RelationalAI at the Knowledge Graph Conference
We are delighted to be attending and sponsoring the Knowledge Graph Conference again this year. Last year was an incredible event – see the highlights here – and this year is lining up to be just as exciting!
Our VP of Strategic Development, Aisha Quaintance (opens in a new tab), is chairing the first ever Semantic Layer track (opens in a new tab). We are also presenting a masterclass and hands-on workshop, taking part in a fireside chat with Snowflake discussing financial services, and co-hosting a happy hour with Women in Data (opens in a new tab).
Here’s a taster of what you can expect:
What do language machines mean for the semantic layer? These are early days for data-driven computer science, so the answer to this question is still unfolding.
This workshop, focused on knowledge graph practitioners, will introduce MLMs and their mechanisms, such as prompt construction, prompt tuning, in-context learning, tool-augmentation, and fine-tuning. We will demonstrate how MLMs can be used in a variety of professional domains.
Crucially, while MLMs offer incredible advantages in processing language, they are not yet able to learn the deep inferencing capabilities of the full mathematical and logic-driven stack. For the foreseeable future, practitioners will need to combine precisely-developed ontologies (logic-driven) with MLMs (data-driven).
In this hands-on masterclass, we show how to do this with examples from RelationalAI’s Rel language. We also preview several other interesting tasks that use MLMs, such as semantic search, and the automatic labeling of features with concepts from an ontology.
Large enterprises maintain a multitude of data assets pertaining to their businesses. It’s arduous for engineers and data scientists to not only find the information they need, but also to ensure it’s accurate and up to date. This can lead to data duplication, misuse of assets, and conflicting results.
We will address this problem by leveraging an enterprise ontology, which we assume users in a domain will intuitively understand. Our approach is novel in that we allow users to navigate over their data assets semantically, using the concepts and relationships of this ontology.
We present a case study involving a client using an ontology of hundreds of concepts to efficiently search for and manage a set of data assets that number in the tens of thousands. This solution uses the RelationalAI Knowledge Graph System to power the search process, including a live demonstration.
In financial services, a common language and data model are essential to not only meet regulatory needs but also to stay competitive by creating more products more quickly and monetizing on massive amounts of accumulated, heterogeneous data.
We see an increasing number of semantic layer and modeling tools such as Legend, Morphir, and others, coming into the open-source realm and gaining adoption amongst other institutions to try to address this. Historically, however, there are challenges with integrating and executing these semantic layers within an existing data infrastructure ecosystem at scale. This often results in obstacles to adoption and difficulties in transitioning efforts to production.
In this talk, we will provide a specific example of how we use relational semantic layers to solve this challenge through a financial services use case. You’ll learn about semantic layers in financial services and how a relational semantic layer fits in a modern data stack.
You’ll also get a technical review of an applied financial services use case involving PURE/Legend, and find out how the business benefits from having a generic model of representation and execution that spans all data sources and types.
The talk will end with forward-looking thoughts on the industry and a chance for you to ask questions of some of the experts implementing these solutions.
The Knowledge Graph Conference will be held at Cornell Tech Campus in New York City, and also online, May 8-12 2023. Sign up and register here (opens in a new tab), and we hope to see you there!
Hybrid and Content-based Recommender Systems in Rel - Part 3
In this series of blog posts, we show how to implement neighborhood-based, graph-based, content-based, and hybrid recommender systems using RelationalAI’s declarative modeling language, Rel.
The implementations of these algorithms demonstrate the efficiency of our Relational Knowledge Graph System (RKGS) for aggregating over paths on large and sparse graphs, computing similarities using our graph analytics library, and building compact, easy to read models, without needing to transfer data outside of our system.
Graph-based Recommender Systems in Rel - Part 2
In our previous blog post, we explained how to model traditional neighborhood-based recommender systems in Rel. In what follows, we focus on modeling graph-based recommender systems.