Papers › GraphGPT: Graph Learning with Generative Pre-trained Transformers

GraphGPT: Graph Learning with Generative Pre-trained Transformers

31 Dec 2023arXiv:2401.00529archive 2025-07-28

Qifang Zhao, Weidong Ren, Tianyu Li, Xiaoxiao Xu, Hong Liu

We introduce GraphGPT, a novel model for Graph learning by self-supervised Generative Pre-training Transformers. Our model transforms each graph or sampled subgraph into a sequence of tokens representing the node, edge and attributes reversibly using the Eulerian path first. Then we feed the tokens into a standard transformer decoder and pre-train it with the next-token-prediction (NTP) task. Lastly, we fine-tune the GraphGPT model with the supervised tasks. This intuitive, yet effective model achieves superior or close results to the state-of-the-art methods for the graph-, edge- and node-level tasks on the large scale molecular dataset PCQM4Mv2, the protein-protein association dataset ogbl-ppa and the ogbn-proteins dataset from the Open Graph Benchmark (OGB). Furthermore, the generative pre-training enables us to train GraphGPT up to 400M+ parameters with consistently increasing performance, which is beyond the capability of GNNs and previous graph transformers. The source code and pre-trained checkpoints will be released soon (https://github.com/alibaba/graph-gpt) to pave the way for the graph foundation model research, and also to assist the scientific discovery in pharmaceutical, chemistry, material and bio-informatics domains, etc.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

alibaba/graph-gpt officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MaskGIT: Masked Generative Image Transformer (arXiv:2202.04200; that paper's own run record: 14 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderGraph Learningscientific discovery

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Link Property Prediction ogbl-citation2 GraphGPT(d1n30) Ext. data No #1 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 GraphGPT(d1n30) Number of params 133096832 #1 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 GraphGPT(d1n30) Test MRR 0.9305 ± 0.0020 #1 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 GraphGPT(d1n30) Validation MRR 0.9295 ± 0.0022 #1 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 GraphGPT(SMTP) Ext. data No #3 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 GraphGPT(SMTP) Number of params 46784128 #3 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 GraphGPT(SMTP) Test MRR 0.9055 ± 0.0016 #3 of 23 Archive leaderboard report
Link Property Prediction ogbl-citation2 GraphGPT(SMTP) Validation MRR 0.9042 ± 0.0014 #3 of 23 Archive leaderboard report
Link Property Prediction ogbl-ppa GraphGPT(SMTP) Ext. data No #3 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa GraphGPT(SMTP) Number of params 145263360 #3 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa GraphGPT(SMTP) Test Hits@100 0.6876 ± 0.0067 #3 of 26 Archive leaderboard report
Link Property Prediction ogbl-ppa GraphGPT(SMTP) Validation Hits@100 0.7017 ± 0.0044 #3 of 26 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections