Open Topics

We offer multiple Bachelor/Master theses, Guided Research projects and IDPs in the area of data mining/machine learning. A non-exhaustive list of open topics is listed below.

If you are interested in a thesis or a guided research project, please send your CV and transcript of records to Prof. Stephan Günnemann via email and we will arrange a meeting to talk about the potential topics.

Deep Generative Models for Graphs

Type: Master's thesis / guided research

Prerequisites:

  • Strong machine learning knowledge
  • Proficiency with deep learning frameworks (Tensorflow or Pytorch)
  • Experience with deep generative models (e.g. having implemented variational autoencoder, generative adversarial networks)
  • Knowledge of graph generative models (e.g. stochastic block model)

Description: 

Generative models are a key instrument in analyzing graphs and networks, with applications in biology, chemistry and social sciences. Deep generative models (e.g. variational autoencoders and generative adversarial networks) allow to learn distributions over complex domains such as images. Despite their success in the context of vector data (images, point clouds), developing deep generative models for graphs and networks remains an important open research problem. Various properties of graphs (e.g. discreteness, permutation invariance, large output space) pose challenges and require development of new techniques.

References:

  1. NetGAN: Generating Graphs via Random Walks
  2. Variational Graph Auto-Encoders
  3. GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Model
  4. Learning Deep Generative Models of Graphs

 

Graph Neural Networks

Type: Master's thesis / Bachelor's thesis / guided research

Prerequisites:

  • Strong machine learning knowledge
  • Proficiency with Python and deep learning frameworks (TensorFlow or PyTorch)
  • Knowledge of graph neural networks (e.g. GCN, MPNN)
  • Knowledge of graph/network theory

Description:

Graph neural networks (GNNs) have recently achieved great successes in a wide variety of applications, such as chemistry, reinforcement learning, knowledge graphs, traffic networks, or computer vision. These models leverage graph data by updating node representations based on messages passed between nodes connected by edges, or by transforming node representation using spectral graph properties. These approaches are very effective, but many theoretical aspects of these models remain unclear and there are many possible extensions to improve GNNs and go beyond the nodes' direct neighbors and simple message aggregation.

Contact: Johannes Klicpera

References:

  1. Semi-supervised classification with graph convolutional networks
  2. Relational inductive biases, deep learning, and graph networks
  3. Diffusion Improves Graph Learning
  4. Weisfeiler and leman go neural: Higher-order graph neural networks

 

Deep Learning for Molecules

Type: Master's thesis / guided research

Prerequisites:

  • Strong machine learning knowledge
  • Proficiency with Python and deep learning frameworks (TensorFlow or PyTorch)
  • Knowledge of graph neural networks (e.g. GCN, SchNet)
  • Optional: Knowledge of machine learning on molecules and quantum chemistry

Description:

Deep learning models, especially graph neural networks (GNNs), have recently achieved great successes in predicting quantum mechanical properties of molecules. There is a vast amount of applications for these models, such as finding the best method of chemical synthesis or selecting candidates for drugs, construction materials, batteries, or solar cells. However, most of these models have only been proposed in recent years and there remain many open questions, such as the best way of representing the molecular structure, incorporating physical properties, exploring the chemical space of molecules, integrating long-range interactions, or predicting non-equilibrium molecule states and transitions.

Contact: Johannes Klicpera

References:

  1. Directional Message Passing for Molecular Graphs
  2. SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
  3. Neural message passing for quantum chemistry
  4. Cormorant: Covariant Molecular Neural Networks

 

Robustness Verification for Deep Classifiers

Type: Master's thesis / Guided research

Prerequisites:

  • Strong machine learning knowledge (at least equivalent to IN2064 plus an advanced course on deep learning)
  • Strong background in mathematical optimization (preferably combined with Machine Learning setting)
  • Proficiency with python and deep learning frameworks (Tensorflow or Pytorch)
  • (Preferred) Knowledge of training techniques to obtain classifiers that are robust against small perturbations in data

Description: Recent work shows that deep classifiers suffer under presence of adversarial examples: misclassified points that are very close to the training samples or even visually indistinguishable from them. This undesired behaviour constraints possibilities of deployment in safety critical scenarios for promising classification methods based on neural nets. Therefore, new training methods should be proposed that promote (or preferably ensure) robust behaviour of the classifier around training samples.

Contact: Aleksei Kuvshinov

References (Background):

  1. Intriguing properties of neural networks
  2. Explaining and harnessing adversarial examples

References:

  1. Certified Adversarial Robustness via Randomized Smoothing
  2. Formal guarantees on the robustness of a classifier against adversarial manipulation
  3. Towards deep learning models resistant to adversarial attacks
  4. Provable defenses against adversarial examples via the convex outer adversarial polytope
  5. Certified defenses against adversarial examples
  6. Lipschitz-margin training: Scalable certification of perturbation invariance for deep neural networks
  7. Provable robustness of relu networks via maximization of linear regions

 

Anomaly detection in dynamic networks

Type: Interdisciplinary project (IDP)

Prerequisites:

  • Strong machine learning knowledge
  • Good programming skills
  • (Preferred) experience with probabilistic graphical models (e.g. stochastic block model)
  • (Preferred) experience with node embedding methods (e.g. DeepWalk, node2vec)

Description: The growing complexity of communication networks makes their analysis and maintenance increasingly challenging for human administrators. For example, campus, home, and enterprise computer networks all suffer from badly secured Internet of Things (IoT) devices, hacker attacks or simply outdated software. Developing automated tools for detection, analysis and mitigation of anomalies (e.g. hardware failures or security threats) in such networks is both an open research problem and an important practical challenge. 

In this IDP, you will work together with the Chair of Communication Networks and our group on developing machine learning models for anomaly detection in dynamic communication networks. You will use methods such as node embedding methods [1], probabilistic graphical models [2] or community detection algorithms [3].

Contact: Patrick Kalmbach

References:

  1. DeepWalk: Online Learning of Social Representations
  2. Statistical clustering of temporal networks through a dynamic stochastic block model
  3. An efficient and principled method for detecting communities in networks