Graph Property Prediction

Benchmarks archive 2025-07-28

5 leaderboard tables shown for this task, 5 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.

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

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

Subtasks archive 2025-07-28

7 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 47 papers with code (56 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.

• Generative Adversarial Networks
  10 Jun 2014 189 repositories listed Syntology ran 23 of 55 samples · 32 unverified · 18 pointer-only (licence)
  We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D…
• How Attentive are Graph Attention Networks?
  30 May 2021 8 repositories listed Syntology ran 6 of 16 samples · 10 unverified · 1 pointer-only (licence)
  Because GATs use a static attention mechanism, there are simple graph problems that GAT cannot express: in a controlled problem, we show that static attention hinders GAT from even fitting the training data.
• Do Transformers Really Perform Bad for Graph Representation?
  9 Jun 2021 5 repositories listed
  Our key insight to utilizing Transformer in the graph is the necessity of effectively encoding the structural information of a graph into the model.
• E(n) Equivariant Graph Neural Networks
  19 Feb 2021 5 repositories listed Syntology ran 15 of 15 samples · 0 unverified · 7 pointer-only (licence)
  This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs).
• Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
  23 Jun 2022 4 repositories listed Syntology ran 3 of 4 samples · 1 unverified
  Despite their widespread success in various domains, Transformer networks have yet to perform well across datasets in the domain of 3D atomistic graphs such as molecules even when 3D-related inductive biases like…
• Recipe for a General, Powerful, Scalable Graph Transformer
  25 May 2022 4 repositories listed Syntology ran 3 of 21 samples · 18 unverified
  We propose a recipe on how to build a general, powerful, scalable (GPS) graph Transformer with linear complexity and state-of-the-art results on a diverse set of benchmarks.
• Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification
  6 Dec 2020 4 repositories listed
  Our studies demonstrate that the proposed DAM method improves the performance of optimizing cross-entropy loss by a large margin, and also achieves better performance than optimizing the existing AUC square loss on…
• Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers
  7 Feb 2024 3 repositories listed Syntology ran 10 of 13 samples · 3 unverified
  We also obtain SOTA results on QM9, MOLPCBA, and LIT-PCBA molecular property prediction benchmarks via transfer learning.
• Global Self-Attention as a Replacement for Graph Convolution
  7 Aug 2021 3 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  The resultant framework - which we call Edge-augmented Graph Transformer (EGT) - can directly accept, process and output structural information of arbitrary form, which is important for effective learning on…
• DeeperGCN: All You Need to Train Deeper GCNs
  13 Jun 2020 3 repositories listed
  Graph Convolutional Networks (GCNs) have been drawing significant attention with the power of representation learning on graphs.
• GotenNet: Rethinking Efficient 3D Equivariant Graph Neural Networks
  24 Apr 2025 2 repositories listed
  Understanding complex three-dimensional (3D) structures of graphs is essential for accurately modeling various properties, yet many existing approaches struggle with fully capturing the intricate spatial relationships…
• Global Concept Explanations for Graphs by Contrastive Learning
  25 Apr 2024 2 repositories listed
  Overall, our results show promising capability to extract the underlying structure-property relationships for complex graph property prediction tasks.
• EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
  21 Jun 2023 2 repositories listed Syntology ran 3 of 5 samples · 2 unverified
  Equivariant Transformers such as Equiformer have demonstrated the efficacy of applying Transformers to the domain of 3D atomistic systems.
• A new perspective on building efficient and expressive 3D equivariant graph neural networks
  7 Apr 2023 2 repositories listed
  Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects.
• Nested Graph Neural Networks
  25 Oct 2021 2 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  The key is to make each node representation encode a subgraph around it more than a subtree.
• Geometric and Physical Quantities Improve E(3) Equivariant Message Passing
