English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We introduce \textit{GraphGPT}, a novel model for Graph learning byself-supervised Generative Pre-training Transformers. Our model transforms eachgraph or sampled subgraph into a sequence of tokens representing the node, edgeand attributes reversibly using the Eulerian path first. Then we feed thetokens into a standard transformer decoder and pre-train it with thenext-token-prediction (NTP) task. Lastly, we fine-tune the GraphGPT model withthe supervised tasks. This intuitive, yet effective model achieves superior orclose results to the state-of-the-art methods for the graph-, edge- andnode-level tasks on the large scale molecular dataset PCQM4Mv2, theprotein-protein association dataset ogbl-ppa and the ogbn-proteins dataset fromthe Open Graph Benchmark (OGB). Furthermore, the generative pre-trainingenables us to train GraphGPT up to 400M+ parameters with consistentlyincreasing performance, which is beyond the capability of GNNs and previousgraph transformers. The source code and pre-trained checkpoints will bereleased soon\footnote{\url{https://github.com/alibaba/graph-gpt}} to pave theway for the graph foundation model research, and also to assist the scientificdiscovery in pharmaceutical, chemistry, material and bio-informatics domains,etc.

GraphGPT: Graph Learning with Generative Pre-trained Transformers