We are regularly looking for student assistants and offer HiWi activities at our Chair as well as in the Research Area Smart Data & Knowledge Services (SDS) at the DFKI. If you are interested, simply ask - even if no position is officially announced!
Context-Aware Recommender Systems for Personal Knowledge Assistants
- context-aware recommender systems
- graph embedding
- information retrieval
- knowledge worker actions and scenarios detection
- personal information management
- re-finding agents
One of the ways to assist knowledge workers in the daily tasks and improve their productivity is by providing them with relevant helpful information based on their current context. There are many challenges in developing such a recommender system which could be capable of recommending the right information at the right time to the right person. Understanding the contextual state of the users as precisely as possible, along with detecting their activities and information need play a significant role in enhancing the context-aware recommender systems for personal knowledge assistants. A mixture of knowledge and skills in various fields such as information retrieval, graph embedding, and machine learning is needed to tackle the existing challenges in this area.
Text Mining / Parallel Data Processing
- Information Extraction
- Knowledge Graphs
- Large Scale Data Processing
- Natural Language Processing
- Web Crawling
Crawling large amounts of websites and web archives requires large scale data processing technologies, like parallel computing in the cloud (e.g. with PySpark). Various NLP tools then are used to automatically extract and classify important keywords from the crawled text, to build knowledge graphs or to classify the document as a whole. A major challenge here is to deal with inconsistencies and ambiguities in human language, written text and faulty HTML code.
Diffusion Models for Super-Resolution
- Deep Learning
- Denoising Diffusion Probabilistic Models
- Single Image Super-Resolution
Denoising Diffusion Probabilistic Models (DDPMs) or Diffusion Models
(https://arxiv.org/abs/2006.11239, https://arxiv.org/abs/2102.09672) became famous with tools like Dall-E and Stable Diffusion.
Unfortunately, many novel approaches require tremendous GPU power and memory. We want to change that by exploring new ways of optimization w.r.t. architecture, time step modifications and analysis of given methods. The application field of the DDPMs will be Single Image Super-Resolution.
Additional Sources: https://arxiv.org/abs/2104.07636 https://arxiv.org/abs/2104.14951 https://arxiv.org/abs/2112.02475 https://arxiv.org/abs/2111.05826 https://arxiv.org/abs/2108.02938
Graph Extraction/Generation from Diagrams
- dynamic system simulation
I am currently supervising students in multiple topics related to the extraction and simulation of Graph-Based Engineering Drawings from optical sources: Graph Extraction from Printed/Handdrawn Circuit Diagrams/Piping&Instumentation Diagrams, Generation of Hand-Drawn Diagrams, Interactive Circuit Detection and Simulation
Efficient & data type independent CUDA kernels
- ptx assembly
With typical GPU code all operands must have the same data type. However, the speed of most operations on GPUs is limited not by computation, but by memory bandwidth and latency. In these cases using the smallest possible data types can greatly enhance performance. The standard approach of compiling one version of a kernel for each combination inputs is infeasible though, since the number of combinations, especially for 3 or more inputs, leads to exorbitantly large binaries and very long compilation times. Much more desirable is a flexible kernel that can load inputs of arbitrary data type and converts them to an intermediate representation that can be used to perform the actual computation.
Note: This topic is highly specialized and requires deep knowledge in CUDA C++ programming and PTX assembly. Please only apply if you have previously worked with those languages.
Learning Analytics in Education
- affective state
- cognitive state
- deep learning
- machine learning
Construction & Application of Enterprise Knowledge Graphs in the E-Invoicing Domain
- knowledge graphs
- knowledge services
- linked data
- semantic web
In recent years knowledge graphs received a lot of attention as well in industry as in science. Knowledge graphs consist of entities and relationships between them and allow integrating new knowledge arbitrarily. Famous instances in industry are knowledge graphs by Microsoft, Google, Facebook or IBM. But beyond these ones, knowledge graphs are also adopted in more domain specific scenarios such as in e-Procurement, e-Invoicing and purchase-to-pay processes. The objective in theses and projects is to explore particular aspects of constructing and/or applying knowledge graphs in the domain of purchase-to-pay processes and e-Invoicing.