# Adaptive Graph Diffusion Networks

arXiv: https://arxiv.org/abs/2012.15024 · HTML: https://mlsanity.com/paper/2012.15024/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2020.

## Built on by (most cited first, 13 of 13)

- [Language is All a Graph Needs](https://mlsanity.com/paper/2308.07134/) (2023)
- [DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion](https://mlsanity.com/paper/2301.09474/) (2023)
- [GraphGPT: Generative Pre-trained Graph Eulerian Transformer](https://mlsanity.com/paper/2401.00529/) (2023)
- [Contextualized Messages Boost Graph Representations](https://mlsanity.com/paper/2403.12529/) (2024)
- [Integrating Structural and Semantic Signals in Text-Attributed Graphs with BiGTex](https://mlsanity.com/paper/2504.12474/) (2025)
- [Ensemble Learning for Graph Neural Networks](https://mlsanity.com/paper/2310.14166/) (2023)
- [Transformers from Diffusion: A Unified Framework for Neural Message Passing](https://mlsanity.com/paper/2409.09111/) (2024)
- [Disentangling Node Attributes from Graph Topology for Improved Generalizability in Link Prediction](https://mlsanity.com/paper/2307.08877/) (2023)
- [Circle Feature Graphormer: Can Circle Features Stimulate Graph Transformer?](https://mlsanity.com/paper/2309.06574/) (2023)
- [Graph Coordinates and Conventional Neural Networks -- An Alternative for Graph Neural Networks](https://mlsanity.com/paper/2312.01342/) (2023)
- [All Nodes are created Not Equal: Node-Specific Layer Aggregation and Filtration for GNN](https://mlsanity.com/paper/2405.07892/) (2024)
- [Enhancing Graph Representations with Neighborhood-Contextualized Message-Passing](https://mlsanity.com/paper/2511.11046/) (2025)
- [Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs](https://mlsanity.com/paper/2606.01660/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have received much attention in the graph deep learning domain. However, recent research empirically and theoretically shows that deep GNNs suffer from over-fitting and over-smoothing problems. The usual solutions either cannot solve extensive runtime of deep GNNs or restrict graph convolution in the same feature space. We propose the Adaptive Graph Diffusion Networks (AGDNs) which perform multi-layer generalized graph diffusion in different feature spaces with moderate complexity and runtime. Standard graph diffusion methods combine large and dense powers of the transition matrix with predefined weighting coefficients. Instead, AGDNs combine smaller multi-hop node representations with learnable and generalized weighting coefficients. We propose two scalable mechanisms of weighting coefficients to capture multi-hop information: Hop-wise Attention (HA) and Hop-wise Convolution (HC). We evaluate AGDNs on diverse, challenging Open Graph Benchmark (OGB) datasets with semi-supervised node classification and link prediction tasks. Until the date of submission (Aug 26, 2022), AGDNs achieve top-1 performance on the ogbn-arxiv, ogbn-proteins and ogbl-ddi datasets and top-3 performance on the ogbl-citation2 dataset. On the similar Tesla V100 GPU cards, AGDNs outperform Reversible GNNs (RevGNNs) with 13% complexity and 1% training runtime of RevGNNs on the ogbn-proteins dataset. AGDNs also achieve comparable performance to SEAL with 36% training and 0.2% inference runtime of SEAL on the ogbl-citation2 dataset.