CIPE constructs graph positional encodings from communicability so that self-attention similarities equal the sum of all-path contributions between nodes, yielding 35.5% average gains on seven benchmarks over structure-agnostic Transformers.
Transformer for graphs: An overview from architecture perspective
8 Pith papers cite this work, alongside 73 external citations. Polarity classification is still indexing.
8
Pith papers citing it
73
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.
Learnable graph patches enable domain-agnostic pre-training of graph models by decomposing heterogeneous graphs into transferable semantic units via patch encoders and aggregators.
The survey groups attention-based GNNs into three stages—graph recurrent attention networks, graph attention networks, and graph transformers—while reviewing architectures and future directions.
Cold users dominate fake news datasets, and the User Evidence Network approximates their absent behavior data from existing user interactions to enable robust misinformation detection.
A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.
RL-SPH is an RL-based start primal heuristic that learns to turn infeasible starting points into feasible integer linear programming solutions, including problems with non-binary integers.
citing papers explorer
-
Communicability-Inspired Positional Encoding (CIPE)
CIPE constructs graph positional encodings from communicability so that self-attention similarities equal the sum of all-path contributions between nodes, yielding 35.5% average gains on seven benchmarks over structure-agnostic Transformers.
-
Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation
GaRA generates task-specific LoRA weight updates conditioned on graph structures to enable better whole-graph encoding in LLMs for zero-shot graph learning.
-
Handling Feature Heterogeneity with Learnable Graph Patches
Learnable graph patches enable domain-agnostic pre-training of graph models by decomposing heterogeneous graphs into transferable semantic units via patch encoders and aggregators.
-
Attention-based graph neural networks: a survey
The survey groups attention-based GNNs into three stages—graph recurrent attention networks, graph attention networks, and graph transformers—while reviewing architectures and future directions.
-
Real-World Challenges in Fake News Detection: Dealing with Posts by Cold Users
Cold users dominate fake news datasets, and the User Evidence Network approximates their absent behavior data from existing user interactions to enable robust misinformation detection.
-
Retrieval-Augmented Generation with Graphs (GraphRAG)
A survey proposing a holistic GraphRAG framework with components including query processor, retriever, organizer, generator, and data source, plus domain-tailored reviews, challenges, and future directions.
-
RL-SPH: Learning to Achieve Feasible Solutions for Integer Linear Programs
RL-SPH is an RL-based start primal heuristic that learns to turn infeasible starting points into feasible integer linear programming solutions, including problems with non-binary integers.
- BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning