Search Results for author:
Found 54 papers, 25 papers with code
Differentially Private Federated Learning of Diffusion Models for Synthetic Tabular Data Generation
The increasing demand for privacy-preserving data analytics in finance necessitates solutions for synthetic data generation that rigorously uphold privacy standards.
GraphGuard: Contrastive Self-Supervised Learning for Credit-Card Fraud Detection in Multi-Relational Dynamic Graphs
Credit card fraud has significant implications at both an individual and societal level, making effective prevention essential.
Towards Scalable and Versatile Weight Space Learning
Learning representations of well-trained neural network models holds the promise to provide an understanding of the inner workings of those models.
Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation
The development of foundation models has revolutionized our ability to interpret the Earth's surface using satellite observational data.
Sample Weight Estimation Using Meta-Updates for Online Continual Learning
This is done by first estimating sample weight parameters for each sample in the mini-batch, then, updating the model with the adapted sample weights.
FedTabDiff: Federated Learning of Diffusion Probabilistic Models for Synthetic Mixed-Type Tabular Data Generation
Realistic synthetic tabular data generation encounters significant challenges in preserving privacy, especially when dealing with sensitive information in domains like finance and healthcare.
Parameter Efficient Self-Supervised Geospatial Domain Adaptation
As large-scale foundation models become publicly available for different domains efficiently adapting them to individual downstream applications and additional data modalities has turned into a central challenge.
Transformer-based Entity Legal Form Classification
We propose the application of Transformer-based language models for classifying entity legal forms from raw legal entity names.
FinDiff: Diffusion Models for Financial Tabular Data Generation
The sharing of microdata, such as fund holdings and derivative instruments, by regulatory institutions presents a unique challenge due to strict data confidentiality and privacy regulations.
Ben-ge: Extending BigEarthNet with Geographical and Environmental Data
Based on this dataset, we showcase the value of combining different data modalities for the downstream tasks of patch-based land-use/land-cover classification and land-use/land-cover segmentation.
Partial Hypernetworks for Continual Learning
Inspired by latent replay methods in CL, we propose partial weight generation for the final layers of a model using hypernetworks while freezing the initial layers.
Learning Emotional Representations from Imbalanced Speech Data for Speech Emotion Recognition and Emotional Text-to-Speech
Effective speech emotional representations play a key role in Speech Emotion Recognition (SER) and Emotional Text-To-Speech (TTS) tasks.
Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models
With this paper, we address that gap by applying two popular sparsification methods on populations of models (so called model zoos) to create sparsified versions of the original zoos.
Fine-grained Emotional Control of Text-To-Speech: Learning To Rank Inter- And Intra-Class Emotion Intensities
State-of-the-art Text-To-Speech (TTS) models are capable of producing high-quality speech.
Class-Incremental Learning with Repetition
We propose two stochastic stream generators that produce a wide range of CIR streams starting from a single dataset and a few interpretable control parameters.
Federated Continual Learning to Detect Accounting Anomalies in Financial Auditing
Our empirical results, using real-world datasets and combined federated continual learning strategies, demonstrate the learned model's ability to detect anomalies in audit settings of data distribution shifts.
Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights
Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation.
Model Zoos: A Dataset of Diverse Populations of Neural Network Models
With this work, we publish a novel dataset of model zoos containing systematically generated and diverse populations of NN models for further research.
RESHAPE: Explaining Accounting Anomalies in Financial Statement Audits by enhancing SHapley Additive exPlanations
However, in unsupervised DL as often applied in financial audits, these methods explain the model output at the level of encoded variables.
Federated and Privacy-Preserving Learning of Accounting Data in Financial Statement Audits
In this work, we propose a Federated Learning framework to train DL models on auditing relevant accounting data of multiple clients.
Hyper-Representations for Pre-Training and Transfer Learning
Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation.
Continual Learning for Unsupervised Anomaly Detection in Continuous Auditing of Financial Accounting Data
This work proposes a continual anomaly detection framework to overcome both challenges and designed to learn from a stream of journal entry data experiences.
Saliency Diversified Deep Ensemble for Robustness to Adversaries
We empirically show a reduced transferability between ensemble members and improved performance compared to the state-of-the-art ensemble defense against medium and high strength white-box attacks.
Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction
Self-Supervised Learning (SSL) has been shown to learn useful and information-preserving representations.
Zero-shot Voice Conversion via Self-supervised Prosody Representation Learning
We then use the learned prosodic representations as conditional information to train and enhance our VC model for zero-shot conversion.
Multi-view Contrastive Self-Supervised Learning of Accounting Data Representations for Downstream Audit Tasks
International audit standards require the direct assessment of a financial statement's underlying accounting transactions, referred to as journal entries.
Heterogeneous Ensemble for ESG Ratings Prediction
Such ratings allow them to make investment decisions in favor of sustainability.
Learning Interpretable Concept Groups in CNNs
We propose a novel training methodology -- Concept Group Learning (CGL) -- that encourages training of interpretable CNN filters by partitioning filters in each layer into concept groups, each of which is trained to learn a single visual concept.
