And the fifth ongoing #CIKM2023 tutorial is Reasoning beyond Triples: Recent Advances in Knowledge Graph Embeddings by Bo Xiong, Mojtaba Nayyeri, Daniel Daza, and Michael Cochez 🧵6/6 Site: kg-beyond-triple.github.io

We convert popular knowledge graph embedding (KGE) models such as ComplEx into generative models of triples that 1️⃣ better scale training to very large knowledge graphs 2️⃣ make reliable predictions with logical constraints 3️⃣ support sampling in our #NeurIPS2023 oral!

🎉 In our recent paper accepted at #AAAI24! we propose NestE, a knowledge graph embedding method that encodes nested facts represented by quoted triples (h,r,t) in which the subject and object are triples themselves. Arxiv: arxiv.org/abs/2312.09219 Code: github.com/xiongbo010/Nes…

Interested in constraints in Neural Networks? Come to poster 489 and I will explain how bottlenecked layers are constraining what you can and cannot predict! #AAAAI24 #AAAI2024

Glad to visit the April Lab at Edinburgh. I learned a lot from many people here. Thank you for the hosting😊

Exciting job opportunity! 🧑‍🔬 We at the School of Informatics, University of Edinburgh (School of Informatics, The University of Edinburgh, EdinburghNLP) are looking for a Research Associate (~postdoc) in NLP and ML for a 3-year project fully funded by Huawei via the Huawei-Edinburgh Joint Lab initiative! The project

Sometimes it’s truly hard to find as passionate and enthusiastic researchers as Pasquale 😃 you should really consider to apply to this job position 🚀 Plus, Edinburgh and @InfAtEd are just amazing 🤩

Congrats to Dr. Andreas Grivas who just defended his #PhD thesis on unargmaxability and constraints in deep learning, examined by Vlad Niculae and Iain Murray 🎉 A pity you could not (yet) see Andreas' beautifully designed thesis! In the meantime, some pics from the pre-viva 👇

3 of 3 submissions of my research will be presented by my co-authors and/or me at EMNLP 2024, Miami, USA. 😀 The topics include #KG and #reasoning with #Uncertainty, #Temporal, #LargeLanguageModels, and #RAG. Congratuations to all the co-authors.

can you guess what are the numbers in this table about? and what is the message? I will incrementally reveal the header and the row ids in the next days, and ultimately its caption. if you figure it out first, you will win a coffee with Pasquale Minervini!

🚨Is complex query answering really complex?🚨 unfortunately not! the current benchmarks boil down to link prediction 98% of the time... how to fix this??? 👇👇👇 📜arxiv.org/abs/2410.12537 with Cosimo Gregucci@ICML Bo Xiong Lorenzo Loconte Pasquale Minervini @ststaab

NeurIPS acknowledges that the cultural generalization made by the keynote speaker today reinforces implicit biases by making generalisations about Chinese scholars. This is not what NeurIPS stands for. NeurIPS is dedicated to being a safe space for all of us. We want to address

How do language models conceptualize? 🤔 In our #ICLR2025 paper, we show that LMs implicitly perform lattice structure learning, and link it to Formal Concept Analysis (FCA)—a classic approach to concept lattice construction✨

Goodbye ChatGPT It’s only been 5 days since Deepseek R1 dropped, and the World is already blown away by its potential. 13 examples that will blow your mind (Don't miss the 5th one):

Chaitanya K. Joshi Ben Finkelshtein Fabrizio Frasca Michael Bronstein Bryan Perozzi Michael Galkin Christopher Morris hi, we found problematic benchmarks in complex query answering as well! arxiv.org/abs/2410.12537 antonio vergari ⚔️ not at #ICML2025 Mathias Niepert Cosimo Gregucci@ICML Christopher Morris Michael Galkin

Does text help KG Foundation Models generalize better? 🤔 Yes (and no)! ☯️ Bootstrapped by LLMs improving KG relation labels, we show that textual similarity between relations can act as an invariance - helping generalization across datasets! 🧵👇

SEMMA (transliteration of செம்ம - meaning awesome), my first PhD work, is accepted to #EMNLP2025 Main! I also found out today that SEMMA has the (tied) highest average reviewer score in this ARR cycle 💪 📜: arxiv.org/abs/2505.20422

🎓 #SWSA Distinguished Dissertation Award 2025 goes to Bo Xiong ! Recognized for his brilliant thesis: “Geometric Relational Embeddings” 🧠 👏 Congrats Bo - see you at #ISWC2025 in #Japan! #DistinguishedDissertationAward #SemanticWeb #KnowledgeGraphs #AI #ResearchExcellence