Diving into Databases: Graph & Vector for Retrieval Augmented Generation – Point of View | LinkedIn
GraphNews
Neural Graphical Models
Neural Graphical Models (NGMs) provide a solution to the challenges posed by traditional graphical models, offering greater flexibility, broader applicability, and improved performance in various domains. Learn more:
Superpowers of Knowledge Graphs, part 1: Data Integration | LinkedIn
JSON Crack - Visualize Data to Graphs
Innovative and open-source visualization application that transforms various data formats, such as JSON, YAML, XML, CSV and more, into interactive graphs.
Embedded databases (2): Deep diving into KùzuDB, a lightweight, fast & scalable graph database
A benchmark study comparing the performance of KùzuDB vs. Neo4j on an artificial social network dataset
Tired of updating your #scraping templates or feeding full webpages to LLMs? Use #Cypher instead!
Tired of updating your #scraping templates or feeding full webpages to LLMs? Use #Cypher instead! I was in the same boat just 3 months ago when I was working… | 16 comments on LinkedIn
Can LLMs replace GNNs as the foundational model in graph machine learning?
Can LLMs replace GNNs as the foundational model in graph machine learning? Over the past decade, the landscape of machine learning with graphs has seen a… | 19 comments on LinkedIn
dotmotif: A performant, powerful query framework to search for network motifs
500 million+ members | Manage your professional identity. Build and engage with your professional network. Access knowledge, insights and opportunities.
PyGraft, a configurable #Python tool to generate both synthetic #schemas and #knowledgeGraphs easily, supporting several RDFS and OWL constructs
Happy to announce PyGraft, a configurable #Python tool to generate both synthetic #schemas and #knowledgeGraphs easily, supporting several RDFS and OWL constructs.
Paper: https://t.co/p1Ei3PIhVz
Code: https://t.co/ID6gU3elqK (also available on PyPI)
@nicolas_hubr @mdaquin
LLMs-represent-Knowledge Graphs | LinkedIn
On August 14, 2023, the paper Natural Language is All a Graph Needs by Ruosong Ye, Caiqi Zhang, Runhui Wang, Shuyuan Xu and Yongfeng Zhang hit the arXiv streets and made quite a bang! The paper outlines a model called InstructGLM that adds further evidence that the future of graph representation lea
A eulogy for RedisGraph
Less than five years after its initial release, Redis has announced that RedisGraph will be discontinued. Why?
Head-to-Tail: How Knowledgeable are Large Language Models (LLM)? A.K.A. Will LLMs Replace Knowledge Graphs?
Since the recent prosperity of Large Language Models (LLMs), there have been
interleaved discussions regarding how to reduce hallucinations from LLM
responses, how to increase the factuality of LLMs, and whether Knowledge Graphs
(KGs), which store the world knowledge in a symbolic form, will be replaced
with LLMs. In this paper, we try to answer these questions from a new angle:
How knowledgeable are LLMs?
To answer this question, we constructed Head-to-Tail, a benchmark that
consists of 18K question-answer (QA) pairs regarding head, torso, and tail
facts in terms of popularity. We designed an automated evaluation method and a
set of metrics that closely approximate the knowledge an LLM confidently
internalizes. Through a comprehensive evaluation of 14 publicly available LLMs,
we show that existing LLMs are still far from being perfect in terms of their
grasp of factual knowledge, especially for facts of torso-to-tail entities.
Ontology Enrichment from Texts: A Biomedical Dataset for Concept Discovery and Placement
Mentions of new concepts appear regularly in texts and require automated
approaches to harvest and place them into Knowledge Bases (KB), e.g.,
ontologies and taxonomies. Existing datasets suffer from three issues, (i)
mostly assuming that a new concept is pre-discovered and cannot support
out-of-KB mention discovery; (ii) only using the concept label as the input
along with the KB and thus lacking the contexts of a concept label; and (iii)
mostly focusing on concept placement w.r.t a taxonomy of atomic concepts,
instead of complex concepts, i.e., with logical operators. To address these
issues, we propose a new benchmark, adapting MedMentions dataset (PubMed
abstracts) with SNOMED CT versions in 2014 and 2017 under the Diseases
sub-category and the broader categories of Clinical finding, Procedure, and
Pharmaceutical / biologic product. We provide usage on the evaluation with the
dataset for out-of-KB mention discovery and concept placement, adapting recent
Large Language Model based methods.
The Memory Game: Investigating the Accuracy of AI Models in Storing and Recalling Facts. Comparing LLMs and Knowledge Graph on Factual Knowledge
The Memory Game: Investigating the Accuracy of AI Models in Storing and Recalling Facts … 🧠 ... Comparing LLMs and Knowledge Graph on Factual Knowledge I’m… | 18 comments on LinkedIn
Having a tough chat with an LLM about knowledge graph paths. | LinkedIn
No, this is not the chat a father has with Lucius L. Malfoy when he asks to walk your daughter along a path to the prom.
Integrating TigerGraph and Large Language Models for Generative AI - TigerGraph
See how to integrate a language language model with TigerGraph to empower question answering with your connected data.
