Learning Efficient Positional Encodings with Graph Neural Networks

• URL: http://arxiv.org/abs/2502.01122v1
• Date: Mon, 03 Feb 2025 07:28:53 GMT
• Title: Learning Efficient Positional Encodings with Graph Neural Networks
• Authors: Charilaos I. Kanatsoulis, Evelyn Choi, Stephanie Jegelka, Jure Leskovec, Alejandro Ribeiro,
• Abstract summary: We introduce PEARL, a novel framework of learnable PEs for graphs. PEARL approximates equivariant functions of eigenvectors with linear complexity, while rigorously establishing its stability and high expressive power. Our analysis demonstrates that PEARL approximates equivariant functions of eigenvectors with linear complexity, while rigorously establishing its stability and high expressive power.
• Score: 109.8653020407373
• License:
• Abstract: Positional encodings (PEs) are essential for effective graph representation learning because they provide position awareness in inherently position-agnostic transformer architectures and increase the expressive capacity of Graph Neural Networks (GNNs). However, designing powerful and efficient PEs for graphs poses significant challenges due to the absence of canonical node ordering and the scale of the graph. {In this work, we identify four key properties that graph PEs should satisfy}: stability, expressive power, scalability, and genericness. We find that existing eigenvector-based PE methods often fall short of jointly satisfying these criteria. To address this gap, we introduce PEARL, a novel framework of learnable PEs for graphs. Our primary insight is that message-passing GNNs function as nonlinear mappings of eigenvectors, enabling the design of GNN architectures for generating powerful and efficient PEs. A crucial challenge lies in initializing node attributes in a manner that is both expressive and permutation equivariant. We tackle this by initializing GNNs with random node inputs or standard basis vectors, thereby unlocking the expressive power of message-passing operations, while employing statistical pooling functions to maintain permutation equivariance. Our analysis demonstrates that PEARL approximates equivariant functions of eigenvectors with linear complexity, while rigorously establishing its stability and high expressive power. Experimental evaluations show that PEARL outperforms lightweight versions of eigenvector-based PEs and achieves comparable performance to full eigenvector-based PEs, but with one or two orders of magnitude lower complexity. Our code is available at https://github.com/ehejin/Pearl-PE.

Related papers

• Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks [53.10674067060148]
  Shapley Interactions (SIs) quantify node contributions and interactions among multiple nodes. By exploiting the GNN architecture, we show that the structure of interactions in node embeddings are preserved for graph prediction. We introduce GraphSHAP-IQ, an efficient approach to compute any-order SIs exactly.
  arXiv  Detail & Related papers  (2025-01-28T13:37:44Z)
• LASE: Learned Adjacency Spectral Embeddings [7.612218105739107]
  We learn nodal Adjacency Spectral Embeddings (ASE) from graph inputs. LASE is interpretable, parameter efficient, robust to inputs with unobserved edges. LASE layers combine Graph Convolutional Network (GCN) and fully-connected Graph Attention Network (GAT) modules.
  arXiv  Detail & Related papers  (2024-12-23T17:35:19Z)
• What Are Good Positional Encodings for Directed Graphs? [13.076497906728333]
  We introduce the notion of Walk Profile, a generalization of walk-counting sequences for directed graphs. We propose a novel Multi-q Magnetic Laplacian PE, which extends the Magnetic Laplacian eigenvector-based PE by incorporating multiple potential factors. Our numerical experiments validate the expressiveness of the proposed PEs and demonstrate their effectiveness in solving sorting network satisfiability.
  arXiv  Detail & Related papers  (2024-07-30T15:38:14Z)
• Long Range Graph Benchmark [32.317725340138104]
  MP-GNNs that simply rely on 1-hop message passing often fare better in several existing graph benchmarks. We benchmark both baseline GNNs and Graph Transformer networks to verify that the models which capture long-range dependencies perform significantly better on these tasks.
  arXiv  Detail & Related papers  (2022-06-16T13:33:22Z)
• Representation Power of Graph Neural Networks: Improved Expressivity via Algebraic Analysis [124.97061497512804]
  We show that standard Graph Neural Networks (GNNs) produce more discriminative representations than the Weisfeiler-Lehman (WL) algorithm. We also show that simple convolutional architectures with white inputs, produce equivariant features that count the closed paths in the graph.
  arXiv  Detail & Related papers  (2022-05-19T18:40:25Z)
• Graph Neural Networks with Learnable Structural and Positional Representations [83.24058411666483]
  A major issue with arbitrary graphs is the absence of canonical positional information of nodes. We introduce Positional nodes (PE) of nodes, and inject it into the input layer, like in Transformers. We observe a performance increase for molecular datasets, from 2.87% up to 64.14% when considering learnable PE for both GNN classes.
  arXiv  Detail & Related papers  (2021-10-15T05:59:15Z)
• Permutation-equivariant and Proximity-aware Graph Neural Networks with Stochastic Message Passing [88.30867628592112]
  Graph neural networks (GNNs) are emerging machine learning models on graphs. Permutation-equivariance and proximity-awareness are two important properties highly desirable for GNNs. We show that existing GNNs, mostly based on the message-passing mechanism, cannot simultaneously preserve the two properties. In order to preserve node proximities, we augment the existing GNNs with node representations.
  arXiv  Detail & Related papers  (2020-09-05T16:46:56Z)
• Building powerful and equivariant graph neural networks with structural message-passing [74.93169425144755]
  We propose a powerful and equivariant message-passing framework based on two ideas. First, we propagate a one-hot encoding of the nodes, in addition to the features, in order to learn a local context matrix around each node. Second, we propose methods for the parametrization of the message and update functions that ensure permutation equivariance.
  arXiv  Detail & Related papers  (2020-06-26T17:15:16Z)

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.