Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
projects
Master Thesis: Conditional Normalising Flows for Interpretability Permalink
This work aims to fill the gap of two existing interpretability methods for global feature importance (Relative feature importance and Shapley additive global importance), by using deep conditional density estimator/sampler – Conditional Normalising Flow. After utilising noise regularisation, they do not require a rigorous hyperparameter search and could be used in the vanilla setting. We make an extensive empirical evaluation on different synthetic and real datasets with the help of a self-designed evaluation benchmark. Ground-truth feature importances are in general intractable, thus we inherited the concepts of strong and weak feature relevance, which have one-to-one relation to the causal structure of data generating mechanism. By utilising continuous datasets with a known causal graph, we can reason about the validity of estimated importances. Additionally, we provided a use case of RFI for detection of influence of sensitive attributes, when they are included in predictive modelling or completely ignored. This thesis extends the existing Python library for Relative Feature Importance, with Conditional Normalising Flow and Mixture Density Network, as well as with the synthetic benchmark.
Research Project: Certain Pseudo-Labeling for Semi-Supervised Image Classification Permalink
Employing uncertanty estimation in pseudo-labelling for semi-supervised image classification methods (Fix-Match). As Vanilla Fix-Match can suffer from overconfident pseudo-labels, we propose to employ active learning techniques to choose more confidently pseudo-labelled images from unlabelled pool. Experimenting with different uncertainty estimators MC Dropout / Spectral Normalisation & GMMs and uncertainty strategies.
Research Project: Semi-Supervised Text Classification Permalink
Semi-supervised text classification based on BERT backbone. The project adapts FixMatch algorithm by introducing an adaptive weak/strong augmentations selection among 6 basic NLP augmentations (from nlpaug library): WordEmbsAug, BackTranslationAug, AbstSummAug, SynonymAug, ContextualWordEmbsAug, ContextualWordEmbsForSentenceAug.
Study Project: Patent Similarity Siemens Permalink
Filing patents is a messy process. Applicants need to ensure their patent does not infringe upon other tens of millions of existing patents. This project aims to automate the search of similar patents.
Measuring, visualising and comparing patent similarities with metadata such as IPC tags. We aim to explore multiple similarity measures (textual, IPC tags, x-citations, graphical, etc), assess correlations, and visualise our findings to draw conclusions.
Study Project: Linear Regression on Homomorphic Encrypted Data Permalink
The aim of this project is to perform Machine Learning (ML) algorithm, namely Linear Regression, on the ciphertext and evaluate its performance and usability. We use gradient descent in order to find LR coefficient estimates, as this algorithm does not require division.
We used Microsoft SEAL C++ library and its Python wrapper - PySEAL. SEAL uses the Fan-Vercauteren homomorphic encryption scheme - Somewhat Fully Homomorphic scheme.
Study Project: Multimodal Emotion Messaging Estimator Permalink
In this project, we introduce the concept of Multimodal Emotion Messaging Estimator (MEME), a human computation and recommendation system. MEME has two main objectives.
1. To recommend emojis on instant messaging platforms which are relevant to the context of the ongoing conversation between users.
2. Creating implicit coherent massive multimodal (text, audios, images) dataset for the multimodal sentiment analysis.
publications
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
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
Estimating Average Causal Effects from Patient Trajectories
D. Frauen, T. Hatt, V. Melnychuk, S. Feuerriegel. Accepted at AAAI, 2023
Fair Off-Policy Learning from Observational Data
D. Frauen, V. Melnychuk, S. Feuerriegel. ArXiv preprint, 2023
Normalizing Flows for Interventional Density Estimation
V. Melnychuk, D. Frauen, S. Feuerriegel. Accepted at ICML, 2023
Counterfactual Fairness for Predictions using Generative Adversarial Networks
Y. Ma, D. Frauen, V. Melnychuk, S. Feuerriegel. ArXiv preprint, 2023
Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model
V. Melnychuk, D. Frauen, S. Feuerriegel. Accepted at NeurIPS, 2023
Reliable Off-Policy Learning for Dosage Combinations
J. Schweisthal, D. Frauen, V. Melnychuk, S. Feuerriegel. Accepted at NeurIPS, 2023
Sharp Bounds for Generalized Causal Sensitivity Analysis
D. Frauen, V. Melnychuk, S. Feuerriegel. Accepted at NeurIPS, 2023
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
Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation
K. Hess, V. Melnychuk, D. Frauen, S. Feuerriegel. Accepted at ICLR, 2024
Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation
V. Melnychuk, D. Frauen, S. Feuerriegel. Accepted at ICLR, 2024
talks
Causal Transformer for Estimating Counterfactual Outcomes, ICML 2022 paper
Published:
Discussing an ICML 2022 paper ‘Causal Transformer for Estimating Counterfactual Outcomes’ at Causality Discussion Group.
| Slides
ICML 2022 & 2023 papers
Published:
Discussing an ICML 2022 paper ‘Causal Transformer for Estimating Counterfactual Outcomes’ and an ICML 2023 paper ‘Normalizing Flows for Interventional Density Estimation’ at the 1st Munich CausalML Workshop.
| Slides
Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation
Published:
Discussing a pre-print ‘Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation’ at the 2nd Munich CausalML Workshop.
| 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.