Research
- Research Topics
- Cell Biology and Tumor Biology
- Stem Cells and Cancer
- Inflammatory Stress in Stem Cells
- Experimental Hematology
- Molecular Embryology
- Signal Transduction and Growth Control
- Epigenetics
- Redox Regulation
- Vascular Oncology and Metastasis
- Clinical Neurobiology
- Molecular Neurogenetics
- Molecular Neurobiology
- Mechanisms Regulating Gene Expression
- Molecular Biology of Centrosomes and Cilia
- Dermato-Oncology
- Pediatric Leukemia
- Tumour Metabolism and Microenvironment
- Personalized Medical Oncology
- Molecular Hematology - Oncology
- Cancer Progression and Metastasis
- Translational Surgical Oncology
- Neuronal Signaling and Morphogenesis
- Cell Signaling and Metabolism
- Cell Fate Engineering and Disease Modeling
- Cancer Drug Development
- Cell Morphogenesis and Signal Transduction
- Functional and Structural Genomics
- Molecular Genome Analysis
- Molecular Genetics
- Pediatric Neurooncology
- Cancer Genome Research
- Chromatin Networks
- Functional Genome Analysis
- Theoretical Systems Biology
- Neuroblastoma Genomics
- Signaling and Functional Genomics
- Signal Transduction in Cancer and Metabolism
- RNA-Protein Complexes and Cell Proliferation
- Systems Biology of Signal Transduction
- Areas of Interest
- Advancement of clinical proteomics for systems medicine
- Bridging from the single cell to the cell population – Epo-induced cellular responses and erythroleukemia
- Deciphering tumor microenvironment interactions determining lung cancer development
- Mechanisms controlling the compensation of liver injury and towards model-based biomarkers for early detection of liver cancer
- Application of dynamic pathway modelling for personalized medicine
- Group Members
- Publications
- Open Positions
- Funding
- Teaching
- Areas of Interest
- Molecular thoracic Oncology
- Proteomics of Stem Cells and Cancer
- Computational Genomics and System Genetics
- Applied Functional Genomics
- Applied Bioinformatics
- Translational Medical Oncology
- Metabolic crosstalk in cancer
- Pediatric Glioma Research
- Cancer Epigenomics
- Translational Pediatric Sarcoma Research
- Artificial Intelligence in Oncology
- Mechanisms of Genomic Variation and Data Science
- Neuropathology
- Pediatric Oncology
- Neurooncology
- Somatic Evolution and Early Detection
- Translational Control and Metabolism
- Soft-Tissue Sarcoma
- Precision Sarcoma Research
- Brain Mosaicism and Tumorigenesis
- Mechanisms of Genome Control
- Translational Gastrointestinal Oncology and Preclinical Models
- Translational Lymphoma Research
- Mechanisms of Leukemogenesis
- Genome Instability in Tumors
- Developmental Origins of Pediatric Cancer
- Brain Tumor Translational Targets
- Translational Functional Cancer Genomics
- Regulatory Genomics and Cancer Evolution
- SPRINT
- Cancer Risk Factors and Prevention
- Cancer Epidemiology
- Biostatistics
- Clinical Epidemiology and Aging Research
- Health Economics
- Physical Activity, Prevention and Cancer
- Primary Cancer Prevention
- Personalized Early Detection of Prostate Cancer
- Digital prevention, diagnostics and therapy guidance
- Policy and Implementation Research for Cancer Prevention
- Tumorigenesis and molecular cancer prevention
- Genomic Epidemiology
- Cancer Survivorship
- Immunology, Infection and Cancer
- Structural Biology of Infection and Immunity
- Cellular Immunology
- B Cell Immunology
- Immune Diversity
- Immunoproteomics
- Personalized Immunotherapy
- mRNA Cancer Immunotherapies
- Tumor Immunology and Tumor Immunotherapy
- Infections and Cancer Epidemiology
- Pathogenesis of Virus-Associated Tumors
- Immunotherapy and Immunoprevention
- Virus-associated Carcinogenesis
- Chronic Inflammation and Cancer
- Microbiome and Cancer
- Molecular Oncology of Gastrointestinal Tumors
