MDL-Pool: Adaptive Multilevel Graph Pooling Based on Minimum Description Length

• URL: http://arxiv.org/abs/2409.10263v2
• Date: Wed, 14 May 2025 19:48:25 GMT
• Title: MDL-Pool: Adaptive Multilevel Graph Pooling Based on Minimum Description Length
• Authors: Jan von Pichowski, Christopher Blöcker, Ingo Scholtes,
• Abstract summary: Graph pooling compresses graphs and summarises their topological properties and features in a vectorial representation.<n>Current approaches pool hierarchical structures in graphs by iteratively applying shallow pooling operators up to a fixed depth.<n>We propose MDL-Pool, a pooling operator based on the minimum description length (MDL) principle.
• Score: 0.716879432974126
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph pooling compresses graphs and summarises their topological properties and features in a vectorial representation. It is an essential part of deep graph representation learning and is indispensable in graph-level tasks like classification or regression. Current approaches pool hierarchical structures in graphs by iteratively applying shallow pooling operators up to a fixed depth. However, they disregard the interdependencies between structures at different hierarchical levels and do not adapt to datasets that contain graphs with different sizes that may require pooling with various depths. To address these issues, we propose MDL-Pool, a pooling operator based on the minimum description length (MDL) principle, whose loss formulation explicitly models the interdependencies between different hierarchical levels and facilitates a direct comparison between multiple pooling alternatives with different depths. MDP-Pool builds on the map equation, an information-theoretic objective function for community detection, which naturally implements Occam's razor and balances between model complexity and goodness-of-fit via the MDL. We demonstrate MDL-Pool's competitive performance in an empirical evaluation against various baselines across standard graph classification datasets.

