Re: Introducing AmpliGraph: a TensorFlow-based Library for Knowledge Graph Embeddings

Hi Luca,
Many thanks for this great tool! 
I was playing around and wanted to know if you were able (in our different experiments) to get the same result:
(1) - either by running different times in the same ENV
(2)  - either by running the same code in a different ENV 

In my use case, in both cases (1), (2), I have different results. I’ve even added a random.see() but still having the same issue. 

Could you point me to how I can guarantee the same result with different settings and/or different runs of the same code?

Cheers,
Ghislain 
 
> Le 3 avr. 2019 à 15:41, Costabello, Luca <luca.costabello@accenture.com> a écrit :
> 
> Hello everybody,
>  
> We are happy to share AmpliGraph, a suite of neural machine learning models for relational representation learning.
>  
> You can use it to discover new knowledge from an existing knowledge graph, find missing statements, or play around with embeddings generated from graphs.
>  
> We designed APIs and documentation to make knowledge graph embeddings accessible to inexperienced users, while also giving researchers a shared library to assess the performance of new models for fair and reproducible experiments.
>  
> AmpliGraph natively supports RDF graphs, and we hope it can be a useful tool for the Web of Data community.
>  
> Anybody interested in machine learning on graphs (whether this means using AmpliGraph in your project, or extending the codebase), just feel free to ping us - many ways to contribute!
>  
> AmpliGraph is licensed under the Apache 2.0 licence.
>  
> pip install ampligraph
>  
> GitHub: http://ampligraph.org <http://ampligraph.org/>  
> Documentation and examples: https://docs.ampligraph.org <https://docs.ampligraph.org/>
>  
>  
> Luca
> Accenture Labs Dublin
> 
> 
> This message is for the designated recipient only and may contain privileged, proprietary, or otherwise confidential information. If you have received it in error, please notify the sender immediately and delete the original. Any other use of the e-mail by you is prohibited. Where allowed by local law, electronic communications with Accenture and its affiliates, including e-mail and instant messaging (including content), may be scanned by our systems for the purposes of information security and assessment of internal compliance with Accenture policy. Your privacy is important to us. Accenture uses your personal data only in compliance with data protection laws. For further information on how Accenture processes your personal data, please see our privacy statement at https://www.accenture.com/us-en/privacy-policy <https://www.accenture.com/us-en/privacy-policy>. 
> ______________________________________________________________________________________
> 
> www.accenture.com <http://www.accenture.com/>
---------------------------------------
Ghislain A. Atemezing, Ph.D
Mail: ghislain.atemezing@gmail.com
Web: https://w3id.org/people/gatemezing <http://www.atemezing.org/>
Twitter: @gatemezing
About Me: https://about.me/ghislain.atemezing <https://about.me/ghislain.atemezing>

Received on Tuesday, 7 May 2019 10:29:42 UTC