Petar Veličković

30 papers · 2018–2025 · 6 conferences · across top CS/AI conferences

Achievements

+13 more ↓

🌍 Conference Polyglot (6) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (7)

🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 👑 Triple Crown 🏆 Keyword Champion (4) 🏆 Grand Slam 👥 Mega-Team (22) 🗃️ Keyword Collector (68) ⚡ Prolific Year (5) 🚀 Conference Pioneer 💎 Century Club (30) 🔥 Unstoppable (8) ❓ The Questioner (3)

Conferences

ICML (9) NIPS (9) ICLR (8) IJCAI (2) AAAI (1) JMLR (1)

Top co-authors

Pietro Lió (6) Razvan Pascanu (5) Charles Blundell (4) Federico Barbero (3) Alex Vitvitskyi (3) Shantanu Thakoor (2) Didier Chetelat (2) Yoshua Bengio (2) Gabriele Corso (2) Jian Tang (2)

Keywords

graph neural network (9) message passing (4) neural algorithmic reasoning (4) combinatorial optimization (3) representation learning (2) self-supervised learning (2) graph algorithm (2) dynamic programming (2) algorithm execution (2) algorithmic reasoning (2) neural network (2) explainable ai (1) concept-based explanation (1) out-of-distribution generalization (1) automated planning (1) multi-task learning (1) curriculum learning (1) constraint satisfaction (1) graph theory (1) reinforcement learning (1)

Papers

What Makes a Good Feedforward Computational Graph? ICML 2025 Softmax is not Enough (for Sharp Size Generalisation) ICML 2025 Positional Attention: Expressivity and Learnability of Algorithmic Computation ICML 2025 Round and Round We Go! What makes Rotary Positional Encodings useful? ICLR 2025 Mastering Board Games by External and Internal Planning with Language Models ICML 2025 Position: Categorical Deep Learning is an Algebraic Theory of All Architectures ICML 2024 Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search IJCAI 2024 Transformers need glasses! Information over-squashing in language tasks NIPS 2024 Position: Topological Deep Learning is the New Frontier for Relational Learning ICML 2024 Half-Hop: A graph upsampling approach for slowing down message passing ICML 2023 Combinatorial Optimization and Reasoning with Graph Neural Networks JMLR 2023 Dual Algorithmic Reasoning ICLR 2023 Affinity-Aware Graph Networks NIPS 2023 Neural Algorithmic Reasoning with Causal Regularisation ICML 2023 Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond ICLR 2022 Learning to Configure Computer Networks with Neural Algorithmic Reasoning NIPS 2022 Graph Neural Networks are Dynamic Programmers NIPS 2022 Algorithmic Concept-Based Explainable Reasoning AAAI 2022 Large-Scale Representation Learning on Graphs via Bootstrapping ICLR 2022 The CLRS Algorithmic Reasoning Benchmark ICML 2022 How to transfer algorithmic reasoning knowledge to learn new algorithms? NIPS 2021 Neural Distance Embeddings for Biological Sequences NIPS 2021 On the role of planning in model-based deep reinforcement learning ICLR 2021 Neural Algorithmic Reasoners are Implicit Planners NIPS 2021 Combinatorial Optimization and Reasoning with Graph Neural Networks IJCAI 2021 Principal Neighbourhood Aggregation for Graph Nets NIPS 2020 Neural Execution of Graph Algorithms ICLR 2020 Pointer Graph Networks NIPS 2020 Deep Graph Infomax ICLR 2019 Graph Attention Networks ICLR 2018