LLMs4OL: Large Language Models for Ontology Learning
We propose the LLMs4OL approach, which utilizes Large Language Models (LLMs)
for Ontology Learning (OL). LLMs have shown significant advancements in natural
language processing, demonstrating their ability to capture complex language
patterns in different knowledge domains. Our LLMs4OL paradigm investigates the
following hypothesis: \textit{Can LLMs effectively apply their language pattern
capturing capability to OL, which involves automatically extracting and
structuring knowledge from natural language text?} To test this hypothesis, we
conduct a comprehensive evaluation using the zero-shot prompting method. We
evaluate nine different LLM model families for three main OL tasks: term
typing, taxonomy discovery, and extraction of non-taxonomic relations.
Additionally, the evaluations encompass diverse genres of ontological
knowledge, including lexicosemantic knowledge in WordNet, geographical
knowledge in GeoNames, and medical knowledge in UMLS.
There is a lot of research on establishing mappings between different ontologies, but hardly any work on how to leverage such mappings in a query federation engine
“There is a lot of research on establishing mappings between different ontologies, but hardly any work on how to leverage such mappings in a query federation engine.
With @Sijin_Cheng and @ferradest, we have embarked on changing that. Paper at @CoopIS2023
https://t.co/vF1emf9R6Z”
Gartner's Hype Cycle 2023
Ah, Gartner's Hype Cycle. It's always fun to see what's on the roller coaster. I think the position of Knowledge Graphs is about right - the KM community is… | 10 comments on LinkedIn
Why Establishing Data Context is the Key to Creating Competitive Advantage - SD Times
The age of Big Data inevitably brought computationally intensive problems to the enterprise. Central to today’s efficient business operations are the activities of data capturing and storage, search, sharing, and data analytics.
Graph Database Market Share, Analysis | Global Report, 2030
Graph Database Market is anticipated to reach USD XX.X MN by 2030, this market report provides the growth, trends, key players & forecast of the market based on in-depth research by industry experts. The global market size, share along with drivers and restraints are covered in the graph database market report
Revolutionising Ontology Engineering with Deep Learning: An Introduction to DeepOnto
In the realm of Artificial Intelligence (AI), ontology engineering plays a pivotal role in structuring knowledge and facilitating semantic…
Human-centered data networking with interpersonal knowledge graphs - DataScienceCentral.com
In the case of interpersonal knowledge graphs, everyone in the community can contribute to the disambiguation and enrichment of the community’s online presence, and at the same time help with findability, accessibility, interoperability and reuse (the FAIR principles). And that applies not only to someone else finding your path to research discovery, but you being able to retrace your own steps whenever you need to.
Finding Money Launderers Using Heterogeneous Graph Neural Networks
Current anti-money laundering (AML) systems, predominantly rule-based,
exhibit notable shortcomings in efficiently and precisely detecting instances
of money laundering. As a result, there has been a recent surge toward
exploring alternative approaches, particularly those utilizing machine
learning. Since criminals often collaborate in their money laundering
endeavors, accounting for diverse types of customer relations and links becomes
crucial. In line with this, the present paper introduces a graph neural network
(GNN) approach to identify money laundering activities within a large
heterogeneous network constructed from real-world bank transactions and
business role data belonging to DNB, Norway's largest bank. Specifically, we
extend the homogeneous GNN method known as the Message Passing Neural Network
(MPNN) to operate effectively on a heterogeneous graph. As part of this
procedure, we propose a novel method for aggregating messages across different
edges of the graph. Our findings highlight the importance of using an
appropriate GNN architecture when combining information in heterogeneous
graphs. The performance results of our model demonstrate great potential in
enhancing the quality of electronic surveillance systems employed by banks to
detect instances of money laundering. To the best of our knowledge, this is the
first published work applying GNN on a large real-world heterogeneous network
for anti-money laundering purposes.
Three things have been perennially true ever since we started Neo4j and kicked off the graph database category
What Mark said. Three things have been perennially true ever since we started Neo4j and kicked off the graph database category: 1) Every year or so there's a…
RedisGraph End-of-Life Announcement
Redis Inc. is phasing out RedisGraph. This blog post explains the motivation behind this decision and the implications for existing customers and community members.
Gartner: Using knowledge graphs to solve data integration issues
Knowledge graphs – a graphic representation of entities in a linked network − have the potential to solve many data integration challenges that pose a significant barrier to the use of AI.
Graph databases gain traction as AI uses expand data management stack
While still a bit of an outlier, graph-oriented databases continue to find a role in the modern data stack -- thanks largely to AI.
Hierarchical Navigable Small World (HNSW) is one of the most efficient ways to build indexes for vector databases. The idea is to build a similarity graph and traverse that graph to find the nodes that are the closest to a query vector
We have seen recently a surge in vector databases in this era of generative AI. The idea behind vector databases is to index the data with vectors that relate… | 30 comments on LinkedIn
SPARQL queries, GPTs and Large Language Models – where are we currently?