Exphormer: Sparse transformers for graphs
H Shirzad, A Velingker… - International …, 2023 - proceedings.mlr.press
Graph transformers have emerged as a promising architecture for a variety of graph learning
and representation tasks. Despite their successes, though, it remains challenging to scale …
and representation tasks. Despite their successes, though, it remains challenging to scale …
Half-Hop: A graph upsampling approach for slowing down message passing
Message passing neural networks have shown a lot of success on graph-structured data.
However, there are many instances where message passing can lead to over-smoothing or …
However, there are many instances where message passing can lead to over-smoothing or …
Graph Decipher: A transparent dual‐attention graph neural network to understand the message‐passing mechanism for the node classification
Graph neural networks (GNNs) can be effectively applied to solve many real‐world
problems across widely diverse fields. Their success is inseparable from the message …
problems across widely diverse fields. Their success is inseparable from the message …
Graphfm: A scalable framework for multi-graph pretraining
Graph neural networks are typically trained on individual datasets, often requiring highly
specialized models and extensive hyperparameter tuning. This dataset-specific approach …
specialized models and extensive hyperparameter tuning. This dataset-specific approach …
Clarify confused nodes via separated learning
Graph neural networks (GNNs) have achieved remarkable advances in graph-oriented
tasks. However, real-world graphs invariably contain a certain proportion of heterophilous …
tasks. However, real-world graphs invariably contain a certain proportion of heterophilous …
Learning to Approximate Adaptive Kernel Convolution on Graphs
Various Graph Neural Networks (GNN) have been successful in analyzing data in non-
Euclidean spaces, however, they have limitations such as oversmoothing, ie, information …
Euclidean spaces, however, they have limitations such as oversmoothing, ie, information …
Self-Training Based Few-Shot Node Classification by Knowledge Distillation
Self-training based few-shot node classification (FSNC) methods have shown excellent
performance in real applications, but they cannot make the full use of the information in the …
performance in real applications, but they cannot make the full use of the information in the …
MS-GDA: Improving Heterogeneous Recipe Representation via Multinomial Sampling Graph Data Augmentation
We study the problem of classifying different cooking styles, based on the recipe. The
difficulty is that the same food ingredients, seasoning, and the very similar instructions result …
difficulty is that the same food ingredients, seasoning, and the very similar instructions result …
A multi-relational neighbors constructed graph neural network for heterophily graph learning
H Xu, Y Gao, Q Liu, M Bie, X Che - Applied Intelligence, 2025 - Springer
Graph neural networks (GNNs) have shown great power in exploring graph representation.
However, most current GNNs are based on the homophily assumption and they have two …
However, most current GNNs are based on the homophily assumption and they have two …
Portraying Fine-grained Tenant Portrait for Churn Prediction using Semi-supervised Graph Convolution and Attention Network
Z Jin, P Qi, M Yao, D Tao - IEEE Transactions on Big Data, 2025 - ieeexplore.ieee.org
With the widespread application of big data and intelligent information systems, the tenant
has become the main form of most scenarios. As a data mining technique, the portrait has …
has become the main form of most scenarios. As a data mining technique, the portrait has …