Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
Graph Learning Tutorial @ ICML 2024
Participated (online) in the panel discussion with Bryan Perozzi, Michael Bronstein, and Christopher Morris on graph foundation models held during the Graph Learning Tutorial at ICML 2024, thanks Ameya and Adrian for inviting!
Foundation Models in Graph & Geometric Deep Learning
In our new Medium blogpost with Michael Bronstein, Jianan Zhao, Haitao Mao, and Zhaocheng Zhu we discuss foundation models in Graph & Geometric DL: from the core theoretical and data challenges to the most recent models that you can try already today!
Visiting WWW and National University of Singapore
A productive week in Singapore! First, gave a keynote at the workshop on Graph Foundation Models at The WebConf 2024 and participated in the panel discussion. Then, visited the group of professor Xavier Bresson at the National University of Singapore with the talk on graph foundation models - from KG reasoning to AI 4 Science. Thank you Professor Bresson for extending the invitation! Slides
Paper accepted at ICML 2024
Our position paper Graph Foundation Models are Already Here was accepted at ICML 2024 as a spotlight paper!
FANeSy Workshop in Santiago, Chile
It was a delightful experience to participate in the week-long workshop on GNNs and neuro-symbolic AI (FANeSy) organized by Pablo Barcelo, CENIA, and Unversidad San Sebastian. Thanks Pablo for the invitation!
Paper accepted at ICLR 2024
Our paper on ULTRA, the first foundation model for KG reasoning, was accepted at ICLR 2024. See you in Vienna!
Graph & Geometric ML in 2024: Where We Are and What’s Next
Together with Michael Bronstein, we wrote a huge blog post on the state of affairs in Graph and Geometric DL in 2023 with some predictions for 2024. Part I focuses on theory and GNN architectures (including graph transformers), Part II talks about cool and exciting applications in structured biology, materials science, ML potentials, algorithmic reasoning, and temporal graph learning. We interviewed many prominent researchers to provide several points of view on each subject - so this work wouldn’t be possible without the massive community engagement!
Dagstuhl and UCSD talks
A few talks on graph foundation models given recently: at UC San Diego and at the Dagstuhl seminar on Scalable Graph Mining and Learning.
Release of ULTRA
Happy to release ULTRA - the first foundation model for knowledge graph reasoning. A single pre-trained ULTRA model is able to do zero-shot link prediction on any unseen KG and do so better than many supervisedly trained baselines on 50+ datasets! More details in the Medium blog post. We release the paper, several checkpoints (177k params), code, and data on GitHub and HuggingFace Spaces.
2 papers accepted at NeurIPS 2023
Our team got two papers accepted at the upcoming NeurIPS’23 in New Orleans!
- A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs. Zhaocheng Zhu, Xinyu Yuan, Mikhail Galkin, Sophie Xhonneux, Ming Zhang, Maxime Gazeau, Jian Tang. preprint
- Improving Systematic Generalization using Iterated Learning and Simplicial Embeddings. Yi Ren, Samuel Lavoie, Mikhail Galkin, Danica J. Sutherland, Aaron Courville.
Graph Machine Learning @ ICML 2023
I was lucky to attend ICML’23 in Honolulu in person and see many friends and Graph ML folks. Check my report on latest and greatest graph learning research in the new blog post together with some stunning photos from Hawaii!
Neural Graph Databases
A new paper Neural graph reasoning: Complex logical query answering meets graph databases and an accompanying Medium post where we introduce the concept of Neural Graph Databases (NGDB) and a whole new categorization of complex logical query answering tasks. NGDBs answer complex queries right in the latent space and are able to reason over missing links (“what’s missing?”) in addition to standard DB-like retrieval (“what’s there”?).
Temporal Graph Learning in 2023
A new Medium post by Andy Huang, Emanuele Rossi, Michael Galkin, and Kellin Pelrine on the recent progress in temporal Graph ML! Featuring theoretical advancements in understanding expressive power of temporal GNNs, discussing evaluation protocols and trustworthiness concerns, looking at temporal KGs, disease modeling, and anomaly detection, as well as pointing to the software libraries and new datasets!
Graph ML in 2023: The State of Affairs
In a new Medium post, we provide an overview of what’s happened in Graph ML in 2022 and its subfields (and hypothesize for potential breakthroughs in 2023), including Generative Models, Physics, PDEs, Graph Transformerrs, Theory, KGs, Algorithmic Reasoning, Hardware, and more!
Denoising Diffusion Generative Models in Graph ML
In the new Medium post, we delve into Denoising Diffusion generative models and their applications in molecular tasks such as conformer generation, protein-ligand docking, molecular linking, and more!
