Unsupervised Anomaly Detection for X-Ray Images
D. Davletshina, V. Melnychuk, V. Tran, H. Singla, M. Berrendorf, E. Faerman, M. Fromm, M. Schubert. ArXiv preprint, 2020
Posts by Collection
portfolio
publications
Knowledge Graph Entity Alignment with Graph Convolutional Networks: Lessons Learned
M. Berrendorf, E. Faerman, V. Melnychuk, V. Tresp, T. Seidl. Accepted at ECIR, 2020
Matching the Clinical Reality: Accurate OCT-Based Diagnosis From Few Labels
V. Melnychuk, E. Faerman, I. Manakov, T. Seidl. ArXiv preprint, 2020
Causal Transformer for Estimating Counterfactual Outcomes
V. Melnychuk, D. Frauen, S. Feuerriegel. Accepted at ICML, 2022 (poster)
Estimating Average Causal Effects from Patient Trajectories
D. Frauen, T. Hatt, V. Melnychuk, S. Feuerriegel. Accepted at AAAI, 2023 (poster)
Normalizing Flows for Interventional Density Estimation
V. Melnychuk, D. Frauen, S. Feuerriegel. Accepted at ICML, 2023 (poster)
Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model
V. Melnychuk, D. Frauen, S. Feuerriegel. Accepted at NeurIPS, 2023 (spotlight poster)
Reliable Off-Policy Learning for Dosage Combinations
J. Schweisthal, D. Frauen, V. Melnychuk, S. Feuerriegel. Accepted at NeurIPS, 2023 (poster)
Sharp Bounds for Generalized Causal Sensitivity Analysis
D. Frauen, V. Melnychuk, S. Feuerriegel. Accepted at NeurIPS, 2023 (poster)
A Neural Framework for Generalized Causal Sensitivity Analysis
D. Frauen, F. Imrie, A. Curth, V. Melnychuk, S. Feuerriegel, M. van der Schaar. Accepted at ICLR, 2024 (poster)
Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation
K. Hess, V. Melnychuk, D. Frauen, S. Feuerriegel. Accepted at ICLR, 2024 (poster)
Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation
V. Melnychuk, D. Frauen, S. Feuerriegel. Accepted at ICLR, 2024 (spotlight poster)
Causal Machine Learning for Predicting Treatment Outcomes
S. Feuerriegel, D. Frauen, V. Melnychuk, J. Schweisthal, K. Hess, A. Curth, S. Bauer, N. Kilbertus, I. S. Kohane & M. van der Schaar. Accepted at Nature Medicine, 2024
Fair Off-Policy Learning from Observational Data
D. Frauen, V. Melnychuk, S. Feuerriegel. Accepted at ICML, 2024 (poster)
DiffPO: A Causal Diffusion Model for Predicting Potential Outcomes of Treatments
Y. Ma, V. Melnychuk, J. Schweisthal, S. Feuerriegel. Accepted at NeurIPS, 2024 (poster)
Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner
V. Melnychuk, S. Feuerriegel, M. van der Schaar. Accepted at NeurIPS, 2024 (poster)
Differentially Private Learners for Heterogeneous Treatment Effects
M. Schröder, V. Melnychuk, S. Feuerriegel. Accepted at ICLR, 2025 (poster)
Conformal Prediction for Causal Effects of Continuous Treatments
M. Schröder, D. Frauen, J. Schweisthal, K. Hess, V. Melnychuk, S. Feuerriegel. Accepted at NeurIPS, 2025 (poster)
Treatment Effect Estimation for Optimal Decision-Making
D. Frauen, V. Melnychuk, J. Schweisthal, M. van der Schaar, S. Feuerriegel. Accepted at NeurIPS, 2025 (poster)
Orthogonal Representation Learning for Estimating Causal Quantities
V. Melnychuk, D. Frauen, J. Schweisthal, S. Feuerriegel. Accepted at AISTATS, 2026 (oral presentation)
An Orthogonal Learner for Individualized Outcomes in Markov Decision Processes
E. Javurek, V. Melnychuk, J. Schweisthal, K. Hess, D. Frauen, S. Feuerriegel. Accepted at ICLR, 2026 (poster)
Efficient and Sharp Off-Policy Learning under Unobserved Confounding
K. Hess, D. Frauen, V. Melnychuk, S. Feuerriegel. Accepted at ICLR, 2026 (poster)
GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomes
V. Melnychuk, S. Feuerriegel. Accepted at ICLR, 2026 (poster)
IGC-Net for Conditional Average Potential Outcome Estimation over Time
K. Hess, D. Frauen, V. Melnychuk, S. Feuerriegel. Accepted at ICLR, 2026 (poster)
Overlap-Adaptive Regularization for Conditional Average Treatment Effect Estimation
V. Melnychuk, D. Frauen, J. Schweisthal, S. Feuerriegel. Accepted at ICLR, 2026 (poster)
Consistent End-to-End Estimation for Counterfactual Fairness
Y. Ma*, V. Melnychuk*, D. Frauen, S. Feuerriegel. Accepted at CLeaR, 2026 (poster)
Frequentist Consistency of Prior-Data Fitted Networks for Causal Inference
V. Melnychuk, V. Balazadeh, S. Feuerriegel, R. G Krishnan. ArXiv preprint, 2026
talks
Causal Transformer for Estimating Counterfactual Outcomes, ICML 2022 paper
Published:
Title: Causal Transformer for Estimating Counterfactual Outcomes
| Slides
Causal Transformer for Estimating Counterfactual Outcomes & Normalizing Flows for Interventional Density Estimation, ICML 2022 & 2023 papers
Published:
Title: Causal Transformer for Estimating Counterfactual Outcomes
| Slides
Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation, ICLR 2024 paper
Published:
Title: Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation
| Slides
Causal ML for predicting treatment outcomes
Published:
Title: Causal ML for predicting treatment outcomes
| Slides
Causal ML for treatment effect estimation
Published:
Tutorial on the universe of the causal ML methods.
| Slides
Causal ML for predicting treatment outcomes
Published:
Title: Causal ML for predicting treatment outcomes
| Slides
Causal ML for predicting treatment outcomes
Published:
Title: Causal ML for predicting treatment outcomes
| Slides
Uncertainty quantification with (causal) prior-fitted networks
Published:
Presenting on-going project with Prof. Rahul G. Krishnan.
Causal ML for treatment effect estimation
Published:
Abstract: In this tutorial, I introduce causal machine learning as a practical toolkit for estimating treatment effects and counterfactuals from observational data. Here, I formalize the potential-outcomes setup and explain why individual treatment effects are not directly observable, which motivates causal identification. I then walk through the key assumptions — consistency, overlap/positivity, and exchangeability — and show how they connect to common causal frameworks (potential outcomes, SCMs, and causal graphs). Building on that foundation, I cover the main estimands (ATE and heterogeneous effects such as CATE) and compare widely used CATE estimators, from plug-in learners (S-/T-learners) to orthogonal and doubly robust approaches based on pseudo-outcomes and residualization (e.g., IPW/RA/DR and R-learning). I conclude the talk with an overview of state-of-the-art works in causal ML and a discussion of open practical challenges such as uncertainty quantification, model selection under limited data, and hidden confounding.
| Slides
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.