# DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs

arXiv: https://arxiv.org/abs/2601.16519 · HTML: https://mlsanity.com/paper/2601.16519/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 23 Jan 2026.

## Builds on (most cited first, 17 of 17)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Adaptive Universal Generalized PageRank Graph Neural Network](https://mlsanity.com/paper/2006.07988/) (2020)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [Graph Condensation for Graph Neural Networks](https://mlsanity.com/paper/2110.07580/) (2021)
- [Subgraph Federated Learning with Missing Neighbor Generation](https://mlsanity.com/paper/2106.13430/) (2021)
- [Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data](https://mlsanity.com/paper/2306.02664/) (2023)
- [Personalized Subgraph Federated Learning](https://mlsanity.com/paper/2206.10206/) (2022)
- [FedGTA: Topology-aware Averaging for Federated Graph Learning](https://mlsanity.com/paper/2401.11755/) (2024)
- [Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?](https://mlsanity.com/paper/2408.08685/) (2024)
- [Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement](https://mlsanity.com/paper/2505.12684/) (2025)
- [Privacy Meets Explainability: A Comprehensive Impact Benchmark](https://mlsanity.com/paper/2211.04110/) (2022)
- [A Comprehensive Data-centric Overview of Federated Graph Learning](https://mlsanity.com/paper/2507.16541/) (2025)
- [Interplay between Federated Learning and Explainable Artificial Intelligence: a Scoping Review](https://mlsanity.com/paper/2411.05874/) (2024)
- [Rethinking Federated Graph Learning: A Data Condensation Perspective](https://mlsanity.com/paper/2505.02573/) (2025)
- [LLaTA: Unlocking Graph Structure Learning with Tree-Guided Large Language Models](https://mlsanity.com/paper/2503.21223/) (2025)

## Abstract (arXiv)

Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. With the rise of large language models (LLMs), textual attributes in FGL graphs are gaining attention. Text-attributed graph federated learning (TAG-FGL) improves FGL by explicitly leveraging LLMs to process and integrate these textual features. However, current TAG-FGL methods face three main challenges: (1) Overhead. LLMs for processing long texts incur high token and computation costs. To make TAG-FGL practical, we introduce graph condensation (GC) to reduce computation load, but this choice also brings new issues. (2) Suboptimal. To reduce LLM overhead, we introduce GC into TAG-FGL by compressing multi-hop texts/neighborhoods into a condensed core with fixed LLM surrogates. However, this one-shot condensation is often not client-adaptive, leading to suboptimal performance. (3) Interpretability. LLM-based condensation further introduces a black-box bottleneck: summaries lack faithful attribution and clear grounding to specific source spans, making local inspection and auditing difficult. To address the above issues, we propose DANCE, a new TAG-FGL paradigm with GC. To improve suboptimal performance, DANCE performs round-wise, model-in-the-loop condensation refresh using the latest global model. To enhance interpretability, DANCE preserves provenance by storing locally inspectable evidence packs that trace predictions to selected neighbors and source text spans. Across 8 TAG datasets, DANCE improves accuracy by 2.33% at an 8% condensation ratio, with 33.42% fewer tokens than baselines.