One Paper Accepted @ LoG 2022
We got one paper accepted at the inaugural Learning on Graphs (LoG) 2022 conference!
- Pablo Barcelo, Mikhail Galkin, Christopher Morris, Miguel Romero Orth. Weisfeiler and Leman Go Relational: we introduce a Relational WL test to quantify expressiveness of relational GNNs (R-GCN and CompGCN).
One Paper Accepted @ AACL-IJCNLP 2022
We got one paper accepted at AACL-IJCNLP 2022!
- Phillip Schneider, Tim Schopf, Juraj Vladika, Mikhail Galkin, Elena Simperl, Florian Matthes. A Decade of Knowledge Graphs in Natural Language Processing: A Survey: your #1 survey on KGs in NLP in the past 10 years.
Three Papers Accepted @ NeurIPS 2022
Glad to announce we got three papers accepted at NeurIPS 2022! Two to the main Research track:
- Ladislav Rampášek, Mikhail Galkin, Vijay Prakash Dwivedi, Anh Tuan Luu, Guy Wolf, Dominique Beaini. Recipe for a General, Powerful, Scalable Graph Transformer: GraphGPS, the best graph transformer of 2022!
- Mikhail Galkin, Zhaocheng Zhu, Hongyu Ren, Jian Tang. Inductive Logical Query Answering in Knowledge Graphs: for the first time, we propose two approaches for inductive complex query answering over unseen nodes.
Graph Machine Learning @ ICML 2022
A fresh Medium post on Graph ML papers at ICML 2022! A comprehensive overview of 35+ papers in 10 categories:
Paper Accepted @ ICML 2022
Our paper Neural-Symbolic Models for Logical Queries on Knowledge Graphs (Zhaocheng Zhu, Mikhail Galkin, Zuobai Zhang, Jian Tang) has been accepted to ICML 2022! In the paper, we introduce GNN-QE, a new approach for complex logical query answering based on NBFNet.
GraphGPS: Navigating Graph Transformers
In the new Medium post, we introduce our new work, GraphGPS, a recipe for building general, powerful, and scalable graph transformers.
Two Papers Accepted @ Graph Learning Benchmarks 2022
We got 2 accepted papers to the Workshop on Graph Learning Benchmarks @ The WebConf 2022! Check the preprints
- An Open Challenge for Inductive Link Prediction on Knowledge Graphs: introducing the Inductive Link Prediction Challenge (ILPC 2022)
- A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphs: more truthful ranking metrics for link prediction.
Two Papers Accepted @ ICLR 2022
Glad to share that we got 2 accepted papers to ICLR 2022! NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs and Query Embedding on Hyper-relational Knowledge Graphs. Updated pre-prints are coming soon!
Graph ML in 2022: Where Are We Now?
A new winter holiday longread - what happened in the Graph ML field in 2021? What to expect in 2022? We reflect upon a dozen of research trends - brought by yours truly, Anton Tsitsulin, Anvar Kurmukov, and Sergey Ivanov (with a surprise cameo appearance in the end).
Knowledge Graphs @ EMNLP 2021
Premium Punta Cana content: a blogpost on Knowledge Graph papers from EMNLP2021: sunny LMs, blue lagoons of ConvAI, sunsets with Entity Linking, white sands of Question Answering!
Invited Talk @ AI Journey 2021
Had a pleasure presenting a new research talk Beyond Shallow Embeddings of Knowledge Graphs at AI Journey 2021 - the biggest Russian-based venue for AI research. Slides, recording (RU).
Best Research Paper Award @ ISWC 2021
Happy to announce that we received the Best Paper Award in the Research Track at International Semantic Web Conference 2021 for our work Improving Inductive Link Prediction Using Hyper-Relational Facts! Won’t be possible without the team of Mehdi Ali, Max Berrendorf, Veronika Thost, Tengfei Ma, Volker Tresp, and Jens Lehmann! GitHub
Knowledge Graphs @ ACL 2021
Regular review of KG-related papers from ACL 2021, the major NLP research venue in the area. This time: neural databases, retrieval, KG embeddings, entity linking, QA, and a bunch of new datasets.
NodePiece - Tokenizing Knowledge Graphs
A new blogpost on our recent research idea: if nodes in a graph are “words”, can we design a fixed-size vocab of “sub-word” units and go beyond shallow embedding? We propose NodePiece, a compositional tokenization approach for dramatic KG vocabulary size reduction, and find that in some tasks, you don’t even need trainable node embeddings! Furthermore, NodePiece is inductive by design and can encode unseen nodes using the same backbone vocabulary.
