Search Results for author: Mikhail Galkin

Found 21 papers, 18 papers with code

MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling

1 code implementation12 Sep 2023 Kin Long Kelvin Lee, Carmelo Gonzales, Marcel Nassar, Matthew Spellings, Mikhail Galkin, Santiago Miret

We propose MatSci ML, a novel benchmark for modeling MATerials SCIence using Machine Learning (MatSci ML) methods focused on solid-state materials with periodic crystal structures.

Multi-Task Learning

Approximate Answering of Graph Queries

no code implementations12 Aug 2023 Michael Cochez, Dimitrios Alivanistos, Erik Arakelyan, Max Berrendorf, Daniel Daza, Mikhail Galkin, Pasquale Minervini, Mathias Niepert, Hongyu Ren

We will first provide an overview of the different query types which can be supported by these methods and datasets typically used for evaluation, as well as an insight into their limitations.

Knowledge Graphs

Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases

1 code implementation26 Mar 2023 Hongyu Ren, Mikhail Galkin, Michael Cochez, Zhaocheng Zhu, Jure Leskovec

Extending the idea of graph databases (graph DBs), NGDB consists of a Neural Graph Storage and a Neural Graph Engine.

Link Prediction Logical Reasoning +1

Attending to Graph Transformers

1 code implementation8 Feb 2023 Luis Müller, Mikhail Galkin, Christopher Morris, Ladislav Rampášek

Recently, transformer architectures for graphs emerged as an alternative to established techniques for machine learning with graphs, such as graph neural networks.

Weisfeiler and Leman Go Relational

1 code implementation30 Nov 2022 Pablo Barcelo, Mikhail Galkin, Christopher Morris, Miguel Romero Orth

Namely, we investigate the limitations in the expressive power of the well-known Relational GCN and Compositional GCN architectures and shed some light on their practical learning performance.

Knowledge Graphs Logical Reasoning +1

Inductive Logical Query Answering in Knowledge Graphs

1 code implementation13 Oct 2022 Mikhail Galkin, Zhaocheng Zhu, Hongyu Ren, Jian Tang

Exploring the efficiency--effectiveness trade-off, we find the inductive relational structure representation method generally achieves higher performance, while the inductive node representation method is able to answer complex queries in the inference-only regime without any training on queries and scales to graphs of millions of nodes.

Complex Query Answering Entity Embeddings +2

A Decade of Knowledge Graphs in Natural Language Processing: A Survey

1 code implementation30 Sep 2022 Phillip Schneider, Tim Schopf, Juraj Vladika, Mikhail Galkin, Elena Simperl, Florian Matthes

In pace with developments in the research field of artificial intelligence, knowledge graphs (KGs) have attracted a surge of interest from both academia and industry.

Knowledge Graphs

Long Range Graph Benchmark

1 code implementation16 Jun 2022 Vijay Prakash Dwivedi, Ladislav Rampášek, Mikhail Galkin, Ali Parviz, Guy Wolf, Anh Tuan Luu, Dominique Beaini

Graph Neural Networks (GNNs) that are based on the message passing (MP) paradigm generally exchange information between 1-hop neighbors to build node representations at each layer.

Benchmarking Graph Classification +4

A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs

2 code implementations7 Jun 2022 Zhaocheng Zhu, Xinyu Yuan, Mikhail Galkin, Sophie Xhonneux, Ming Zhang, Maxime Gazeau, Jian Tang

Experiments on both transductive and inductive knowledge graph reasoning benchmarks show that A*Net achieves competitive performance with existing state-of-the-art path-based methods, while merely visiting 10% nodes and 10% edges at each iteration.

Knowledge Graphs

Recipe for a General, Powerful, Scalable Graph Transformer

3 code implementations25 May 2022 Ladislav Rampášek, Mikhail Galkin, Vijay Prakash Dwivedi, Anh Tuan Luu, Guy Wolf, Dominique Beaini

We propose a recipe on how to build a general, powerful, scalable (GPS) graph Transformer with linear complexity and state-of-the-art results on a diverse set of benchmarks.

Graph Classification Graph Property Prediction +4

Neural-Symbolic Models for Logical Queries on Knowledge Graphs

1 code implementation ICML 2022 Zhaocheng Zhu, Mikhail Galkin, Zuobai Zhang, Jian Tang

Answering complex first-order logic (FOL) queries on knowledge graphs is a fundamental task for multi-hop reasoning.

A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphs

2 code implementations14 Mar 2022 Charles Tapley Hoyt, Max Berrendorf, Mikhail Galkin, Volker Tresp, Benjamin M. Gyori

The link prediction task on knowledge graphs without explicit negative triples in the training data motivates the usage of rank-based metrics.

Benchmarking Knowledge Graph Embedding +2

An Open Challenge for Inductive Link Prediction on Knowledge Graphs

1 code implementation3 Mar 2022 Mikhail Galkin, Max Berrendorf, Charles Tapley Hoyt

An emerging trend in representation learning over knowledge graphs (KGs) moves beyond transductive link prediction tasks over a fixed set of known entities in favor of inductive tasks that imply training on one graph and performing inference over a new graph with unseen entities.

Graph Representation Learning Inductive Link Prediction +1

Improving Inductive Link Prediction Using Hyper-Relational Facts

1 code implementation10 Jul 2021 Mehdi Ali, Max Berrendorf, Mikhail Galkin, Veronika Thost, Tengfei Ma, Volker Tresp, Jens Lehmann

In this work, we classify different inductive settings and study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by recent advancements in graph neural networks.

Inductive Link Prediction Knowledge Graphs

Query Embedding on Hyper-relational Knowledge Graphs

1 code implementation ICLR 2022 Dimitrios Alivanistos, Max Berrendorf, Michael Cochez, Mikhail Galkin

Besides that, we propose a method to answer such queries and demonstrate in our experiments that qualifiers improve query answering on a diverse set of query patterns.

Knowledge Graphs Link Prediction +2

Message Passing for Hyper-Relational Knowledge Graphs

1 code implementation EMNLP 2020 Mikhail Galkin, Priyansh Trivedi, Gaurav Maheshwari, Ricardo Usbeck, Jens Lehmann

We also demonstrate that existing benchmarks for evaluating link prediction (LP) performance on hyper-relational KGs suffer from fundamental flaws and thus develop a new Wikidata-based dataset - WD50K.

Knowledge Graphs Link Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.