GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts

• URL: http://arxiv.org/abs/2312.04693v3
• Date: Mon, 28 Oct 2024 11:34:06 GMT
• Title: GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts
• Authors: Shirley Wu, Kaidi Cao, Bruno Ribeiro, James Zou, Jure Leskovec,
• Abstract summary: GraphMETRO is a Graph Neural Network architecture that models natural diversity and captures complex distributional shifts. GraphMETRO achieves state-of-the-art results on four datasets from the GOOD benchmark.
• Score: 75.51612253852002
• License:
• Abstract: Graph data are inherently complex and heterogeneous, leading to a high natural diversity of distributional shifts. However, it remains unclear how to build machine learning architectures that generalize to the complex distributional shifts naturally occurring in the real world. Here, we develop GraphMETRO, a Graph Neural Network architecture that models natural diversity and captures complex distributional shifts. GraphMETRO employs a Mixture-of-Experts (MoE) architecture with a gating model and multiple expert models, where each expert model targets a specific distributional shift to produce a referential representation w.r.t. a reference model, and the gating model identifies shift components. Additionally, we design a novel objective that aligns the representations from different expert models to ensure reliable optimization. GraphMETRO achieves state-of-the-art results on four datasets from the GOOD benchmark, which is comprised of complex and natural real-world distribution shifts, improving by 67% and 4.2% on the WebKB and Twitch datasets. Code and data are available at https://github.com/Wuyxin/GraphMETRO.

Related papers

• 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)
• AnyGraph: Graph Foundation Model in the Wild [16.313146933922752]
  Graph foundation models offer the potential to learn robust, generalizable representations from graph data. In this work, we investigate a unified graph model, AnyGraph, designed to handle key challenges. Our experiments on diverse 38 graph datasets have demonstrated the strong zero-shot learning performance of AnyGraph.
  arXiv  Detail & Related papers  (2024-08-20T09:57:13Z)
• GraphFM: A Scalable Framework for Multi-Graph Pretraining [2.882104808886318]
  We introduce a scalable multi-graph multi-task pretraining approach specifically tailored for node classification tasks across diverse graph datasets from different domains. We demonstrate the efficacy of our approach by training a model on 152 different graph datasets comprising over 7.4 million nodes and 189 million edges. Our results show that pretraining on a diverse array of real and synthetic graphs improves the model's adaptability and stability, while performing competitively with state-of-the-art specialist models.
  arXiv  Detail & Related papers  (2024-07-16T16:51:43Z)
• Hi-GMAE: Hierarchical Graph Masked Autoencoders [90.30572554544385]
  Hierarchical Graph Masked AutoEncoders (Hi-GMAE) Hi-GMAE is a novel multi-scale GMAE framework designed to handle the hierarchical structures within graphs. Our experiments on 15 graph datasets consistently demonstrate that Hi-GMAE outperforms 17 state-of-the-art self-supervised competitors.
  arXiv  Detail & Related papers  (2024-05-17T09:08:37Z)
• GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks [72.01829954658889]
  This paper introduces the mathematical definition of this novel problem setting. We devise a general framework that coordinates a single graph-shared structure learner and multiple graph-specific GNNs. The well-trained structure learner can directly produce adaptive structures for unseen target graphs without any fine-tuning.
  arXiv  Detail & Related papers  (2023-06-20T03:33:22Z)
• Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling [60.0185734837814]
  Graph neural networks (GNNs) have found extensive applications in learning from graph data. To bolster the generalization capacity of GNNs, it has become customary to augment training graph structures with techniques like graph augmentations. This study introduces the concept of Mixture-of-Experts (MoE) to GNNs, with the aim of augmenting their capacity to adapt to a diverse range of training graph structures.
  arXiv  Detail & Related papers  (2023-04-06T01:09:36Z)
• GrannGAN: Graph annotation generative adversarial networks [72.66289932625742]
  We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases. In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features.
  arXiv  Detail & Related papers  (2022-12-01T11:49:07Z)
• Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoders [16.302222204710276]
  This paper proposes a new multi-level framework that jointly models node-level properties and graph-level statistics. We introduce a new micro-macro training objective for graph generation that combines node-level and graph-level losses. Our experiments show that adding micro-macro modeling to the GraphVAE model improves graph quality scores up to 2 orders of magnitude on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-10-30T13:45:21Z)
• Generating the Graph Gestalt: Kernel-Regularized Graph Representation Learning [47.506013386710954]
  A complete scientific understanding of graph data should address both global and local structure. We propose a joint model for both as complementary objectives in a graph VAE framework. Our experiments demonstrate a significant improvement in the realism of the generated graph structures, typically by 1-2 orders of magnitude of graph structure metrics.
  arXiv  Detail & Related papers  (2021-06-29T10:48:28Z)
• A Deep Latent Space Model for Graph Representation Learning [10.914558012458425]
  We propose a Deep Latent Space Model (DLSM) for directed graphs to incorporate the traditional latent variable based generative model into deep learning frameworks. Our proposed model consists of a graph convolutional network (GCN) encoder and a decoder, which are layer-wise connected by a hierarchical variational auto-encoder architecture. Experiments on real-world datasets show that the proposed model achieves the state-of-the-art performances on both link prediction and community detection tasks.
  arXiv  Detail & Related papers  (2021-06-22T12:41:19Z)

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.