Message Detouring: A Simple Yet Effective Cycle Representation for Expressive Graph Learning

Graph learning is crucial in the fields of bioinformatics, social networks, and chemicals. Although high-order graphlets, such as cycles, are critical to achieving an informative graph representation for node classification, edge prediction, and graph recognition, modeling high-order topological characteristics poses significant computational challenges, restricting its widespread applications in machine learning. To address this limitation, we introduce the concept of \textit{message detouring} to hierarchically characterize cycle representation throughout the entire graph, which capitalizes on the contrast between the shortest and longest pathways within a range of local topologies associated with each graph node. The topological feature representations derived from our message detouring landscape demonstrate comparable expressive power to high-order \textit{Weisfeiler-Lehman} (WL) tests but much less computational demands. In addition to the integration with graph kernel and message passing neural networks, we present a novel message detouring neural network, which uses Transformer backbone to integrate cycle representations across nodes and edges. Aside from theoretical results, experimental results on expressiveness, graph classification, and node classification show message detouring can significantly outperform current counterpart approaches on various benchmark datasets.

Learning to Approximate Adaptive Kernel Convolution on Graphs

Various Graph Neural Networks (GNNs) have been successful in analyzing data in non-Euclidean spaces, however, they have limitations such as oversmoothing, i.e., information becomes excessively averaged as the number of hidden layers increases. The issue stems from the intrinsic formulation of conventional graph convolution where the nodal features are aggregated from a direct neighborhood per layer across the entire nodes in the graph. As setting different number of hidden layers per node is infeasible, recent works leverage a diffusion kernel to redefine the graph structure and incorporate information from farther nodes. Unfortunately, such approaches suffer from heavy diagonalization of a graph Laplacian or learning a large transform matrix. In this regards, we propose a diffusion learning framework, where the range of feature aggregation is controlled by the scale of a diffusion kernel. For efficient computation, we derive closed-form derivatives of approximations of the graph convolution with respect to the scale, so that node-wise range can be adaptively learned. With a downstream classifier, the entire framework is made trainable in an end-to-end manner. Our model is tested on various standard datasets for node-wise classification for the state-of-the-art performance, and it is also validated on a real-world brain network data for graph classifications to demonstrate its practicality for Alzheimer classification.

Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals

Graph neural networks (GNNs) are widely used in domains like social networks and biological systems. However, the locality assumption of GNNs, which limits information exchange to neighboring nodes, hampers their ability to capture long-range dependencies and global patterns in graphs. To address this, we propose a new inductive bias based on variational analysis, drawing inspiration from the Brachistochrone problem. Our framework establishes a mapping between discrete GNN models and continuous diffusion functionals. This enables the design of application-specific objective functions in the continuous domain and the construction of discrete deep models with mathematical guarantees. To tackle over-smoothing in GNNs, we analyze the existing layer-by-layer graph embedding models and identify that they are equivalent to l2-norm integral functionals of graph gradients, which cause over-smoothing. Similar to edge-preserving filters in image denoising, we introduce total variation (TV) to align the graph diffusion pattern with global community topologies. Additionally, we devise a selective mechanism to address the trade-off between model depth and over-smoothing, which can be easily integrated into existing GNNs. Furthermore, we propose a novel generative adversarial network (GAN) that predicts spreading flows in graphs through a neural transport equation. To mitigate vanishing flows, we customize the objective function to minimize transportation within each community while maximizing inter-community flows. Our GNN models achieve state-of-the-art (SOTA) performance on popular graph learning benchmarks such as Cora, Citeseer, and Pubmed.

