Susan Nazirizadeh

🚀 Exciting News! 🚀 We are thrilled to announce that Kumo AI's position paper "Relational Deep Learning: Graph Representation Learning on Relational Databases," has been accepted at #ICML 2024! 🎉 Join us in Vienna from July 21-27, where our very own Matthias Fey will be presenting this exciting new research area. 🔗 https://icml.cc/ In collaboration with Stanford University, we introduce Relational Deep Learning (#RDL), a new research area for applying deep learning on relational databases by viewing them as temporal, heterogeneous graphs. This method eliminates the need for manual feature engineering, leading to more accurate models built faster. 🚀 We’ve also developed #RelBench, a benchmark suite to facilitate research in this new area, using diverse datasets from Stack Exchange discussions to Amazon book reviews. 📚 Stay tuned for more updates on our presentation format, and check out our paper here: https://lnkd.in/dk24vbSg #ICML2024 #MachineLearning #AI #GraphNeuralNetworks #RelationalDeepLearning #DataScience #KumoAI #StanfordCollaboration

38

📅 Mark your calendars for September 18th in #Vienna! At the #DataScience MeetUp, Andreas from Neo4j and Sebastian will talk about the relevance of #KnowledgeGraphs for Gen #AI, and explain why proper #GraphVisualization is critical for understanding your #data. We look forward to seeing you there! https://lnkd.in/e-EKZ9fZ

6

🚀 The Future is Agentic! 🤖🌐 I recently started reading Multi-Agent Reinforcement Learning: Foundations and Applications, authored by Stefano V. Albrecht, Filippos Christianos, and Lukas Schäfer. This book is an excellent introduction to the exciting and increasingly relevant field of multi-agent systems. The best part? You can download the book for free from https://marl-book.com/ The book provides a solid foundation in this transformative area of AI, covering both theoretical principles and practical applications. As we look ahead to 2025, I truly believe it will be the year of agentic AI, where autonomous, collaborative agents revolutionize industries, research, and beyond. If you’re interested in understanding the future of AI, I highly recommend giving this book a read! Let’s gear up for the era of intelligent agents. #AI #MultiAgentSystems #ReinforcementLearning #AgenticAI #MARL #MITPress

16

AnchorGT: A Novel Attention Architecture for Graph Transformers as a Flexible Building Block to Improve the Scalability of a Wide Range of Graph Transformer Models Quick read: https://lnkd.in/gFiQyv8a Paper: https://lnkd.in/gsJqpi5F #machinelearning #ai

18

🔵 Week 3 : AI Paper by Hand ✍ --Paper 3 ➡️ RuAG: Learned-Rule-Augmented Generation For Large Language Models-- Combine RAG and Monte Carlo Tree Search (MCTS) and we get RuAG, a very interesting approach to instill data into an LLM. Here is a pdf of my annotated version of the paper, hope this helps you grab the central essence of this cool idea! 💡 🟢 A quick summary of what I understood: ----------------------------------------------------- RuAG (learned-rule-augmented generation) is a novel framework that distills large volume of information into logic rules using MCTS which are translated into natural language for seamless augmentation of an LLM's knowledge. --------- Central Idea ---------- The way RuAG works can be summarized as: 1. It starts with features (body predicate) and labels (target predicate). Target predicate is defined to be task-relevant while the body predicates are initialized as all the data attributions in the dataset. Based on task and description, LLM generates new target predicates and eliminates most irrelevant body predicates. 2. Next, RuAG uses an automated formulation for MCTS to generate set of first-order logic rules. It involves building a search tree and simulating outcomes to estimate the value of actions. To do so, it starts by build a search tree, selects the most promising child node, calculates the reward for the new node and propagates it up the tree. 3. Finally, the search rules are cleaned and translated into natural language which is then used for improved LLM generation. --------- Results ---------- - For Relation Extraction, RuAG achieves an F1-score of 60.42% - For Anomaly Detection, RuAG achieves an F1-score of 92.59%. In both cases, RuAG outperforms all baselines 💡 Paper : https://lnkd.in/g7BGrrv3 [Repost ♻️ ] Please help me share this resource to your network! #aibyhand #deeplearning #neuralnetworks #ai

84

1 Kommentar