# Graph Neural Networks **URL:** \ **Category:** DL4J\ **Created:** [November 10, 2022, 11:39am UTC](https://community.konduit.ai/t/graph-neural-networks/2061 "2022-11-10T11:39:08Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![partarstu](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/partarstu/32/276_2.png) [@partarstu](https://community.konduit.ai/u/partarstu)\ **Post date:** [November 10, 2022, 11:39am UTC](https://community.konduit.ai/t/graph-neural-networks/2061/1 "2022-11-10T11:39:08Z")
Hello everyone. Based on the documentation and the post from the end of July, seems like DL4J has currently no out-of-the-box support for Graph Neural Networks. Is there any support planned in the future releases? Are there maybe some basic examples of GNN implementation using SameDiff ? ---
**Author:** ![SidneyLann](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/sidneylann/32/367_2.png) [@SidneyLann](https://community.konduit.ai/u/SidneyLann)\ **Post date:** [November 10, 2022, 12:17pm UTC](https://community.konduit.ai/t/graph-neural-networks/2061/2 "2022-11-10T12:17:12Z")
I think there will have no deeplearning4j gnn, I’m using tf gnn by python4j. ---
**Author:** ![agibsonccc](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/agibsonccc/32/697_2.png) [@agibsonccc](https://community.konduit.ai/u/agibsonccc)\ **Post date:** [November 10, 2022, 11:56pm UTC](https://community.konduit.ai/t/graph-neural-networks/2061/3 "2022-11-10T23:56:43Z")
@SidneyLann @partarstu some of the building blocks are there but @SidneyLann is right that it would need some fleshing out. @partarstu could you detail more of what you might be looking for? Eg: [Is there a manual about GCN(Graph Convolutional Networks) using DL4J - #12 by xiumuzidiao](https://community.konduit.ai/t/is-there-a-manual-about-gcn-graph-convolutional-networks-using-dl4j/1931/12) It seems like some folks make it work. I think what @SidneyLann wanted was something higher level. If you’re willing to (sort of like what you did with your other models) I’d be happy to work with you on what is/isn’t supported. ---
**Author:** ![partarstu](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/partarstu/32/276_2.png) [@partarstu](https://community.konduit.ai/u/partarstu)\ **Post date:** [November 11, 2022, 12:34pm UTC](https://community.konduit.ai/t/graph-neural-networks/2061/4 "2022-11-11T12:34:57Z")
@agibsonccc , right now I’m looking for some basic stuff, nothing fancy. I posted this question because I didn’t want to re-invent the wheel in case it’s already there. But even if it’s not - 2-d convolution and FF layers will be the starting point and I’ll go on with them for now. If then I’ll need some support - I’ll definitely let you know. Thanks a lot ! ---
**Author:** ![partarstu](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/partarstu/32/276_2.png) [@partarstu](https://community.konduit.ai/u/partarstu)\ **Post date:** [November 11, 2022, 12:39pm UTC](https://community.konduit.ai/t/graph-neural-networks/2061/5 "2022-11-11T12:39:39Z")
@SidneyLann , thanks for a tip! Personally I’m not fond of using TF imported models because it brings more efforts to work with them in case I need significant modifications. I think using SameDiff directly will be a quicker solution for my case. But it’s good to know that there’s an already working model which could be imported! ---
**Author:** ![agibsonccc](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/agibsonccc/32/697_2.png) [@agibsonccc](https://community.konduit.ai/u/agibsonccc)\ **Post date:** [November 11, 2022, 1:35pm UTC](https://community.konduit.ai/t/graph-neural-networks/2061/6 "2022-11-11T13:35:20Z")
@partarstu I think he has some fair points. Some specific abstractions would be needed for most people. I do think the building blocks are there.We built this library for deepwalk (graph embeddings): > **[deeplearning4j/deeplearning4j/deeplearning4j-graph at...](https://github.com/deeplearning4j/deeplearning4j/tree/01f340ea13c4713e00f8dde23a64af75f092d283/deeplearning4j/deeplearning4j-graph)** > > 01f340ea13c4713e00f8dde23a64af75f092d283/deeplearning4j/deeplearning4j-graph The thread I linked I think has most of the basics you’d need. I think you could roll your own blocks that achieve the same results. ---
**Author:** ![partarstu](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/partarstu/32/276_2.png) [@partarstu](https://community.konduit.ai/u/partarstu)\ **Post date:** [November 11, 2022, 9:26pm UTC](https://community.konduit.ai/t/graph-neural-networks/2061/7 "2022-11-11T21:26:01Z")
@agibsonccc thanks a lot! I’ll take a look at it !