A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
Graphs are structured data that models complex relations between real-world entities.
Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar …
Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar …
Graphglow: Universal and generalizable structure learning for graph neural networks
Graph structure learning is a well-established problem that aims at optimizing graph
structures adaptive to specific graph datasets to help message passing neural networks (ie …
structures adaptive to specific graph datasets to help message passing neural networks (ie …
Grapes: Learning to sample graphs for scalable graph neural networks
Graph neural networks (GNNs) learn to represent nodes by aggregating information from
their neighbors. As GNNs increase in depth, their receptive field grows exponentially …
their neighbors. As GNNs increase in depth, their receptive field grows exponentially …
Learning Adaptive Multiresolution Transforms via Meta-Framelet-based Graph Convolutional Network
Graph Neural Networks are popular tools in graph representation learning that capture the
graph structural properties. However, most GNNs employ single-resolution graph feature …
graph structural properties. However, most GNNs employ single-resolution graph feature …
ReFNet: Rehearsal-based graph lifelong learning with multi-resolution framelet graph neural networks
M Li, X Yang, Y Chen, S Zhou, Y Gu, Q Hu - Information Sciences, 2025 - Elsevier
Graph lifelong learning (GLL), also known as graph continual or incremental learning,
focuses on adapting to new tasks presented by emerging graph data while preserving the …
focuses on adapting to new tasks presented by emerging graph data while preserving the …
Disentangled Active Learning on Graphs
Active learning on graphs (ALG) has emerged as a compelling research field due to its
capacity to address the challenge of label scarcity. Existing ALG methods incorporate …
capacity to address the challenge of label scarcity. Existing ALG methods incorporate …
Denoising Multiscale Spectral Graph Wavelet Neural Networks for Gas Utilization Ratio Prediction in Blast Furnace
C Liu, J Li, Y Li, J Tan - IEEE Transactions on Neural Networks …, 2024 - ieeexplore.ieee.org
Given the crucial role of the gas utilization ratio (GUR) in reflecting blast furnace operation
and energy consumption, accurately predicting its development trend holds significant value …
and energy consumption, accurately predicting its development trend holds significant value …
Benchmarking Spectral Graph Neural Networks: A Comprehensive Study on Effectiveness and Efficiency
With the recent advancements in graph neural networks (GNNs), spectral GNNs have
received increasing popularity by virtue of their specialty in capturing graph signals in the …
received increasing popularity by virtue of their specialty in capturing graph signals in the …
SLOG: An Inductive Spectral Graph Neural Network Beyond Polynomial Filter
Graph neural networks (GNNs) have exhibited superb power in many graph related tasks.
Existing GNNs can be categorized into spatial GNNs and spectral GNNs. The spatial GNNs …
Existing GNNs can be categorized into spatial GNNs and spectral GNNs. The spatial GNNs …