Search Results for author: Berthold Reinwald

Found 9 papers, 1 papers with code

Declarative Machine Learning - A Classification of Basic Properties and Types

no code implementations19 May 2016 Matthias Boehm, Alexandre V. Evfimievski, Niketan Pansare, Berthold Reinwald

Specification alternatives range from ML algorithms expressed in domain-specific languages (DSLs) with optimization for performance, to ML task (learning problem) specifications with optimization for performance and accuracy.

BIG-bench Machine Learning Classification +1

Deep Learning with Apache SystemML

no code implementations8 Feb 2018 Niketan Pansare, Michael Dusenberry, Nakul Jindal, Matthias Boehm, Berthold Reinwald, Prithviraj Sen

Enterprises operate large data lakes using Hadoop and Spark frameworks that (1) run a plethora of tools to automate powerful data preparation/transformation pipelines, (2) run on shared, large clusters to (3) perform many different analytics tasks ranging from model preparation, building, evaluation, and tuning for both machine learning and deep learning.

BIG-bench Machine Learning

Fine Grained Classification of Personal Data Entities

no code implementations23 Nov 2018 Riddhiman Dasgupta, Balaji Ganesan, Aswin Kannan, Berthold Reinwald, Arun Kumar

Entity Type Classification can be defined as the task of assigning category labels to entity mentions in documents.

Classification General Classification

A Neural Architecture for Person Ontology population

no code implementations22 Jan 2020 Balaji Ganesan, Riddhiman Dasgupta, Akshay Parekh, Hima Patel, Berthold Reinwald

A person ontology comprising concepts, attributes and relationships of people has a number of applications in data protection, didentification, population of knowledge graphs for business intelligence and fraud prevention.

Classification General Classification +3

Forecasting in multivariate irregularly sampled time series with missing values

no code implementations6 Apr 2020 Shivam Srivastava, Prithviraj Sen, Berthold Reinwald

Sparse and irregularly sampled multivariate time series are common in clinical, climate, financial and many other domains.

General Classification Irregular Time Series +3

Knowledge Graph Embedding using Graph Convolutional Networks with Relation-Aware Attention

no code implementations14 Feb 2021 Nasrullah Sheikh, Xiao Qin, Berthold Reinwald, Christoph Miksovic, Thomas Gschwind, Paolo Scotton

Knowledge graph embedding methods learn embeddings of entities and relations in a low dimensional space which can be used for various downstream machine learning tasks such as link prediction and entity matching.

Graph Attention Knowledge Graph Embedding +2

Relation-aware Graph Attention Model With Adaptive Self-adversarial Training

no code implementations14 Feb 2021 Xiao Qin, Nasrullah Sheikh, Berthold Reinwald, Lingfei Wu

Furthermore, the expressivity of the learned representation depends on the quality of negative samples used during training.

Attribute Entity Embeddings +3

Scaling Knowledge Graph Embedding Models

no code implementations8 Jan 2022 Nasrullah Sheikh, Xiao Qin, Berthold Reinwald, Chuan Lei

Developing scalable solutions for training Graph Neural Networks (GNNs) for link prediction tasks is challenging due to the high data dependencies which entail high computational cost and huge memory footprint.

Knowledge Graph Embedding Link Prediction

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