Estimation of Air Pollution with Remote Sensing Data: Revealing Greenhouse Gas Emissions from Space
Air pollution is a major driver of climate change.
Power Plant Classification from Remote Imaging with Deep Learning
Using a ResNet-50 deep learning model, we are able to achieve a mean accuracy of 90. 0% in distinguishing 10 different power plant types and a background class.
NoiseVC: Towards High Quality Zero-Shot Voice Conversion
Voice conversion (VC) is a task that transforms voice from target audio to source without losing linguistic contents, it is challenging especially when source and target speakers are unseen during training (zero-shot VC).
Continual Speaker Adaptation for Text-to-Speech Synthesis
The naive solution of sequential fine-tuning of a model for new speakers can lead to poor performance of older speakers.
Leaking Sensitive Financial Accounting Data in Plain Sight using Deep Autoencoder Neural Networks
Nowadays, organizations collect vast quantities of sensitive information in `Enterprise Resource Planning' (ERP) systems, such as accounting relevant transactions, customer master data, or strategic sales price information.
Characterization of Industrial Smoke Plumes from Remote Sensing Data
The major driver of global warming has been identified as the anthropogenic release of greenhouse gas (GHG) emissions from industrial activities.
Using IPA-Based Tacotron for Data Efficient Cross-Lingual Speaker Adaptation and Pronunciation Enhancement
Recent neural Text-to-Speech (TTS) models have been shown to perform very well when enough data is available.
Learning Sampling in Financial Statement Audits using Vector Quantised Autoencoder Neural Networks
The audit of financial statements is designed to collect reasonable assurance that an issued statement is free from material misstatement 'true and fair presentation'.
Facial Recognition: A cross-national Survey on Public Acceptance, Privacy, and Discrimination
With rapid advances in machine learning (ML), more of this technology is being deployed into the real world interacting with us and our environment.
An Investigation of the Weight Space to Monitor the Training Progress of Neural Networks
We show that the model trajectories can be separated and the order of checkpoints on the trajectories recovered, which may serve as a first step towards DNN model versioning.
Neural Networks and Value at Risk
Utilizing a generative regime switching framework, we perform Monte-Carlo simulations of asset returns for Value at Risk threshold estimation.
Adversarial Learning of Deepfakes in Accounting
Second, we show that adversarial autoencoder neural networks are capable of learning a human interpretable model of journal entries that disentangles the entries latent generative factors.
Detection of Accounting Anomalies in the Latent Space using Adversarial Autoencoder Neural Networks
We demonstrate that such artificial neural networks are capable of learning a semantic meaningful representation of real-world journal entries.
Overcoming Missing and Incomplete Modalities with Generative Adversarial Networks for Building Footprint Segmentation
This assumption limits the applications of multi-modal models since in practice the data collection process is likely to generate data with missing, incomplete or corrupted modalities.
What do Deep Networks Like to See?
To do this, an autoencoder (AE) was fine-tuned on gradients from a pre-trained classifier with fixed parameters.
Ranked #887 on
Image Classification
on ImageNet
Adversarial Defense based on Structure-to-Signal Autoencoders
We analyze their robustness against several white-box and gray-box scenarios on the large ImageNet dataset.
Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks
In this paper, we address the problem of preserving semantic segmentation boundaries in high resolution satellite imagery by introducing a new cascaded multi-task loss.
Detection of Anomalies in Large Scale Accounting Data using Deep Autoencoder Networks
Learning to detect fraud in large-scale accounting data is one of the long-standing challenges in financial statement audits or fraud investigations.
EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification
We present a novel dataset based on Sentinel-2 satellite images covering 13 spectral bands and consisting out of 10 classes with in total 27, 000 labeled and geo-referenced images.
An Evolutionary Algorithm to Learn SPARQL Queries for Source-Target-Pairs: Finding Patterns for Human Associations in DBpedia
We show the scalability of the algorithm by running it against a SPARQL endpoint loaded with > 7. 9 billion triples.
AudioPairBank: Towards A Large-Scale Tag-Pair-Based Audio Content Analysis
One contribution is the previously unavailable documentation of the challenges and implications of collecting audio recordings with these type of labels.
Mapping Images to Sentiment Adjective Noun Pairs with Factorized Neural Nets
We consider the visual sentiment task of mapping an image to an adjective noun pair (ANP) such as "cute baby".
The YLI-MED Corpus: Characteristics, Procedures, and Plans
The YLI Multimedia Event Detection corpus is a public-domain index of videos with annotations and computed features, specialized for research in multimedia event detection (MED), i. e., automatically identifying what's happening in a video by analyzing the audio and visual content.
YFCC100M: The New Data in Multimedia Research
We present the Yahoo Flickr Creative Commons 100 Million Dataset (YFCC100M), the largest public multimedia collection that has ever been released.
Multimedia Computers and Society H.3.7
Large-Scale Deep Learning on the YFCC100M Dataset
We train our three-layer deep neural network on the Yahoo!
DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks
Nearly one million Flickr images tagged with these ANPs are downloaded to train the classifiers of the concepts.
