4 citations · 8 across the 8 of their papers we have counts for
8 papers
Bayesian Sensitivity of Causal Inference Estimators under Evidence-Based Priors
Nikita Dhawan, Daniel Shen, Leonardo Cotta +1
Causal inference, especially in observational studies, relies on untestable assumptions about the true data-generating process. Sensitivity analysis helps us determine how robust o…
Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab
Haonan Duan, Stephen Zhewen Lu, Caitlin Fiona Harrigan +5
Designing experiments and result interpretations are core scientific competencies, particularly in biology, where researchers perturb complex systems to uncover the underlying syst…
End-To-End Causal Effect Estimation from Unstructured Natural Language Data
Nikita Dhawan, Leonardo Cotta, Karen Ullrich +2
Knowing the effect of an intervention is critical for human decision-making, but current approaches for causal effect estimation rely on manual data collection and structuring, reg…
Test-Time Fairness and Robustness in Large Language Models
Leonardo Cotta, Chris J. Maddison
Frontier Large Language Models (LLMs) can be socially discriminatory or sensitive to spurious features of their inputs. Because only well-resourced corporations can train frontier…
Probabilistic Invariant Learning with Randomized Linear Classifiers
Leonardo Cotta, Gal Yehuda, Assaf Schuster +1
Designing models that are both expressive and preserve known invariances of tasks is an increasingly hard problem. Existing solutions tradeoff invariance for computational or memor…
Causal Lifting and Link Prediction
Leonardo Cotta, Beatrice Bevilacqua, Nesreen Ahmed +1
Existing causal models for link prediction assume an underlying set of inherent node factors -- an innate characteristic defined at the node's birth -- that governs the causal evol…
Reconstruction for Powerful Graph Representations
Leonardo Cotta, Christopher Morris, Bruno Ribeiro
Graph neural networks (GNNs) have limited expressive power, failing to represent many graph classes correctly. While more expressive graph representation learning (GRL) alternative…
Unsupervised Joint -node Graph Representations with Compositional Energy-Based Models
Leonardo Cotta, Carlos H. C. Teixeira, Ananthram Swami +1
Existing Graph Neural Network (GNN) methods that learn inductive unsupervised graph representations focus on learning node and edge representations by predicting observed edges in…