Related papers

• OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Models [57.94189874119267]
  Multi-Agent Systems (MAS) offer a powerful paradigm for solving complex problems.<n>Current graph learning-based design methodologies often adhere to a "one-for-one" paradigm.<n>We propose OFA-TAD, a one-for-all framework that generates adaptive collaboration graphs for any task described in natural language.
  arXiv  Detail & Related papers  (2026-01-19T12:23:44Z)
• Geometry-Aware Edge Pooling for Graph Neural Networks [20.080879481223924]
  Graph Neural Networks (GNNs) have shown significant success for graph-based tasks.<n>Motivated by the prevalence of large datasets in real-world applications, pooling layers are crucial components of GNNs.<n>We propose novel graph pooling layers for structure aware pooling via edge collapses.
  arXiv  Detail & Related papers  (2025-06-13T12:01:46Z)
• Refinement Module based on Parse Graph for Human Pose Estimation [9.106514619168536]
  We propose a new context relation and hierarchical structure modeling module, RMPG, based on Parse Graph.<n> RMPG adaptively refines feature maps through top-down decomposition of feature maps and bottom-up composition of sub-node feature maps with context information.<n>It can be flexibly embedded as a plug-in into various mainstream Human Pose Estimation networks.
  arXiv  Detail & Related papers  (2025-01-19T15:05:15Z)
• DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts [70.21017141742763]
  Graph neural networks (GNNs) are gaining popularity for processing graph-structured data. Existing methods generally use a fixed number of GNN layers to generate representations for all graphs. We propose the depth adaptive mixture of expert (DA-MoE) method, which incorporates two main improvements to GNN.
  arXiv  Detail & Related papers  (2024-11-05T11:46:27Z)
• SSHPool: The Separated Subgraph-based Hierarchical Pooling [47.78745802682822]
  We develop a novel local graph pooling method, namely the Separated Subgraph-based Hierarchical Pooling (SSH) for graph classification. We individually employ the local graph convolution units as the local structure to further compress each subgraph into a coarsened node. We develop an end-to-end GNN framework associated with the SSHPool module for graph classification.
  arXiv  Detail & Related papers  (2024-03-24T13:03:35Z)
• RGM: A Robust Generalizable Matching Model [49.60975442871967]
  We propose a deep model for sparse and dense matching, termed RGM (Robust Generalist Matching) To narrow the gap between synthetic training samples and real-world scenarios, we build a new, large-scale dataset with sparse correspondence ground truth. We are able to mix up various dense and sparse matching datasets, significantly improving the training diversity.
  arXiv  Detail & Related papers  (2023-10-18T07:30:08Z)
• Dynamic Graph Message Passing Networks for Visual Recognition [112.49513303433606]
  Modelling long-range dependencies is critical for scene understanding tasks in computer vision. A fully-connected graph is beneficial for such modelling, but its computational overhead is prohibitive. We propose a dynamic graph message passing network, that significantly reduces the computational complexity.
  arXiv  Detail & Related papers  (2022-09-20T14:41:37Z)
• Higher-order Clustering and Pooling for Graph Neural Networks [77.47617360812023]
  Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks. HoscPool is a clustering-based graph pooling operator that captures higher-order information hierarchically. We evaluate HoscPool on graph classification tasks and its clustering component on graphs with ground-truth community structure.
  arXiv  Detail & Related papers  (2022-09-02T09:17:10Z)
• FlowPool: Pooling Graph Representations with Wasserstein Gradient Flows [3.655021726150369]
  Existing graph pooling methods offer no guarantee with regards to the similarity of a graph representation and its pooled version. We propose FlowPool, a pooling method that optimally preserves the statistics of a graph representation to its pooled counterpart by minimizing their Wasserstein distance. Our method is amenable to automatic differentiation and can be integrated in end-to-end deep learning architectures.
  arXiv  Detail & Related papers  (2021-12-18T20:07:06Z)
• Edge but not Least: Cross-View Graph Pooling [76.71497833616024]
  This paper presents a cross-view graph pooling (Co-Pooling) method to better exploit crucial graph structure information. Through cross-view interaction, edge-view pooling and node-view pooling seamlessly reinforce each other to learn more informative graph-level representations.
  arXiv  Detail & Related papers  (2021-09-24T08:01:23Z)
• Structure-Aware Hierarchical Graph Pooling using Information Bottleneck [2.7088996845250897]
  Graph pooling is an essential ingredient of Graph Neural Networks (GNNs) in graph classification and regression tasks. We propose a novel pooling method named as HIBPool where we leverage the Information Bottleneck (IB) principle. We also introduce a novel structure-aware Discriminative Pooling Readout (DiP-Readout) function to capture the informative local subgraph structures in the graph.
  arXiv  Detail & Related papers  (2021-04-27T07:27:43Z)
• Accurate Learning of Graph Representations with Graph Multiset Pooling [45.72542969364438]
  We propose a Graph Multiset Transformer (GMT) that captures the interaction between nodes according to their structural dependencies. Our experimental results show that GMT significantly outperforms state-of-the-art graph pooling methods on graph classification benchmarks.
  arXiv  Detail & Related papers  (2021-02-23T07:45:58Z)
• CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning [74.90535111881358]
  We propose a new interpretable graph pooling framework - CommPOOL. It can capture and preserve the hierarchical community structure of graphs in the graph representation learning process. CommPOOL is a general and flexible framework for hierarchical graph representation learning.
  arXiv  Detail & Related papers  (2020-12-10T21:14:18Z)
• Multivariate Time Series Classification with Hierarchical Variational Graph Pooling [23.66868187446734]
  Existing deep learning-based MTSC techniques are primarily concerned with the temporal dependency of single time series. We propose a novel graph pooling-based framework MTPool to obtain the expressive global representation of MTS. Experiments on ten benchmark datasets exhibit MTPool outperforms state-of-the-art strategies in the MTSC task.
  arXiv  Detail & Related papers  (2020-10-12T12:36:47Z)
• Graph Pooling with Node Proximity for Hierarchical Representation Learning [80.62181998314547]
  We propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Results show that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.
  arXiv  Detail & Related papers  (2020-06-19T13:09:44Z)
• SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features [0.0]
  This paper proposes two main contributions, the first is a differential module calculating structural similarity features based on the adjacency matrix. The second main contribution is on integrating these features with a revisited pooling layer DiffPool arXiv:1806.08804 to propose a pooling layer referred to as SimPool. Experimental results demonstrate that as part of an end-to-end Graph Neural Network architecture SimPool calculates node cluster assignments that resemble more to the locality.
  arXiv  Detail & Related papers  (2020-06-03T12:51:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.