  6 Oct 2021 2 repositories listed Syntology ran 0 of 8 samples · 8 unverified
  Including covariant information, such as position, force, velocity or spin is important in many tasks in computational physics and chemistry.
• Weisfeiler and Lehman Go Cellular: CW Networks
  23 Jun 2021 2 repositories listed
  Nevertheless, these models can be severely constrained by the rigid combinatorial structure of Simplicial Complexes (SCs).
• Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence
  13 Feb 2025 1 repository listed Syntology ran 4 of 12 samples · 8 unverified
  Message-passing Graph Neural Networks (GNNs) are often criticized for their limited expressiveness, issues like over-smoothing and over-squashing, and challenges in capturing long-range dependencies, while Graph…
• Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning
  26 Dec 2024 1 repository listed
  In the real world, however, the graph data can suffer from significant distribution shifts across clients as the clients may collect their graph data for different purposes.
• Data-Driven Self-Supervised Graph Representation Learning
  24 Dec 2024 1 repository listed
  Our approach is general that it can be applied to homogeneous and heterogeneous graphs.
• Next Level Message-Passing with Hierarchical Support Graphs
  22 Jun 2024 1 repository listed Syntology ran 4 of 10 samples · 6 unverified
  Message-Passing Neural Networks (MPNNs) are extensively employed in graph learning tasks but suffer from limitations such as the restricted scope of information exchange, by being confined to neighboring nodes during…
• Towards Neural Scaling Laws for Foundation Models on Temporal Graphs
  14 Jun 2024 1 repository listed Syntology ran 4 of 5 samples · 1 unverified
  Next, we evaluate the transferability of Temporal Graph Neural Networks (TGNNs) for the temporal graph property prediction task by pre-training on a collection of up to sixty-four token transaction networks and then…
• Learning Long Range Dependencies on Graphs via Random Walks
  5 Jun 2024 1 repository listed Syntology ran 13 of 13 samples · 0 unverified
  Message-passing graph neural networks (GNNs) excel at capturing local relationships but struggle with long-range dependencies in graphs.
• Graph neural networks with configuration cross-attention for tensor compilers
  26 May 2024 1 repository listed
  With the recent popularity of neural networks comes the need for efficient serving of inference workloads.
• Contextualized Messages Boost Graph Representations
  19 Mar 2024 1 repository listed
  In the paper, a novel perspective on the representational capability of GNNs is investigated across all levelsx2014node-level, neighborhood-level, and graph-levelx2014when the space of node feature representation is…
• Graph Transformers for Large Graphs
  18 Dec 2023 1 repository listed Syntology ran 2 of 5 samples · 3 unverified · 5 pointer-only (licence)
  As such, a key innovation of this work lies in the creation of a fast neighborhood sampling technique coupled with a local attention mechanism that encompasses a 4-hop reception field, but achieved through just 2-hop…
• TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs
  25 Aug 2023 1 repository listed Syntology ran 2 of 4 samples · 2 unverified
  TpuGraphs provides 25x more graphs than the largest graph property prediction dataset (with comparable graph sizes), and 770x larger graphs on average compared to existing performance prediction datasets on machine…
• Learning Large Graph Property Prediction via Graph Segment Training
  21 May 2023 1 repository listed Syntology ran 6 of 8 samples · 2 unverified
  Here we propose Graph Segment Training (GST), a general framework that utilizes a divide-and-conquer approach to allow learning large graph property prediction with a constant memory footprint.
• Graph Propagation Transformer for Graph Representation Learning
  19 May 2023 1 repository listed Syntology ran 4 of 8 samples · 4 unverified · 8 pointer-only (licence)
  The core insight of our method is to fully consider the information propagation among nodes and edges in a graph when building the attention module in the transformer blocks.
• Data-Centric Learning from Unlabeled Graphs with Diffusion Model
  17 Mar 2023 1 repository listed Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)
  A conventional approach is training a model with the unlabeled graphs on self-supervised tasks and then fine-tuning the model on the prediction tasks.

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.