Node Classification on Non-Homophilic (Heterophilic) Graphs

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

15 leaderboard tables shown for this task, 15 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 15 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

15 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

29 shown of 29 papers with code (29 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Graph Attention Networks
  30 Oct 2017 93 repositories listed Syntology ran 50 of 106 samples · 56 unverified · 43 pointer-only (licence)
  We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph…
• Semi-Supervised Classification with Graph Convolutional Networks
  9 Sep 2016 55 repositories listed Syntology ran 31 of 58 samples · 27 unverified · 22 pointer-only (licence)
  We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs.
• Inductive Representation Learning on Large Graphs
  7 Jun 2017 20 repositories listed Syntology ran 3 of 5 samples · 2 unverified · 5 pointer-only (licence)
  Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions.
• Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
  27 Oct 2020 7 repositories listed Syntology ran 2 of 5 samples · 3 unverified · 2 pointer-only (licence)
  Graph Neural Networks (GNNs) are the predominant technique for learning over graphs.
• Simplifying Graph Convolutional Networks
  19 Feb 2019 7 repositories listed Syntology ran 3 of 8 samples · 5 unverified
  Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations.
• Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
  27 Oct 2021 5 repositories listed Syntology ran 7 of 21 samples · 14 unverified · 4 pointer-only (licence)
  Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other.
• Predict then Propagate: Graph Neural Networks meet Personalized PageRank
  14 Oct 2018 5 repositories listed Syntology ran 1 of 12 samples · 11 unverified
  We utilize this propagation procedure to construct a simple model, personalized propagation of neural predictions (PPNP), and its fast approximation, APPNP.
• Simple and Deep Graph Convolutional Networks
  4 Jul 2020 4 repositories listed Syntology ran 5 of 7 samples · 2 unverified · 4 pointer-only (licence)
  We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}.
• Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
  20 Jun 2020 4 repositories listed Syntology ran 13 of 21 samples · 8 unverified · 6 pointer-only (licence)
  We investigate the representation power of graph neural networks in the semi-supervised node classification task under heterophily or low homophily, i.
• Geom-GCN: Geometric Graph Convolutional Networks
  13 Feb 2020 4 repositories listed Syntology ran 7 of 7 samples · 0 unverified · 7 pointer-only (licence)
  From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses.
• MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
  30 Apr 2019 3 repositories listed
  Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships.
• Scale Invariance of Graph Neural Networks
  28 Nov 2024 1 repository listed
  We address two fundamental challenges in Graph Neural Networks (GNNs): (1) the lack of theoretical support for invariance learning, a critical property in image processing, and (2) the absence of a unified model capable…
• Edge Directionality Improves Learning on Heterophilic Graphs
  17 May 2023 1 repository listed Syntology ran 3 of 5 samples · 2 unverified
  Graph Neural Networks (GNNs) have become the de-facto standard tool for modeling relational data.
• Addressing Heterophily in Node Classification with Graph Echo State Networks
  14 May 2023 1 repository listed
  Node classification tasks on graphs are addressed via fully-trained deep message-passing models that learn a hierarchy of node representations via multiple aggregations of a node's neighbourhood.
• GCNH: A Simple Method For Representation Learning On Heterophilous Graphs
  21 Apr 2023 1 repository listed
  Yet, achievement of consistent GNN performance on heterophilous graphs remains an open research problem.
• Graph Neural Networks with Learnable and Optimal Polynomial Bases
  24 Feb 2023 1 repository listed
  Second, we examine the supposedly unsolvable definition of optimal polynomial basis from Wang & Zhang (2022) and propose a simple model, OptBasisGNN, which computes the optimal basis for a given graph structure and…
• Clenshaw Graph Neural Networks
  29 Oct 2022 1 repository listed
  Graph Convolutional Networks (GCNs), which use a message-passing paradigm with stacked convolution layers, are foundational methods for learning graph representations.
• Revisiting Heterophily For Graph Neural Networks
  14 Oct 2022 1 repository listed Syntology ran 2 of 7 samples · 5 unverified
  ACM is more powerful than the commonly used uni-channel framework for node classification tasks on heterophilic graphs and is easy to be implemented in baseline GNN layers.
• Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
  15 May 2022 1 repository listed
  Further, for other homophilous nodes excluded in the neighborhood, they are ignored for information aggregation.
• Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
  9 Feb 2022 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  In this paper, we use cellular sheaf theory to show that the underlying geometry of the graph is deeply linked with the performance of GNNs in heterophilic settings and their oversmoothing behaviour.
• Deformable Graph Convolutional Networks
  29 Dec 2021 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  To address the two common problems of graph convolution, in this paper, we propose Deformable Graph Convolutional Networks (Deformable GCNs) that adaptively perform convolution in multiple latent spaces and capture…
• BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
  21 Jun 2021 1 repository listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  Many representative graph neural networks, e.
• Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
  11 Jun 2021 1 repository listed Syntology ran 1 of 12 samples · 11 unverified
  We find that the prediction performance of a wide range of GNN models is highly correlated with the node level assortativity.
• New Benchmarks for Learning on Non-Homophilous Graphs
  3 Apr 2021 1 repository listed
  Much data with graph structures satisfy the principle of homophily, meaning that connected nodes tend to be similar with respect to a specific attribute.
• Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
  12 Feb 2021 1 repository listed
  We are the first to take a unified perspective to jointly explain the oversmoothing and heterophily problems at the node level.
• Beyond Low-frequency Information in Graph Convolutional Networks
  4 Jan 2021 1 repository listed
  For a deeper understanding, we theoretically analyze the roles of low-frequency signals and high-frequency signals on learning node representations, which further explains why FAGCN can perform well on different types…
• Adaptive Universal Generalized PageRank Graph Neural Network
  14 Jun 2020 1 repository listed Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)
  We address these issues by introducing a new Generalized PageRank (GPR) GNN architecture that adaptively learns the GPR weights so as to jointly optimize node feature and topological information extraction, regardless…
• Non-Local Graph Neural Networks
  29 May 2020 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Modern graph neural networks (GNNs) learn node embeddings through multilayer local aggregation and achieve great success in applications on assortative graphs.
• Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
  5 Jun 2019 1 repository listed Syntology ran 1 of 9 samples · 8 unverified
  Recently, neural network based approaches have achieved significant improvement for solving large, complex, graph-structured problems.

Syntology lines on 19 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.