sirolf

📣 SIGMOD/PODS Warm-up Session Vector DBs are booming, but key questions are open: what works, what’s missing, and where are the bottlenecks? @SIGMODConf 🗓 Sunday, May 31 🕠 5:30–7:00 pm Speakers R. Krishnaswamy, A. Meliou, Y. Papakonstantinou, Y. Tao.

📢 New position paper: “𝗡𝗲𝘂𝗿𝗮𝗹 𝗔𝗹𝗴𝗼𝗿𝗶𝘁𝗵𝗺𝗶𝗰 𝗥𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴 𝗥𝗲𝗾𝘂𝗶𝗿𝗲𝘀 𝗮 𝗖𝗹𝗲𝗮𝗿 𝗦𝗰𝗼𝗽𝗲, 𝗧𝗵𝗲𝗼𝗿𝗲𝘁𝗶𝗰𝗮𝗹 𝗙𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻𝘀, 𝗮𝗻𝗱 𝗘𝗺𝗽𝗶𝗿𝗶𝗰𝗮𝗹 𝗥𝗶𝗴𝗼𝗿” When and where should we use Neural Algorithmic Reasoning (NAR)? NAR is an exciting emerging area at the intersection of 𝙘𝙡𝙖𝙨𝙨𝙞𝙘𝙖𝙡 𝙖𝙡𝙜𝙤𝙧𝙞𝙩𝙝𝙢 𝙙𝙚𝙨𝙞𝙜𝙣 and 𝙣𝙚𝙪𝙧𝙖𝙡 𝙘𝙤𝙢𝙥𝙪𝙩𝙖𝙩𝙞𝙤𝙣 — but its foundations are still underdeveloped. In this paper, we argue that the field needs: ✨ a sharper 𝙙𝙚𝙛𝙞𝙣𝙞𝙩𝙞𝙤𝙣 of what NAR is (and is not), including clearer distinctions from neighboring paradigms, 📐 stronger 𝙩𝙝𝙚𝙤𝙧𝙮 for expressivity and generalization, 🧪 more rigorous 𝙗𝙚𝙣𝙘𝙝𝙢𝙖𝙧𝙠𝙨 and connection to high-impact 𝙖𝙥𝙥𝙡𝙞𝙘𝙖𝙩𝙞𝙤𝙣𝙨.

@pmddomingos 4/4 A more substantive related work section is needed to show how this variation of Tensor Logic fits in the wider landscape of similar languages. You may have found the path to AGI, but not to related work yet.

I've found the path to AGI: arxiv.org/abs/2510.12269

@pmddomingos 3/4 And there is more to explore: Tensor Languages for Graph Learning 🔗 arxiv.org/abs/2204.04661 Tensor Relational Algebra (TRA) 🔗 doi.org/10.14778/34573… Neurosymbolic Approaches (survey) 🔗 arxiv.org/abs/2108.11451 And many many more...

@pmddomingos 2/4 There’s a deep lineage of ideas unifying logic, algebra, and learning: MATLANG 🔗 dl.acm.org/doi/abs/10.114… 🔗 arxiv.org/abs/2010.13717 LARA 🔗 arxiv.org/pdf/1604.03607 🔗 arxiv.org/abs/1909.11693 FAQ 🔗 arxiv.org/abs/1504.04044 Datalogo 🔗 arxiv.org/abs/2105.14435

@pmddomingos 1/4 Bold claim: “Tensor Logic: The Language of AI.” Sure: it grabs attention. But attention isn’t all you need. In research, you still have to situate your work in prior art.

🚀 Join us at the SIGMOD/PODS 2025 Warmup Session: Query Optimization Unleashed — Bridging Theory, AI, and Systems for the Future of Databases. 📅 Sunday, June 22, 2025 🕔 17:00-18:30 (Starts 17:15) 2025.sigmod.org/warmup.shtml

Congrats to all the UnRavL team for a Best Paper Honorable Mention at the 2024 Learning on Graphs Conference! UnRavL expands the types of queries that we can answer over incomplete knowledge graphs🧙 Read the paper here: openreview.net/pdf?id=183XrFq…

🚀 Don't miss Tamara Cucumides’ talk at LOG 2024 at 19h10 CET about "UnRavL: A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs". openreview.net/forum?id=183Xr… @LogConference

@mkoubarakis @florisgeerts @EETN_gr @EurAI_ECCAI @eu_tailor @ArchimedesUnit @AITeamUoA @TechVida @magdalenaosimk It was a pleasure participating in the summer school. Thanks for the invitation and the great organization!

⁦@florisgeerts⁩ giving his tutorial on the power of graph learning today at ESSAI 2024. ⁦@EETN_gr⁩ ⁦@EurAI_ECCAI⁩ ⁦@eu_tailor⁩ ⁦@ArchimedesUnit⁩ ⁦@AITeamUoA⁩ ⁦@TechVida⁩ ⁦@magdalenaosimk⁩

@mkoubarakis @EurAI_ECCAI @eu_tailor @ArchimedesUnit @EETN_gr @AITeamUoA @iit_demokritos Disclaimer: I’ll be giving a tutorial on the power of graph learning there 😀 Looking forward to the hottest summer school in AI 👍

Week 1 of ESSAI 2024 has just ended successfully. We attended 1 keynote, 13 courses and 8 tutorials given by top AI researchers. We are now looking forward to a relaxing weekend and an exciting week 2. @EurAI_ECCAI @eu_tailor @ArchimedesUnit @EETN_gr @AITeamUoA @iit_demokritos

the speakers kindly agreed to make the slides of their presentation available. You can find them here: 2024.sigmod.org/pods_special.s…

Exciting news for SIGMOD/PODS @SigmodConf attendees! Join us in Santiago, Chile for "Unlocking the Secrets: Bridging Theory and Practice" on June 9, 2024, 16:00-18:00. 2024.sigmod.org/pods_special.s… Don't miss this chance to bridge theory and practice!  #TheoryAndPractice

With almost 700 attendees from all around the globe, the presence of the @ACM_President president Yannis Ioannidis, six keynote speakers, 10 #PODS research sessions, and 36 #SIGMOD research sessions, demos, tutorials, and workshops, we are saying goodbye ... 👇

@mmbronstein I hope that you are not referring to the fries? if so, then I have to object as a Belgian 🇧🇪 😉

Only in Boston they know how to do them properly

Machine learning and database theory combine well: A Neuro-Symbolic Framework for Answering Graph Pattern Queries in Knowledge Graphs Read more: arxiv.org/abs/2310.04598 #nesy #graphlearning #knowledgegraph

Have you ever wondered when more expressive GNNs and graph kernels matter? Come to our poster at the ICLR 2024 Workshop on Bridging the Gap Between Practice and Theory in Deep Learning (10:00) to learn more: arxiv.org/pdf/2402.07568. Also accepted at ICML 2024.

@chrsmrrs 👏

🙂

Fantastic workshop in the mountains of Chile with great people! Thanks to Pablo Barceló for making this happen. Chile is a focal point of graph ML research! Hope to be back soon, perhaps with our horses? @mmbronstein @HaggaiMaron @michael_galkin 🐎🐎🐎