Knowledge Graphs @ ICLR 2021
I compiled a short overview of cool KG-related papers on Neural Reasoning, Temporal Reasoning, Relational Learning, and a bit of Complex QA! Brew some Hot beverage and have a nice weekend reading.
Machine Learning on Knowledge Graphs @ NeurIPS 2020
Concluding the year with the review of KG-related papers from NeurIPS 2020: Query Embedding, NAS, Meta-Learning, 📦 vs 🔮, big new benchmarks incl. OGB and GraphGYM, and ⚡️ KeOps!
Knowledge Graphs & NLP @ EMNLP 2020
My review of most prominent KG-related papers from EMNLP 2020. This time we talk about KG-augmented language models, information extraction, entity linking, KG representation algorithms, and many more!
Representation Learning on RDF* and LPG Graphs
I wrote a new Medium post about our recent EMNLP 2020 paper “Message Passing for Hyper-Relational Knowledge Graphs” where we design graph neural nets for more complex graph structures such as hyper-relational KGs like Wikidata.
Knowledge Graphs in Natural Language Processing @ ACL 2020
The anniversary post is the series of KG-related papers. It’s been one year since I started publising such digests, and we’re back to the NLP roots and ACL 2020! This time I focus on question answering, KG embeddings, graph-to-text NLG, some ConvAI and OpenIE.
Knowledge Graphs @ ICLR 2020
Published a review of KG-related papers from the past ICLR 2020! Among other things we’ll review what’s happening in complex QA, KG embeddings and entity matching with graph embeddings.
Knowledge Graphs @ AAAI 2020
Here is a fresh digest of KG-related papers in the NLP context from the past AAAI 2020! We’ll check out new stuff in KG-augmented Language Models, GNN-based entity matching, news on link prediction especially in the temporal dimension, and finally some new papers in ConvAI and Knowledge Graph Question Answering!
Machine Learning on Graphs @ NeurIPS 2019
A new review on Medium of KG and NLP-related papers from NeurIPS 2019. We’ll have a look on novelties in hyperbolic graph embeddings, new KG embeddings with some logic support, new trends in Markov Logic Nets, new goodies from the ConvAI part, and some interesting GNN-related publications. My review of knowledge graph-related papers from EMNLP 2019.
Knowledge Graphs & NLP @ EMNLP 2019
My review of knowledge graph-related papers from EMNLP 2019. Part I is about language models, extracting KGs from text, dialogue systems, and KG embeddings. Part II discusses question answering, natural language generation from KGs, commonsense reasoning, and NER & RL.
The Mushroom Effect or Why You Need Knowledge Graphs for Dialog Systems
A new post on Medium. Be sure to check it out!
Knowledge graphs in Natural Language Processing @ ACL 2019
Hello, ACL 2019 has just finished and I attended the whole week of the conference talks, tutorials, and workshops in beautiful Florence! In this post I would like to recap how knowledge graphs slowly but firmly integrate into the NLP community 
SpaCy IRL 2019 - Wikidata-based NER in v3.0
On July, 6th in Berlin I attended spaCy IRL - a conference organized by explosion.ai and spacy which you probably know as one of the most popular, powerful and fast NLP libraries. Here is a short overview of the event. 
Impressions from CISS 2
Recently returned back from the 2nd Conversational Intelligence Summer School organized by the Text Machine Lab of UMass Lowell and iPavlov lab from MIPT, Moscow. The School took place in Lowell, MA, USA, one of the first US industrial cities with remaining spirit of the industrial revolution. 
