Knowledge graphs can help // in reasonable reasoning
ML sucks (Yann LeCun), AI == reasoning{generation of hypotheses, setting goals, planing, etc.} // not stupid stats
Knowledge representation is a key factor of success!
GraphRAG
Quickly create knowledge graphs for accurate, explainable results. Developers can easily create knowledge graphs with Gemini models, Google Cloud VertexAI, LangChain, and Neo4j from unstructured data like PDFs, web pages, and documents — either directly or loaded from Google Cloud Storage buckets.
Ingest, process, and analyze real-time data in seconds. Developers can use Flex templates in Dataflow to create repeatable, secure data pipelines that ingest, process, and analyze data across Google BigQuery, Google Cloud Storage, and Neo4j — supplying knowledge graphs with real-time information and enabling GenAI applications to provide relevant, timely insights.
Build GenAI applications powered by knowledge graphs on Google Cloud. Customers can use Gemini for Google Workspace and Reasoning Engine from Vertex AI platform to easily deploy, monitor, and scale GenAI apps and APIs onto Google Cloud Run. Gemini models are trained on Neo4j’s training data to automatically turn any language code snippets to Neo4j’s Cypher query language. The result makes application development faster, easier, and more collaborative by integrating natural language understanding and generation capabilities within various applications and environments. Developers can also use Cypher with any Integrated Development Environment (IDE) supported by Gemini models for more efficient querying and visualization of graph data. Neo4j’s vector search, GraphRAG, and conversational memory capabilities integrate seamlessly through LangChain and Neo4j AuraDB with Google Cloud.
Translational research requires data at multiple scales of biological organization. Advancements in sequencing and multi-omics technologies have increased the availability of these data, but researchers face significant integration challenges. Knowledge graphs (KGs) are used to model complex phenomena, and methods exist to construct them automatically. However, tackling complex biomedical integration problems requires flexibility in the way knowledge is modeled. Moreover, existing KG construction methods provide robust tooling at the cost of fixed or limited choices among knowledge representation models. PheKnowLator (Phenotype Knowledge Translator) is a semantic ecosystem for automating the FAIR (Findable, Accessible, Interoperable, and Reusable) construction of ontologically grounded KGs with fully customizable knowledge representation. The ecosystem includes KG construction resources (e.g., data preparation APIs), analysis tools (e.g., SPARQL endpoint resources and abstraction algorithms), and benchmarks (e.g., prebuilt KGs). We evaluated the ecosystem by systematically comparing it to existing open-source KG construction methods and by analyzing its computational performance when used to construct 12 different large-scale KGs. With flexible knowledge representation, PheKnowLator enables fully customizable KGs without compromising performance or usability.
This paper presents PheKnowLator (Phenotype Knowledge Translator), an open-source ecosystem for automating the construction of ontologically grounded knowledge graphs (KGs) in the life sciences domain. The key components of PheKnowLator are:
1. Knowledge Graph Construction Resources: Tools to download and process heterogeneous data sources, and an algorithm to construct customizable KGs with different knowledge representations (class-based, instance-based, standard/inverse relations, semantic abstraction).
2. Knowledge Graph Benchmarks: A collection of prebuilt KGs that can be used to systematically evaluate the effects of different knowledge representations on downstream analyses and learning algorithms.
3. Knowledge Graph Tools: APIs, SPARQL endpoints, Jupyter notebooks, and data storage for using and analyzing the constructed KGs.
The paper evaluates PheKnowLator by comparing it to 15 other open-source biomedical KG construction methods, and by analyzing its performance in constructing 12 different benchmarks of a large-scale human disease mechanism KG. PheKnowLator enables fully customizable KG construction without compromising performance or usability. The ability to generate alternative KG representations as benchmarks is a key novel aspect that allows systematic evaluation of knowledge modeling decisions.
Complex logical query answering (CLQA) in knowledge graphs (KGs) goes beyond simple KG completion and aims at answering compositional queries comprised of multiple projections and logical operations. Existing CLQA methods that learn parameters bound to certain entity or relation vocabularies can only be applied to the graph they are trained on which requires substantial training time before being deployed on a new graph. Here we present ULTRAQUERY, an inductive reasoning model that can zero-shot answer logical queries on any KG. The core idea of ULTRAQUERY is to derive both projections and logical operations as vocabularyindependent functions which generalize to new entities and relations in any KG. With the projection operation initialized from a pre-trained inductive KG reasoning model, ULTRAQUERY can solve CLQA on any KG even if it is only finetuned on a single dataset. Experimenting on 23 datasets, ULTRAQUERY in the zero-shot inference mode shows competitive or better query answering performance than best available baselines and sets a new state of the art on 14 of them. The code is available: https://github.com/ DeepGraphLearning/ULTRA
Concept-based explainable AI is promising as a tool to improve the understanding of complex models at the premises of a given user, viz. as a tool for personalized explainability. An important class of concept-based explainability methods is constructed with empirically defined concepts, indirectly defined through a set of positive and negative examples, as in the TCAV approach (Kim et al., 2018). While it is appealing to the user to avoid formal definitions of concepts and their operationalization, it can be challenging to establish relevant concept datasets. Here, we address this challenge using general knowledge graphs (such as, e.g., Wikidata or WordNet) for comprehensive concept definition and present a workflow for user-driven data collection in both text and image domains. The concepts derived from knowledge graphs are defined interactively, providing an opportunity for personalization and ensuring that the concepts reflect the user’s intentions. We test the retrieved concept datasets on two concept-based explainability methods, namely concept activation vectors (CAVs) and concept activation regions (CARs) (Crabbe and van der Schaar, 2022). We show that CAVs and CARs based on these empirical concept datasets provide robust and accurate explanations. Importantly, we also find good alignment between the models’ representations of concepts and the structure of knowledge graphs, i.e., human representations. This supports our conclusion that knowledge graph-based concepts are relevant for XAI.
Automatic knowledge graph construction aims to manufacture structured human knowledge. To this end, much effort has historically been spent extracting informative fact patterns from different data sources. However, more recently, research interest has shifted to acquiring conceptualized structured knowledge beyond informative data. In addition, researchers have also been exploring new ways of handling sophisticated construction tasks in diversified scenarios. Thus, there is a demand for a systematic review of paradigms to organize knowledge structures beyond data-level mentions. To meet this demand, we comprehensively survey more than 300 methods to summarize the latest developments in knowledge graph construction. A knowledge graph is built in three steps: knowledge acquisition, knowledge refinement, and knowledge evolution. The processes of knowledge acquisition are reviewed in detail, including obtaining entities with finegrained types and their conceptual linkages to knowledge graphs; resolving coreferences; and extracting entity relationships in complex scenarios. The survey covers models for knowledge refinement, including knowledge graph completion, and knowledge fusion. Methods to handle knowledge evolution are also systematically presented, including condition knowledge acquisition, condition knowledge graph completion, and knowledge dynamic. We present the paradigms to compare the distinction among these methods along the axis of the data environment, motivation, and architecture. Additionally, we also provide briefs on accessible resources that can help readers to develop practical knowledge graph systems. The survey concludes with discussions on the challenges and possible directions for future exploration.
Temporal knowledge graphs and the generic condition knowledge graphs
In terms of knowledge graph refinement tasks, interpretable reasoning has become a prevalent trend. Researchers are seeking solutions that merge cross-lingual knowledge and derive new relationships between nodes through logic and reasoning. Researchers are also focusing on knowledge graphs for conditional knowledge, such as temporal knowledge graphs and the generic condition knowledge graphs
