# Trivial Graph Features and Classical Learning are Enough to Detect Random Anomalies

arXiv: https://arxiv.org/abs/2603.01841 · HTML: https://mlsanity.com/paper/2603.01841/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Builds on (most cited first, 13 of 13)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Graph-based Anomaly Detection and Description: A Survey](https://mlsanity.com/paper/1404.4679/) (2014)
- [Anomaly Detection in Dynamic Graphs via Transformer](https://mlsanity.com/paper/2106.09876/) (2021)
- [Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs](https://mlsanity.com/paper/2005.07427/) (2020)
- [MIDAS: Microcluster-Based Detector of Anomalies in Edge Streams](https://mlsanity.com/paper/1911.04464/) (2019)
- [F-FADE: Frequency Factorization for Anomaly Detection in Edge Streams](https://mlsanity.com/paper/2011.04723/) (2020)
- [Fast and Accurate Anomaly Detection in Dynamic Graphs with a Two-Pronged Approach](https://mlsanity.com/paper/2011.13085/) (2020)
- [Stream Graphs and Link Streams for the Modeling of Interactions over Time](https://mlsanity.com/paper/1710.04073/) (2017)
- [SLADE: Detecting Dynamic Anomalies in Edge Streams without Labels via Self-Supervised Learning](https://mlsanity.com/paper/2402.11933/) (2024)
- [MonLAD: Money Laundering Agents Detection in Transaction Streams](https://mlsanity.com/paper/2201.10051/) (2022)
- [Full Bitcoin Blockchain Data Made Easy](https://mlsanity.com/paper/2106.08072/) (2021)

## Abstract (arXiv)

Detecting anomalies in link streams that represent various kinds of interactions is an important research topic with crucial applications. Because of the lack of ground truth data, proposed methods are mostly evaluated through their ability to detect randomly injected links. In contrast with most proposed methods, that rely on complex approaches raising computational and/or interpretability issues, we show here that trivial graph features and classical learning techniques are sufficient to detect such anomalies extremely well. This basic approach has very low computational costs and it leads to easily interpretable results. It also has many other desirable properties that we study through an extensive set of experiments. We conclude that detection methods should now target more complex kinds of anomalies.