Graph embeddings are one of my favorite underused things in ML.<p>I've used them to do things like characterise users based on follow/follower patterns, but there are many more applications.<p>In the past I've had great success with Facebook Research's StarSpace
I've been doing some work on link prediction in knowledge graphs recently with poor results on real-world data. These methods don't necessarily require a huge amount of data but they are very sensitive to noise and the 'density' of dataset. The benchmark datasets are, in essence, very easy to get good performance on. It's a real shame that metrics for these methods' tolerance of noise and sparsity are not reported because these are going to be present in almost any real-world dataset in far greater quantities than current benchmarks.
Looks very seriously made and documented, congrats ! Was looking at it a bit closely the other days and put it onto my list of future tools. There's been another somewhat related library released by facebook recently, <a href="https://ai.facebook.com/blog/open-sourcing-pytorch-biggraph-for-faster-embeddings-of-extremely-large-graphs/" rel="nofollow">https://ai.facebook.com/blog/open-sourcing-pytorch-biggraph-...</a>
Can you help me understand, what are possible inputs to ampligraph?<p>I think the main use-case is plugging in an existing knowledge graph, and it filling in the gaps, correct?<p>Can I augment this will really high-quality embeddings for the nodes, that were learned over auxiliary unlabelled text?<p>What are other ways I can augment the data set?<p>Is this useful only when there are many edge-types, or is it also good when there are very few?<p>It looks promising, I just couldn't immediately grok when I use should look to this library.
Cool. KGE methods are becoming more and more useful as companies are trying to find ways to interface some internal knowledge graph with machine learning techniques. I expect this space to grow substantially!
btw, we are hiring research engineers here in our Dublin Lab. Send me an email if interested: luca.costabello@accenture.com
<a href="https://www.accenture.com/ie-en/careers/jobdetails?src=&id=00693824_en" rel="nofollow">https://www.accenture.com/ie-en/careers/jobdetails?src=&id=0...</a>