Search Results for author: Igor Melnyk

Found 28 papers, 7 papers with code

Auditing and Generating Synthetic Data with Controllable Trust Trade-offs

no code implementations21 Apr 2023 Brian Belgodere, Pierre Dognin, Adam Ivankay, Igor Melnyk, Youssef Mroueh, Aleksandra Mojsilovic, Jiri Navratil, Apoorva Nitsure, Inkit Padhi, Mattia Rigotti, Jerret Ross, Yair Schiff, Radhika Vedpathak, Richard A. Young

We present an auditing framework that offers a holistic assessment of synthetic datasets and AI models trained on them, centered around bias and discrimination prevention, fidelity to the real data, utility, robustness, and privacy preservation.

Model Selection Privacy Preserving

Knowledge Graph Generation From Text

1 code implementation18 Nov 2022 Igor Melnyk, Pierre Dognin, Payel Das

In this work we propose a novel end-to-end multi-stage Knowledge Graph (KG) generation system from textual inputs, separating the overall process into two stages.

Graph Generation Language Modelling

Reprogramming Large Pretrained Language Models for Antibody Sequence Infilling

no code implementations5 Oct 2022 Igor Melnyk, Vijil Chenthamarakshan, Pin-Yu Chen, Payel Das, Amit Dhurandhar, Inkit Padhi, Devleena Das

We introduce Reprogramming for Protein Sequence Infilling, a framework in which pretrained natural language models are repurposed for protein sequence infilling via reprogramming, to infill protein sequence templates as a method of novel protein generation.

Specificity Text Infilling

AlphaFold Distillation for Improved Inverse Protein Folding

no code implementations5 Oct 2022 Igor Melnyk, Aurelie Lozano, Payel Das, Vijil Chenthamarakshan

In this work, we propose to perform knowledge distillation on the folding model's confidence metrics, e. g., pTM or pLDDT scores, to obtain a smaller, faster and end-to-end differentiable distilled model, which then can be included as part of the structure consistency regularized inverse folding model training.

Drug Discovery Knowledge Distillation +2

Benchmarking deep generative models for diverse antibody sequence design

no code implementations12 Nov 2021 Igor Melnyk, Payel Das, Vijil Chenthamarakshan, Aurelie Lozano

Here we consider three recently proposed deep generative frameworks for protein design: (AR) the sequence-based autoregressive generative model, (GVP) the precise structure-based graph neural network, and Fold2Seq that leverages a fuzzy and scale-free representation of a three-dimensional fold, while enforcing structure-to-sequence (and vice versa) consistency.


ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models

1 code implementation EMNLP 2021 Pierre L. Dognin, Inkit Padhi, Igor Melnyk, Payel Das

Automatic construction of relevant Knowledge Bases (KBs) from text, and generation of semantically meaningful text from KBs are both long-standing goals in Machine Learning.

Graph Generation reinforcement-learning +2

Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design

1 code implementation24 Jun 2021 Yue Cao, Payel Das, Vijil Chenthamarakshan, Pin-Yu Chen, Igor Melnyk, Yang shen

Designing novel protein sequences for a desired 3D topological fold is a fundamental yet non-trivial task in protein engineering.

Image Captioning as an Assistive Technology: Lessons Learned from VizWiz 2020 Challenge

1 code implementation21 Dec 2020 Pierre Dognin, Igor Melnyk, Youssef Mroueh, Inkit Padhi, Mattia Rigotti, Jarret Ross, Yair Schiff, Richard A. Young, Brian Belgodere

Image captioning has recently demonstrated impressive progress largely owing to the introduction of neural network algorithms trained on curated dataset like MS-COCO.

Image Captioning Navigate

Alleviating Noisy Data in Image Captioning with Cooperative Distillation

no code implementations21 Dec 2020 Pierre Dognin, Igor Melnyk, Youssef Mroueh, Inkit Padhi, Mattia Rigotti, Jarret Ross, Yair Schiff

Image captioning systems have made substantial progress, largely due to the availability of curated datasets like Microsoft COCO or Vizwiz that have accurate descriptions of their corresponding images.

Image Captioning

Tabular Transformers for Modeling Multivariate Time Series

1 code implementation3 Nov 2020 Inkit Padhi, Yair Schiff, Igor Melnyk, Mattia Rigotti, Youssef Mroueh, Pierre Dognin, Jerret Ross, Ravi Nair, Erik Altman

This results in two architectures for tabular time series: one for learning representations that is analogous to BERT and can be pre-trained end-to-end and used in downstream tasks, and one that is akin to GPT and can be used for generation of realistic synthetic tabular sequences.

Fraud Detection Synthetic Data Generation +1

DualTKB: A Dual Learning Bridge between Text and Knowledge Base

no code implementations EMNLP 2020 Pierre L. Dognin, Igor Melnyk, Inkit Padhi, Cicero Nogueira dos santos, Payel Das

In this work, we present a dual learning approach for unsupervised text to path and path to text transfers in Commonsense Knowledge Bases (KBs).

Optimizing Mode Connectivity via Neuron Alignment

1 code implementation NeurIPS 2020 N. Joseph Tatro, Pin-Yu Chen, Payel Das, Igor Melnyk, Prasanna Sattigeri, Rongjie Lai

Yet, current curve finding algorithms do not consider the influence of symmetry in the loss surface created by model weight permutations.

