# Stochastic Sequential Decision Making over Expanding Networks with Graph Filtering

arXiv: https://arxiv.org/abs/2603.19501 · HTML: https://mlsanity.com/paper/2603.19501/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking](https://mlsanity.com/paper/2010.00577/) (2020)
- [Learning graphs from data: A signal representation perspective](https://mlsanity.com/paper/1806.00848/) (2018)
- [Convolutional Neural Network Architectures for Signals Supported on Graphs](https://mlsanity.com/paper/1805.00165/) (2018)
- [Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks](https://mlsanity.com/paper/2003.03777/) (2020)
- [Graph signal processing for machine learning: A review and new perspectives](https://mlsanity.com/paper/2007.16061/) (2020)
- [Graph Filters for Signal Processing and Machine Learning on Graphs](https://mlsanity.com/paper/2211.08854/) (2022)
- [How Powerful is Graph Convolution for Recommendation?](https://mlsanity.com/paper/2108.07567/) (2021)
- [Learning by Transference: Training Graph Neural Networks on Growing Graphs](https://mlsanity.com/paper/2106.03693/) (2021)
- [Training Robust Graph Neural Networks with Topology Adaptive Edge Dropping](https://mlsanity.com/paper/2106.02892/) (2021)
- [Wide and Deep Graph Neural Network with Distributed Online Learning](https://mlsanity.com/paper/2107.09203/) (2021)
- [Topology-aware Embedding Memory for Continual Learning on Expanding Networks](https://mlsanity.com/paper/2401.13200/) (2024)
- [Adaptive Diffusions for Scalable Learning over Graphs](https://mlsanity.com/paper/1804.02081/) (2018)
- [Online Control Barrier Functions for Decentralized Multi-Agent Navigation](https://mlsanity.com/paper/2303.04313/) (2023)
- [Filtering Random Graph Processes Over Random Time-Varying Graphs](https://mlsanity.com/paper/1705.00442/) (2017)
- [How Powerful is Graph Filtering for Recommendation](https://mlsanity.com/paper/2406.08827/) (2024)
- [Online Graph-Adaptive Learning with Scalability and Privacy](https://mlsanity.com/paper/1812.00974/) (2018)
- [ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks](https://mlsanity.com/paper/2403.09171/) (2024)
- [Graph filtering over expanding graphs](https://mlsanity.com/paper/2203.08058/) (2022)
- [Co-Optimizing Reconfigurable Environments and Policies for Decentralized Multi-Agent Navigation](https://mlsanity.com/paper/2403.14583/) (2024)
- [Learning Expanding Graphs for Signal Interpolation](https://mlsanity.com/paper/2203.07966/) (2022)
- [Modularity of ErdHos-R'enyi random graphs](https://mlsanity.com/paper/1808.02243/) (2018)
- [Streaming Network Embedding through Local Actions](https://mlsanity.com/paper/1811.05932/) (2018)
- [Accurate Graph Filtering in Wireless Sensor Networks](https://mlsanity.com/paper/2004.11922/) (2020)
- [Graph Neural Networks over the Air for Decentralized Tasks in Wireless Networks](https://mlsanity.com/paper/2302.08447/) (2023)
- [Online Graph Filtering Over Expanding Graphs](https://mlsanity.com/paper/2409.07204/) (2024)

## Abstract (arXiv)

Graph filters leverage topological information to process networked data with existing methods mainly studying fixed graphs, ignoring that graphs often expand as nodes continually attach with an unknown pattern. The latter requires developing filter-based decision-making paradigms that take evolution and uncertainty into account. Existing approaches rely on either pre-designed filters or online learning, limited to a myopic view considering only past or present information. To account for future impacts, we propose a stochastic sequential decision-making framework for filtering networked data with a policy that adapts filtering to expanding graphs. By representing filter shifts as agents, we model the filter as a multi-agent system and train the policy following multi-agent reinforcement learning. This accounts for long-term rewards and captures expansion dynamics through sequential decision-making. Moreover, we develop a context-aware graph neural network to parameterize the policy, which tunes filter parameters based on information of both the graph and agents. Experiments on synthetic and real datasets from cold-start recommendation to COVID prediction highlight the benefits of using a sequential decision-making perspective over batch and online filtering alternatives.