Boosting Graph Anomaly Detection with Adaptive Message Passing

Jingyan Chen, Guanghui Zhu, C. Yuan, Y. Huang
2/12/2026

No official code found. Best implementation: LiamMa/GRIT (133 stars, MIT, last commit 2025-08-20).

Semantic Scholar

Code Implementations(1)

LiamMa/GRITCommunity70%
MIT

This is an official implementation for "GRIT: Graph Inductive Biases in Transformers without Message Passing".

13320Shell, PythonMay 22, 20231 years agoMIT

Similar Papers

Dynamic Personalized Federated Learning with Adaptive Differential Privacy

100% match1 repo922026

Efficient Model Stealing Defense with Noise Transition Matrix

100% match2026

Achieving Cross Modal Generalization with Multimodal Unified Representation

100% match1 repo2432026

Effective Bayesian Heteroscedastic Regression with Deep Neural Networks

100% match1 repo262026

A General Representation Learning Framework with Generalization Performance Guarantees

100% match2026

Toward Exploratory Inverse Constraint Inference with Generative Diffusion Verifiers

100% match1 repo12026

Cite this paper

@article{chen2026boosting,
  title  = {Boosting Graph Anomaly Detection with Adaptive Message Passing},
  author = {Jingyan Chen and Guanghui Zhu and C. Yuan and Y. Huang},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:4ceb1a27b25c57e8bb6a11e5d3e221521ae6b5e0},
  journal = {ICLR 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/4ceb1a27b25c57e8bb6a11e5d3e221521ae6b5e0.svg)](https://codeofpaper.com/paper/4ceb1a27b25c57e8bb6a11e5d3e221521ae6b5e0)

Discussion