Optimizing Loss Landscape Connectivity via Neuron Alignment

no code implementations25 Sep 2019 N. Joseph Tatro, Pin-Yu Chen, Payel Das, Igor Melnyk, Prasanna Sattigeri, Rongjie Lai

Empirically, this initialization is critical for efficiently learning a simple, planar, low-loss curve between networks that successfully generalizes.

Estimating Information Flow in DNNs

no code implementations ICLR 2019 Ziv Goldfeld, Ewout van den Berg, Kristjan Greenewald, Brian Kingsbury, Igor Melnyk, Nam Nguyen, Yury Polyanskiy

We then develop a rigorous estimator for I(X;T) in noisy DNNs and observe compression in various models.

Improved Adversarial Image Captioning

no code implementations ICLR Workshop DeepGenStruct 2019 Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jarret Ross, Tom Sercu

In this paper we study image captioning as a conditional GAN training, proposing both a context-aware LSTM captioner and co-attentive discriminator, which enforces semantic alignment between images and captions.

Image Captioning

Wasserstein Barycenter Model Ensembling

1 code implementation13 Feb 2019 Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jerret Ross, Cicero dos Santos, Tom Sercu

In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters.

General Classification Image Captioning +1

Estimating Information Flow in Deep Neural Networks

no code implementations12 Oct 2018 Ziv Goldfeld, Ewout van den Berg, Kristjan Greenewald, Igor Melnyk, Nam Nguyen, Brian Kingsbury, Yury Polyanskiy

We then develop a rigorous estimator for $I(X;T)$ in noisy DNNs and observe compression in various models.

Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer

no code implementations ACL 2018 Cicero Nogueira dos Santos, Igor Melnyk, Inkit Padhi

We introduce a new approach to tackle the problem of offensive language in online social media.

Style Transfer Text Style Transfer +1

Adversarial Semantic Alignment for Improved Image Captions

no code implementations30 Apr 2018 Pierre L. Dognin, Igor Melnyk, Youssef Mroueh, Jarret Ross, Tom Sercu

When evaluated on OOC and MS-COCO benchmarks, we show that SCST-based training has a strong performance in both semantic score and human evaluation, promising to be a valuable new approach for efficient discrete GAN training.

Image Captioning

Deep learning algorithm for data-driven simulation of noisy dynamical system

no code implementations22 Feb 2018 Kyongmin Yeo, Igor Melnyk

It is shown that, when the numerical discretization is used, the function estimation problem can be solved by a multi-label classification problem.

Multi-Label Classification Time Series Analysis

Learning temporal evolution of probability distribution with Recurrent Neural Network

no code implementations ICLR 2018 Kyongmin Yeo, Igor Melnyk, Nam Nguyen, Eun Kyung Lee

We propose to tackle a time series regression problem by computing temporal evolution of a probability density function to provide a probabilistic forecast.

General Classification regression +1

Improved Neural Text Attribute Transfer with Non-parallel Data

no code implementations26 Nov 2017 Igor Melnyk, Cicero Nogueira dos santos, Kahini Wadhawan, Inkit Padhi, Abhishek Kumar

Text attribute transfer using non-parallel data requires methods that can perform disentanglement of content and linguistic attributes.

Disentanglement Text Attribute Transfer

R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting

no code implementations10 Sep 2017 Hardik Goel, Igor Melnyk, Arindam Banerjee

In many multivariate time series modeling problems, there is usually a significant linear dependency component, for which VARs are suitable, and a nonlinear component, for which RNNs are suitable.

Multivariate Time Series Forecasting

SenGen: Sentence Generating Neural Variational Topic Model

no code implementations1 Aug 2017 Ramesh Nallapati, Igor Melnyk, Abhishek Kumar, Bo-Wen Zhou

We present a new topic model that generates documents by sampling a topic for one whole sentence at a time, and generating the words in the sentence using an RNN decoder that is conditioned on the topic of the sentence.

Semi-Markov Switching Vector Autoregressive Model-based Anomaly Detection in Aviation Systems

no code implementations21 Feb 2016 Igor Melnyk, Arindam Banerjee, Bryan Matthews, Nikunj Oza

In this context the goal is to detect anomalous flight segments, due to mechanical, environmental, or human factors in order to identifying operationally significant events and provide insights into the flight operations and highlight otherwise unavailable potential safety risks and precursors to accidents.

Anomaly Detection Time Series Analysis

Estimating Structured Vector Autoregressive Model

no code implementations21 Feb 2016 Igor Melnyk, Arindam Banerjee

While considerable advances have been made in estimating high-dimensional structured models from independent data using Lasso-type models, limited progress has been made for settings when the samples are dependent.

A Spectral Algorithm for Inference in Hidden Semi-Markov Models

no code implementations12 Jul 2014 Igor Melnyk, Arindam Banerjee

Hidden semi-Markov models (HSMMs) are latent variable models which allow latent state persistence and can be viewed as a generalization of the popular hidden Markov models (HMMs).

Cannot find the paper you are looking for? You can Submit a new open access paper.