Search Results for author: Vlado Menkovski

Found 36 papers, 13 papers with code

You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets

no code implementations28 Nov 2022 Tianjin Huang, Tianlong Chen, Meng Fang, Vlado Menkovski, Jiaxu Zhao, Lu Yin, Yulong Pei, Decebal Constantin Mocanu, Zhangyang Wang, Mykola Pechenizkiy, Shiwei Liu

Recent works have impressively demonstrated that there exists a subnetwork in randomly initialized convolutional neural networks (CNNs) that can match the performance of the fully trained dense networks at initialization, without any optimization of the weights of the network (i. e., untrained networks).

Out-of-Distribution Detection

Neural Langevin Dynamics: towards interpretable Neural Stochastic Differential Equations

no code implementations17 Nov 2022 Simon M. Koop, Mark A. Peletier, Jacobus W. Portegies, Vlado Menkovski

Neural Stochastic Differential Equations (NSDE) have been trained as both Variational Autoencoders, and as GANs.

Comparison of neural closure models for discretised PDEs

1 code implementation26 Oct 2022 Hugo Melchers, Daan Crommelin, Barry Koren, Vlado Menkovski, Benjamin Sanderse

Of the two trajectory fitting procedures, the discretise-then-optimise approach produces more accurate models than the optimise-then-discretise approach.

Towards Learned Simulators for Cell Migration

no code implementations2 Oct 2022 Koen Minartz, Yoeri Poels, Vlado Menkovski

Simulators driven by deep learning are gaining popularity as a tool for efficiently emulating accurate but expensive numerical simulators.

Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training

no code implementations30 May 2022 Lu Yin, Vlado Menkovski, Meng Fang, Tianjin Huang, Yulong Pei, Mykola Pechenizkiy, Decebal Constantin Mocanu, Shiwei Liu

Recent works on sparse neural network training (sparse training) have shown that a compelling trade-off between performance and efficiency can be achieved by training intrinsically sparse neural networks from scratch.

Semantic-Based Few-Shot Learning by Interactive Psychometric Testing

no code implementations16 Dec 2021 Lu Yin, Vlado Menkovski, Yulong Pei, Mykola Pechenizkiy

In this work, we advance the few-shot learning towards this more challenging scenario, the semantic-based few-shot learning, and propose a method to address the paradigm by capturing the inner semantic relationships using interactive psychometric learning.

Association Few-Shot Learning

Calibrated Adversarial Training

1 code implementation1 Oct 2021 Tianjin Huang, Vlado Menkovski, Yulong Pei, Mykola Pechenizkiy

In this paper, we present the Calibrated Adversarial Training, a method that reduces the adverse effects of semantic perturbations in adversarial training.

Process Discovery Using Graph Neural Networks

1 code implementation13 Sep 2021 Dominique Sommers, Vlado Menkovski, Dirk Fahland

In this paper, we explore the problem of supervised learning of a process discovery technique D. We introduce a technique for training an ML-based model D using graph convolutional neural networks; D translates a given input event log into a sound Petri net.

VAE-CE: Visual Contrastive Explanation using Disentangled VAEs

1 code implementation20 Aug 2021 Yoeri Poels, Vlado Menkovski

An explanation is specified as a set of transformations of the input datapoint, with each step depicting a concept changing towards the contrastive class.


Hierarchical Semantic Segmentation using Psychometric Learning

no code implementations7 Jul 2021 Lu Yin, Vlado Menkovski, Shiwei Liu, Mykola Pechenizkiy

One of the major challenges in the supervised learning approaches is expressing and collecting the rich knowledge that experts have with respect to the meaning present in the image data.

Image Segmentation Metric Learning +1

Direction-Aggregated Attack for Transferable Adversarial Examples

1 code implementation19 Apr 2021 Tianjin Huang, Vlado Menkovski, Yulong Pei, Yuhao Wang, Mykola Pechenizkiy

Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs.

Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networks

1 code implementation16 Apr 2021 Tianjin Huang, Yulong Pei, Vlado Menkovski, Mykola Pechenizkiy

Although various approaches have been proposed to solve this problem, two major limitations exist: (1) unsupervised approaches usually work much less efficiently due to the lack of supervisory signal, and (2) existing anomaly detection methods only use local contextual information to detect anomalous nodes, e. g., one- or two-hop information, but ignore the global contextual information.

Self-Supervised Anomaly Detection supervised anomaly detection

A Metric for Linear Symmetry-Based Disentanglement

no code implementations26 Nov 2020 Luis A. Pérez Rey, Loek Tonnaer, Vlado Menkovski, Mike Holenderski, Jacobus W. Portegies

We propose a metric for the evaluation of the level of LSBD that a data representation achieves.


Quantifying and Learning Linear Symmetry-Based Disentanglement

1 code implementation NeurIPS 2021 Loek Tonnaer, Luis A. Pérez Rey, Vlado Menkovski, Mike Holenderski, Jacobus W. Portegies

The definition of Linear Symmetry-Based Disentanglement (LSBD) formalizes the notion of linearly disentangled representations, but there is currently no metric to quantify LSBD.

Disentanglement Interpretable Machine Learning

Bridging the Performance Gap between FGSM and PGD Adversarial Training

1 code implementation7 Nov 2020 Tianjin Huang, Vlado Menkovski, Yulong Pei, Mykola Pechenizkiy

In addition, it achieves comparable performance of adversarial robustness on MNIST dataset under white-box attack, and it achieves better performance than adv. PGD under white-box attack and effectively defends the transferable adversarial attack on CIFAR-10 dataset.

