Day 60 of #100daysofnetworks
Graph Context: Groups and Categories
Hello everyone! Today is DAY SIXTY! We have made some major progress, and it will be fun to pause and reflect on what we have gotten through. But that is a task for another day! Today, we continue in our efforts to create a useful Knowledge Graph of Artificial Life Research!
Over the last several weeks, we have done a lot of Knowledge Graph work. If you are new here, you should go to this blog’s archive and read from Day 48 up to now. We are on day 60, and that indicates how much effort we have spent on this, so far.
Here is the latest article, prior to what you are currently reading. In that article, I describe how we added temporal capabilities to our Knowledge Graph. Today, we will go even further, and after today, we will use this Knowledge Graph for GraphRAG and Artificial Intelligence.
Latest Improvements and Reasoning
I’ll just do this as a show-and-tell. You will be able to see the results as I describe the work that led to the results. Today, I added two additional node types:
Groups
Categories
You can see some of the groups that are related to Artificial Life research in some way.
Categories, on the other hand, are more specific. From what we have seen so far, I expect that there will be a link from Physics to Chemical and Classical Physics.
Yes, that looks how I would expect. Excellent! We can expand any of these nodes to continue our exploration. Let’s do that. This is today’s show-and-tell. You’ve seen what we’ve added, now let’s see what we can do!
I like the space stuff, so let’s expand that!
Very good! This category links to three papers:
Excellent! I can see papers, and I can access them on the web to read the articles. Let’s continue this exploration! Let’s expand the paper nodes!
Looking at one of them, I can see the authors that participated in writing the paper, and the year in which it was written. Let’s expand these author nodes to see if any of them wrote other papers!
Lucky day! Jekan led us to other collaborators and papers! Let’s expand those!
Expanding these nodes has opened a path to Computer Science and Robotics! Let’s see what that paper is about!
So freaking cool. See, that’s why I love this dataset. MULTI. ROBOT. CLIFF CLIMBING. LOW-GRAVITY ENVIRONMENTS.
I want to meet people who write these kinds of articles. These are interesting people!
We’re still not out of space, so let’s keep going! Let’s see where Robotics leads us.
Expanding the Robotics node led to a cluster of potential learning. But let’s do something different. Let’s expand this whole cluster and see what emerges.
It led to many more categories and articles, so many that I needed to change the visualization in order for it to make more sense.
The entire Artificial Life Research Knowledge Graph has become much more useful. It is ready, now, for next work. The build is complete, for now.
What’s Next
Now that we have the Knowledge Graph that I originally set out to build several months ago, we are ready to build our GraphRAG and AI interfaces! Here is what I have in mind.
Compare and Contrast: Cognee vs Manual - I thought it would be neat to explore both Knowledge Graphs side by side. This isn’t a better or worse comparison. Cognee uses AI to build Knowledge Graphs, and I design datasets so that Knowledge Graph construction is simple.
Fully Expand Artificial Life Database - We are currently using 60% of the dataset, and I want to use 100% of it.
Artificial Intelligence Engineering - I’m going to build a GraphRAG from scratch for Artificial Life Research.
I have kicked off my next book and will write about it, soon!
Everything is awesome! Everything is as I wanted! That is all for today!
Please Support this Work!
I have written over 50 articles for this series. Each one takes about four hours of research, and several pages of writing and editing. Here are some ways you can support the blog!
Please subscribe if you have not. This motivates me like nothing else!
LET’S DO BUSINESS. Reach out to me if you need data or AI help! Happy to help! You can read about the partners we are currently looking for here.
BIGGEST HELP to the BLOG: Please consider upgrading if you are a subscriber. Thank you to all current paying subscribers for making this research and development possible!
Please buy my book to understand how I think about Natural Language Processing and Network Science combined.
Please reach out to me if interested in training related to Data Science, Data Engineering, Network Science, Knowledge Graphs, Artificial Intelligence, or anything else I write about. Feel free to message me on Substack or on LinkedIn!
Feel free to hang out in the comments and have a good time!
We have come so far since the very first day of the very first #100daysofnetworks. I love writing for this series. Thank you for being a part of it!