DeepGraphDMD: Interpretable Spatio-Temporal Decomposition of Non-linear Functional Brain Network Dynamics

Functional brain dynamics is supported by parallel and overlapping functional network modes that are associated with specific neural circuits. Decomposing these network modes from fMRI data and finding their temporal characteristics is challenging due to their time-varying nature and the non-linearity of the functional dynamics. Dynamic Mode Decomposition (DMD) algorithms have been quite popular for solving this decomposition problem in recent years. In this work, we apply GraphDMD -- an extension of the DMD for network data -- to extract the dynamic network modes and their temporal characteristics from the fMRI time series in an interpretable manner. GraphDMD, however, regards the underlying system as a linear dynamical system that is sub-optimal for extracting the network modes from non-linear functional data. In this work, we develop a generalized version of the GraphDMD algorithm -- DeepGraphDMD -- applicable to arbitrary non-linear graph dynamical systems. DeepGraphDMD is an autoencoder-based deep learning model that learns Koopman eigenfunctions for graph data and embeds the non-linear graph dynamics into a latent linear space. We show the effectiveness of our method in both simulated data and the HCP resting-state fMRI data. In the HCP data, DeepGraphDMD provides novel insights into cognitive brain functions by discovering two major network modes related to fluid and crystallized intelligence.

Pathology Steered Stratification Network for Subtype Identification in Alzheimer's Disease

Alzheimer's disease (AD) is a heterogeneous, multifactorial neurodegenerative disorder characterized by beta-amyloid, pathologic tau, and neurodegeneration. The massive heterogeneity between neurobiological examinations and clinical assessment is the current biggest challenge in the early diagnosis of Alzheimer's disease, urging for a comprehensive stratification of the aging population that is defined by reliable neurobiological biomarkers and closely associated with clinical outcomes. However, existing statistical inference approaches in neuroimaging studies of AD subtype identification fail to take into account the neuropathological domain knowledge, which could lead to ill-posed results that are sometimes inconsistent with neurological principles. To fill this knowledge gap, we propose a novel pathology steered stratification network (PSSN) that integrates mainstream AD pathology with multimodal longitudinal neuroimaging data to categorize the aging population. By combining theory-based biological modeling and data-driven deep learning, this cross-disciplinary approach can not only generate long-term biomarker prediction consistent with the end-state of individuals but also stratifies subjects into fine-grained subtypes with distinct neurological underpinnings, where ag-ing brains within the same subtype share com-mon biological behaviors that emerge as similar trajectories of cognitive decline. Our stratification outperforms K-means and SuStaIn in both inter-cluster heterogeneity and intra-cluster homogeneity of various clinical scores. Importantly, we identify six subtypes spanning AD spectrum, where each subtype exhibits a distinctive biomarker pattern that is consistent with its clinical outcome. A disease evolutionary graph is further provided by quantifying subtype transition probabilities, which may assist pre-symptomatic diagnosis and guide therapeutic treatments.

Multi-resolution Graph Neural Network for Identifying Disease-specific Variations in Brain Connectivity

Convolution Neural Network (CNN) recently have been adopted in several neuroimaging studies for diagnosis capturing disease-specific changes in the brain. While many of these methods are designed to work with images in $\mathbb R^n$ exploiting regular structure of the domain, they are not well-suited to analyze data with irregular structure such as brain connectivity. As there is significant interest in understanding the altered interactions between different brain regions that lead to neuro-disorders, it is important to develop data-driven methods that work with a population of graph data for traditional prediction tasks. In this regime, we propose a novel CNN-based framework with adaptive graph transforms to learn the most disease-relevant connectome feature maps which have the highest discrimination power across diagnostic categories. The backbone of our framework is a multi-resolution representation of the graph matrix which is steered by a set of wavelet-like graph transforms. In this context, our supervised graph learning framework outperforms conventional graph methods that predict diagnostic label only based on the underlying individual graph. Our extensive experiments on two real datasets of functional and structural brain networks show that our multi-resolution framework achieves significantly higher accuracy, precision and recall in predicting diagnostic labels and identifying disease-specific brain connectivities that are associated with brain disorders such as Attention-Deficit/Hyperactivity Disorder (ADHD) and Alzheimer's Disease (AD).