Emile will present our work on Knowledge Graph Embeddings at Eurips' Salon des RefusΓ©s on Friday!
We show how linearity prevent KGEs from scaling to larger graphs + propose a simple solution using a Mixture of Softmaxes (see LLM literature) to break the limitations at a low parameter cost. π¨
Almost off to @euripsconf.bsky.social in Copenhagen π©π° πͺπΊ! I'll present 3 posters:
π§ Neurosymbolic Diffusion Models: Thursday's poster session.
Going to NeurIPS? @edoardo-ponti.bsky.social and @nolovedeeplearning.bsky.social will present the paper in San Diego Thu 13:00
arxiv.org/abs/2505.13138
We're glad to announce the NeSy 2025 Test of Time award for "Probabilistic Inference Modulo Theories"!
πRodrigo de Salvo Braz was here to accept the award.
This is groundwork for recent NeSy approaches like DeepSeaProbLog and the probabilistic algebraic layer.
Explanation between Vincristine and Hematologic Cancer from Hetionet dataset
π Check out our IJCAI'25 paper on Explainable link prediction in KGs πβ¨
We use a path-based RL model to generate explanations for predictions. We do so by rewarding path properties that make good explanations γ°οΈ
Great work led by Susana Nunes & @catiapesquita.bsky.social π
π arxiv.org/pdf/2509.02276
βοΈ I will be in Edinburgh this summer (Jun-Aug) at @edinburgh-uni.bsky.social, visiting the group of Antonio Vergari (@nolovedeeplearning.bsky.social) to work on #neurosymbolic #AI and #probabilistic #ML
If you are around and want to chat about these topics, let's meet for coffee!
We propose Neurosymbolic Diffusion Models! We find diffusion is especially compelling for neurosymbolic approaches, combining powerful multimodal understanding with symbolic reasoning π
Read more π
ποΈ Deadline extended: π₯2nd June 2025!π₯
We are looking forward to your works on:
π #circuits and #tensor #networks πΈοΈ
β³ normalizing #flows π¨
βοΈ scaling #NeSy #AI π¦
π
fast and #reliable inference π
...& more!
please share π
π Are you working on informed-ML, Neuro-symbolic AI or ML verification?
π Our special track on the Journal of Artificial Intelligence Research (JAIR) about "Integration of Logical Constraints in Deep Learning" is the right venue for you! π
CfP: www.jair.org/index.php/ja...
Deadline: May 31, 2025
Great idea! Interested to join too :)