Adversarial Attack Adversarial Robustness

Quantifying and Learning Disentangled Representations with Limited Supervision

no code implementations28 Sep 2020 Loek Tonnaer, Luis Armando Pérez Rey, Vlado Menkovski, Mike Holenderski, Jacobus W. Portegies

Although several works focus on learning LSBD representations, such methods require supervision on the underlying transformations for the entire dataset, and cannot deal with unlabeled data.

Disentanglement Interpretable Machine Learning

Complex Vehicle Routing with Memory Augmented Neural Networks

no code implementations22 Sep 2020 Marijn van Knippenberg, Mike Holenderski, Vlado Menkovski

Deep Learning may provide solutions which are less time-consuming and of higher quality at large scales, as it generally does not need to generate solutions in an iterative manner, and Deep Learning models have shown a surprising capacity for solving complex tasks in recent years.

Combinatorial Optimization

Explaining Predictions by Approximating the Local Decision Boundary

no code implementations14 Jun 2020 Georgios Vlassopoulos, Tim van Erven, Henry Brighton, Vlado Menkovski

We address this by introducing a new benchmark data set with artificially generated Iris images, and showing that we can recover the latent attributes that locally determine the class.

Knowledge Elicitation using Deep Metric Learning and Psychometric Testing

no code implementations14 Apr 2020 Lu Yin, Vlado Menkovski, Mykola Pechenizkiy

The main reason for such a reductionist approach is the difficulty in eliciting the domain knowledge from the experts.

Metric Learning

Causal Discovery from Incomplete Data: A Deep Learning Approach

no code implementations15 Jan 2020 Yuhao Wang, Vlado Menkovski, Hao Wang, Xin Du, Mykola Pechenizkiy

As systems are getting more autonomous with the development of artificial intelligence, it is important to discover the causal knowledge from observational sensory inputs.

Causal Discovery Imputation

Pedestrian orientation dynamics from high-fidelity measurements

no code implementations14 Jan 2020 Joris Willems, Alessandro Corbetta, Vlado Menkovski, Federico Toschi

We investigate in real-life conditions and with very high accuracy the dynamics of body rotation, or yawing, of walking pedestrians - an highly complex task due to the wide variety in shapes, postures and walking gestures.

Deep learning velocity signals allows to quantify turbulence intensity

no code implementations13 Nov 2019 Alessandro Corbetta, Vlado Menkovski, Roberto Benzi, Federico Toschi

Turbulence, the ubiquitous and chaotic state of fluid motions, is characterized by strong and statistically non-trivial fluctuations of the velocity field, over a wide range of length- and time-scales, and it can be quantitatively described only in terms of statistical averages.

BSDAR: Beam Search Decoding with Attention Reward in Neural Keyphrase Generation

no code implementations17 Sep 2019 Iftitahu Ni'mah, Vlado Menkovski, Mykola Pechenizkiy

This study mainly investigates two decoding problems in neural keyphrase generation: sequence length bias and beam diversity.

Keyphrase Generation

Hierarchical Annotation of Images with Two-Alternative-Forced-Choice Metric Learning

no code implementations23 May 2019 Niels Hellinga, Vlado Menkovski

Many tasks such as retrieval and recommendations can significantly benefit from structuring the data, commonly in a hierarchical way.

Metric Learning Retrieval

Micro-expression detection in long videos using optical flow and recurrent neural networks

no code implementations26 Mar 2019 Michiel Verburg, Vlado Menkovski

This paper presents a novel micro-expression spotting method using a recurrent neural network (RNN) on optical flow features.

Micro-Expression Spotting Optical Flow Estimation +1

StampNet: unsupervised multi-class object discovery

1 code implementation7 Feb 2019 Joost Visser, Alessandro Corbetta, Vlado Menkovski, Federico Toschi

Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background.

Image Clustering Object Discovery

Diffusion Variational Autoencoders

2 code implementations25 Jan 2019 Luis A. Pérez Rey, Vlado Menkovski, Jacobus W. Portegies

A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable of capturing topological properties of certain datasets.

Evolutionary Construction of Convolutional Neural Networks

no code implementations2 Jan 2019 Marijn van Knippenberg, Vlado Menkovski, Sergio Consoli

It combines deep neural networks and evolutionary algorithms to improve and/or automate the construction of neural networks.

Anomaly Detection for imbalanced datasets with Deep Generative Models

no code implementations2 Nov 2018 Nazly Rocio Santos Buitrago, Loek Tonnaer, Vlado Menkovski, Dimitrios Mavroeidis

We train a generative model without supervision on the `negative' (common) datapoints and use this model to estimate the likelihood of unseen data.

Anomaly Detection

Deep Learning in Information Security

no code implementations12 Sep 2018 Stefan Thaler, Vlado Menkovski, Milan Petkovic

Machine learning has a long tradition of helping to solve complex information security problems that are difficult to solve manually.

BIG-bench Machine Learning

Weakly supervised training of deep convolutional neural networks for overhead pedestrian localization in depth fields

no code implementations9 Jun 2017 Alessandro Corbetta, Vlado Menkovski, Federico Toschi

Even though hand-crafted image analysis algorithms are successful in many common cases, they fail frequently when there are complex interactions of multiple objects in the image.

Data Augmentation Object Localization

Understanding Anatomy Classification Through Attentive Response Maps

no code implementations19 Nov 2016 Devinder Kumar, Vlado Menkovski, Graham W. Taylor, Alexander Wong

One of the main challenges for broad adoption of deep learning based models such as convolutional neural networks (CNN), is the lack of understanding of their decisions.

Anatomy Classification +1

Can Pretrained Neural Networks Detect Anatomy?

no code implementations18 Dec 2015 Vlado Menkovski, Zharko Aleksovski, Axel Saalbach, Hannes Nickisch

Convolutional neural networks demonstrated outstanding empirical results in computer vision and speech recognition tasks where labeled training data is abundant.

Anatomy speech-recognition +1

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