomaly Detector with In-context Learning, by Yixin Liu et al.
ARC: A Generalist Graph Anomaly Detector with In-Context Learning
by Yixin Liu, Shiyuan Li, Yu Zheng, Qingfeng Chen, Chengqi Zhang, Shirui Pan
First submitted to arxiv on: 27 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A machine learning educator can summarize this abstract as follows: The paper proposes a novel approach to graph anomaly detection (GAD) called ARC, which enables a single model to detect anomalies across various graph datasets without retraining or fine-tuning. This is achieved through in-context learning, where the model extracts dataset-specific patterns from the target dataset using few-shot normal samples at inference time. ARC consists of three components: a feature alignment module that unifies features into a common space; an ego-neighbor residual graph encoder that learns abnormality-related node embeddings; and a cross-attentive in-context anomaly scoring module that predicts node abnormality using few-shot normal samples. The paper demonstrates the superior performance, efficiency, and generalizability of ARC on multiple benchmark datasets from various domains. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary For curious high school students or non-technical adults, the abstract can be summarized as follows: This paper is about finding unusual patterns in big networks (like social media or communication systems). Right now, most methods for doing this require lots of training data and are not very good at adapting to new situations. The researchers came up with a new approach called ARC that can detect anomalies in many different types of networks without needing retraining. They tested it on several datasets and showed that it works better than other methods. |
Keywords
» Artificial intelligence » Alignment » Anomaly detection » Encoder » Few shot » Fine tuning » Inference » Machine learning
