Amauri H Souza

6 papers · 2024–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (14) ❓ The Questioner

Venues

ICML (4) ICLR (2)

Top co-authors

Vikas Garg (4) Diego Mesquita (3) Samuel Kaski (3) Tiago Silva (3) Yogesh Verma (2) Luiz Max Carvalho (1) Eliezer de Souza da Silva (1) Rafal Karczewski (1) Omar Rivasplata (1) Vikas K Garg (1)

Research topics

Machine Learning (6) Deep Learning (5) Architectures (4) Optimization & Theory (3) Core Methods (2) Learning Types · Deep Learning (2) Models (2) Mathematics & Optimization (1) Reinforcement Learning (1) Application Areas (1) Learning Types · Machine Learning (1) Methods (1) Optimization (1)

Keywords

graph neural network (2) persistent homology (2) generative flow network (2) generalization bound (2) expressivity (1) divide and conquer (1) phylogenetic inference (1) equivariant graph neural network (1) drug discovery (1) positional encoding (1) detailed balance (1) mode coverage (1) pac-bayesian inequality (1) equivariant (1) regularizer (1) learnable method (1) pipe (1) gflownet (1) aggregating balance condition (1) federated bayesian structure learning (1)

Papers

Generalization and Distributed Learning of GFlowNets ICLR 2025 Positional Encoding meets Persistent Homology on Graphs ICML 2025 When do GFlowNets learn the right distribution? ICLR 2025 Embarrassingly Parallel GFlowNets ICML 2024 On the Generalization of Equivariant Graph Neural Networks ICML 2024 Topological Neural Networks go Persistent, Equivariant, and Continuous ICML 2024