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
The Simple Web-based Tool for Visualization and Sharing of Semantic Data and Ontologies
Download here
FuhSen: A Federated Hybrid Search Engine for Building a Knowledge Graph On-Demand (Short Paper)
Download here
Enterprise Knowledge Graphs: A Semantic Approach for Knowledge Management in the Next Generation of Enterprise Information Systems
Download here
Demonstration of a Customizable Representation Model for Graph-Based Visualizations of Ontologies–GizMO
Download here
Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework
Download here
A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphs
Use Google Scholar for full citation
Download here
An Open Challenge for Inductive Link Prediction on Knowledge Graphs
Use Google Scholar for full citation
Download here
NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs
Download here
Neural-Symbolic Models for Logical Queries on Knowledge Graphs
Use Google Scholar for full citation
Download here
A Decade of Knowledge Graphs in Natural Language Processing: A Survey
Use Google Scholar for full citation
Download here
Inductive Logical Query Answering in Knowledge Graphs
Use Google Scholar for full citation
Download here
Long Range Graph Benchmark
Use Google Scholar for full citation
Download here
Recipe for a General, Powerful, Scalable Graph Transformer
Use Google Scholar for full citation
Download here
Approximate Answering of Graph Queries
Use Google Scholar for full citation
Download here
PARSAC: Fast, Human-quality Floorplanning for Modern SoCs with Complex Design Constraints
Download here
TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs
Download here
talks
Knowledge Graphs and Conversational AI
An extended version of the AI Journey talk. Slides in PDF
Stanford CS 520 Lecture 1 Slides
I had a privilege giving a talk at the kick-off Lecture 1 of the CS 520 Stanford seminar on Knowledge Graphs. The topic of L1 was ‘What is a Knowledge Graph’ where I approached definitions of a KG from multiple perspectives. Slides in PDF
Placing Knowledge Graphs in Graph ML
I gave a talk at the annual Data Fest organized by the Open Data Science community where my main focus was placing KGs into the Graph ML field. We discussed how KGs differ from traditional graphs and what are some interesting open problems combining GNNs and KGs. YouTube and Slides
Message Passing for Hyper-Relational Knowledge Graphs
Here is the recorded presentation of our EMNLP 2020 paper on designing GNNs for more complex graph structures such as hyper-relational KGs like Wikidata. Slideslive Video and PDF Slides
Complex Question Answering over Knowledge Graphs
I conducted several lectures at different venues (e.g., AI Journey 2020 and others) on Complex KGQA using shorter or longer versions of this deck. PDF Slides
Placing Knowledge Graphs in Graph ML
Gave a talk on how to place knowledge graphs into the ecosystem of Graph ML research, open challenges and theoretical problems. PDF Slides
Intro to Knowledge Graphs
Had a pleasure presenting the introduction to knowledge graphs to the students of the COMP 599 Network Science course at McGill in the Autumn semester 2021. Thanks Prof. Reihaney Rabbany for inviting me! PDF Slides
Beyond Shallow Embeddings of Knowledge Graphs
A new talk covering the challenges of KG representation learning when it comes to inductive tasks and featurizing nodes unseen during training time. PDF Slides
Compositional Tokenization in Knowledge Graphs
A collection of talks under the main umbrella idea - can we design a uniform node representation mechanism for representation learning on KGs suitable for both transductive and inductive tasks? Covering a lot of intuition from our NodePiece paper. PDF Slides
NodePiece @ Netflix and Twitter
Delivered a few virtual talks about the NodePiece paper at Netflix (March 4th) and Twitter (March 16th). PDF Slides
Discovering New ML Applications on Knowledge Graphs
Delivered a virtual talk at Bosch (April 12th) on discovering new Graph ML applications over KGs going beyond transductive link prediction at Netflix. PDF Slides
Inductive Graph Reasoning without Node Features
Delivered an in-person talk at the Topology & Geometry Workshop at Banff International Research Station (BIRS) in beautiful Kelowna, BC, Canada! The talk covered our ICLR’22 and NeurIPS’22 papers. PDF Slides
GraphGPS
Presented our recent GraphGPS paper at the LOG2 reading group together with Ladislav Rampášek. The recording is available on YouTube.
LoG 2022 Mila Meetup
Presented a handful of papers from our group at Mila (accepted to LoG and NeurIPS’22) at the local meetup of the Learning on Graphs Conference. Slides
Neural Graph Databases
Presented our recent work on Neural Graph Databases at the “Knowledge Graph and Semantic Computing” seminar series at UIUC.
Neural Graph Databases
Presented our recent work on Neural Graph Databases at the NLP seminar at UKRI Centre for Doctoral Training in Natural Language Processing at the University of Edinburgh.
Towards Foundation Models for Graph Reasoning and AI4Science
Visited UCSD with the talk on foundation models for graph learning. Slides
Graph Foundation Models
I was glad to participate in the Dagstuhl seminar on Scalable Graph Mining and Learning in snowy December Dagstuhl together with many other prominent Graph ML researchers and presenting the recent work on graph foundation models.
Foundation Models for Knowledge Graph Reasoning?
Gave a talk on Ultra at the LOGG reading group, recording is already available on YouTube. Thanks Hannes and Dominique for the invitation!
Neural Graph Reasoning
Gave a talk on neural graph reasoning, neural graph databases, and query answering with GNNs at Stardog.
Foundation Models for Knowledge Graph Reasoning: Is Inductive Reasoning Solved?
It was a delightful experience to participate in the week-long workshop on GNNs and neuro-symbolic AI (FANeSy) organized by Pablo Barcelo, CENIA, and Unversidad San Sebastian. Thanks Pablo for the invitation!
Graph Foundation Models for Knowledge Graph Reasoning and Beyond
Visited the group of professor Xavier Bresson at the National University of Singapore with the talk on graph foundation models - from KG reasoning to AI 4 Science. Slides