# A (More) Realistic Evaluation Setup for Generalisation of Community Models on Malicious Content Detection

arXiv: https://arxiv.org/abs/2404.01822 · HTML: https://mlsanity.com/paper/2404.01822/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 71 references that are in the map.
- First posted on arXiv 2 Apr 2024.

## Builds on (most cited first, 30 of 37)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML](https://mlsanity.com/paper/1909.09157/) (2019)
- [Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples](https://mlsanity.com/paper/1903.03096/) (2019)
- [Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods](https://mlsanity.com/paper/2110.14446/) (2021)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Media](https://mlsanity.com/paper/1809.01286/) (2018)
- [Is Homophily a Necessity for Graph Neural Networks?](https://mlsanity.com/paper/2106.06134/) (2021)
- [A Review on Language Models as Knowledge Bases](https://mlsanity.com/paper/2204.06031/) (2022)
- [Fake News Detection on Social Media using Geometric Deep Learning](https://mlsanity.com/paper/1902.06673/) (2019)
- [FANG: Leveraging Social Context for Fake News Detection Using Graph Representation](https://mlsanity.com/paper/2008.07939/) (2020)
- [Beyond News Contents: The Role of Social Context for Fake News Detection](https://mlsanity.com/paper/1712.07709/) (2017)
- [Graph Meta Learning via Local Subgraphs](https://mlsanity.com/paper/2006.07889/) (2020)
- [Graph-based Semi-supervised Learning: A Comprehensive Review](https://mlsanity.com/paper/2102.13303/) (2021)
- [Towards Few-Shot Fact-Checking via Perplexity](https://mlsanity.com/paper/2103.09535/) (2021)
- [Diverse Few-Shot Text Classification with Multiple Metrics](https://mlsanity.com/paper/1805.07513/) (2018)
- [Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks](https://mlsanity.com/paper/1911.03863/) (2019)
- [Detecting Hate Speech with GPT-3](https://mlsanity.com/paper/2103.12407/) (2021)
- [Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Tasks](https://mlsanity.com/paper/1908.10423/) (2019)
- [Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive Learning](https://mlsanity.com/paper/2204.08143/) (2022)
- [Graph-based Modeling of Online Communities for Fake News Detection](https://mlsanity.com/paper/2008.06274/) (2020)
- [Adversarial Active Learning based Heterogeneous Graph Neural Network for Fake News Detection](https://mlsanity.com/paper/2101.11206/) (2021)
- [Abusive Language Detection with Graph Convolutional Networks](https://mlsanity.com/paper/1904.04073/) (2019)
- [Multilingual and cross-lingual document classification: A meta-learning approach](https://mlsanity.com/paper/2101.11302/) (2021)
- [Learning to Learn to Disambiguate: Meta-Learning for Few-Shot Word Sense Disambiguation](https://mlsanity.com/paper/2004.14355/) (2020)
- [On Unifying Misinformation Detection](https://mlsanity.com/paper/2104.05243/) (2021)

## Built on by (most cited first, 1 of 1)

- [Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directions](https://mlsanity.com/paper/2509.25539/) (2025)

## Abstract (arXiv)

Community models for malicious content detection, which take into account the context from a social graph alongside the content itself, have shown remarkable performance on benchmark datasets. Yet, misinformation and hate speech continue to propagate on social media networks. This mismatch can be partially attributed to the limitations of current evaluation setups that neglect the rapid evolution of online content and the underlying social graph. In this paper, we propose a novel evaluation setup for model generalisation based on our few-shot subgraph sampling approach. This setup tests for generalisation through few labelled examples in local explorations of a larger graph, emulating more realistic application settings. We show this to be a challenging inductive setup, wherein strong performance on the training graph is not indicative of performance on unseen tasks, domains, or graph structures. Lastly, we show that graph meta-learners trained with our proposed few-shot subgraph sampling outperform standard community models in the inductive setup. We make our code publicly available.