7 citations · 17 across the 12 of their papers we have counts for
12 papers
UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG
Dobrik Georgiev, Kheeran Naidu, Kheeran K. Naidu +4
Large language models (LLMs) frequently generate confident yet factually incorrect content when used for language generation (a phenomenon often known as hallucination). Retrieval…
KNARsack: Teaching Neural Algorithmic Reasoners to Solve Pseudo-Polynomial Problems
Stjepan Požgaj, Dobrik Georgiev, Marin Šilić +1
Neural algorithmic reasoning (NAR) is a growing field that aims to embed algorithmic logic into neural networks by imitating classical algorithms. In this extended abstract, we det…
Deep Equilibrium Algorithmic Reasoning
Dobrik Georgiev, JJ Wilson, Davide Buffelli +1
Neural Algorithmic Reasoning (NAR) research has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. However, most previous approaches have a…
Neural Algorithmic Reasoning with Multiple Correct Solutions
Zeno Kujawa, John Poole, Dobrik Georgiev +3
Neural Algorithmic Reasoning (NAR) extends classical algorithms to higher dimensional data. However, canonical implementations of NAR train neural networks to return only a single…
The Deep Equilibrium Algorithmic Reasoner
Dobrik Georgiev, Pietro Liò, Davide Buffelli
Recent work on neural algorithmic reasoning has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms. Doing so, however, has always used a rec…
Parallel Algorithms Align with Neural Execution
Valerie Engelmayer, Dobrik Georgiev, Petar Veličković
Neural algorithmic reasoners are parallel processors. Teaching them sequential algorithms contradicts this nature, rendering a significant share of their computations redundant. Pa…
Neural Algorithmic Reasoning for Combinatorial Optimisation
Dobrik Georgiev, Danilo Numeroso, Davide Bacciu +1
Solving NP-hard/complete combinatorial problems with neural networks is a challenging research area that aims to surpass classical approximate algorithms. The long-term objective i…
Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis
Han Xuanyuan, Pietro Barbiero, Dobrik Georgiev +2
Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current explainability approaches are t…
HEAT: Hyperedge Attention Networks
Dobrik Georgiev, Marc Brockschmidt, Miltiadis Allamanis
Learning from structured data is a core machine learning task. Commonly, such data is represented as graphs, which normally only consider (typed) binary relationships between pairs…
Algorithmic Concept-based Explainable Reasoning
Dobrik Georgiev, Pietro Barbiero, Dmitry Kazhdan +2
Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems. This has numerous benefits, su…
PyTorch, Explain! A Python library for Logic Explained Networks
Pietro Barbiero, Gabriele Ciravegna, Dobrik Georgiev +1
"PyTorch, Explain!" is a Python module integrating a variety of state-of-the-art approaches to provide logic explanations from neural networks. This package focuses on bringing the…
Neural Bipartite Matching
Dobrik Georgiev, Pietro Liò
Graph neural networks (GNNs) have found application for learning in the space of algorithms. However, the algorithms chosen by existing research (sorting, Breadth-First search, sho…