- Applied Tumor Immunity
- Neuroimmunology and Brain Tumor Immunology
- Applied Tumor Biology
- Virotherapy
- Adaptive Immunity and Lymphoma
- Dermal Oncoimmunology
- Immune Regulation in Cancer
- Systems Immunology and Single Cell Biology
- Pediatric Immuno-Oncology
- Epithelium Microbiome lnteractions
- Experimental Hepatology, Inflammation and Cancer
- GMP & T Cell Therapy
- Tumorvirus-specific Vaccination Strategies
- Mammalian Cell Cycle Control Mechanisms
- Molecular Therapy of Virus-Associated Cancers
- DNA Vectors
- Episomal-Persistent DNA in Cancer- and Chronic Diseases
- Immune Monitoring
- News
- Imaging and Radiooncology
- Radiology
- Research
- Computational Radiology Research Group
- Contrast Agents In Radiology Research Group
- Neuro-Oncologic Imaging Research Group
- Radiological Early Response Assessment Of Modern Cancer Therapies
- Imaging In Monoclonal Plasma Cell Disorders
- 7 Tesla MRI - Novel Imaging Biomarkers
- Functional Imaging
- Visualization And Forensic Imaging
- PET/MRI
- Dual- and Multienergy CT
- Radiomics Research Group
- Prostate Research Group
- Bone marrow
- Musculoskeletal Imaging
- Microstructural Imaging Research Group
- Staff
- Patients
- Research
- Medical Physics in Radiology
- X-Ray Imaging and Computed Tomography
- Federated Information Systems
- Translational Molecular Imaging
- Medical Physics in Radiation Oncology
- Biomedical Physics in Radiation Oncology
- Intelligent Medical Systems
- Medical Image Computing
- Radiooncology - Radiobiology
- Smart Technologies for Tumor Therapy
- Team
- Research
- Microrobots and Miniaturize Devices for Minimally-invasive Surgery
- Magnetic localization and sensing for biomedical devices
- Nanorobots for Targeted Delivery in Deep Biological Tissues
- 3D Additive Manufacturing of Soft Materials as In Vitro Tumor Models
- Surgical Simulation on Cyber-physical Organ Models
- News
- Vacancies
- Radiation Oncology
- Molecular Radiooncology
- Nuclear Medicine
- Translational Radiation Oncology
- Translational Radiotheranostics
- Interactive Machine Learning
- Intelligent Systems and Robotics in Urology
- Multiparametric methods for early detection of prostate cancer
- Translational Molecular Imaging in Oncologic Therapy Monitoring
- Radiology
- Cell Biology and Tumor Biology
- Research Groups A-Z
- Junior Research Groups
- Core Facilities
- News
- List of Core Facilities
- Antibodies
- Cellular Tools
- Center for Preclinical Research
- Central Library
- Chemical Biology
- Dieter Morszeck Biorepository
- Electron Microscopy
- Flow Cytometry
- Information Technology ITCF
- Light Microscopy
- Metabolomics
- Microarray
- Microbiological Diagnostics
- Next Generation Sequencing
- Omics IT and Data Management
- Proteomics
- Radiopharmaceuticals and Preclinical Trials
- Single-cell Open Lab
- Small Animal Imaging
- Transgenic Service
- Tumor Models
- OMERO@DKFZ
- List of Technologies
- DKFZ Core Facilities Publication Policy
- Enabling Technology
- Data Science @ DKFZ
- INFORM
- Baden-Württemberg Cancer Registry
- Cooperations & Networks
- National Cooperations
- International Cooperations
- Cooperational Research Program with Israel: DKFZ - MOST in Cancer Research
- Program
- Members of the Program Committee
- Call
- Publication Database
- German-Israeli Cancer Research Schools
- Archive
- Heidelberg - Israel, Science and Culture
- Symposium 40 Years of German-Israeli Cooperation
- 35th Anniversary Symposium
- 34th Meeting of the DKFZ-MOST Program
- 40th Anniversary Publication
- 30th Anniversary Publication
- 20th Anniversary Publication
- Flyer - The Cancer Cooperation Program
- List Publications 1976-2004
- Highlight-Projects
- Cooperational Research Program with Israel: DKFZ - MOST in Cancer Research
- Cooperations with industrial companies
- DKFZ PostDoc Network
- Cross Program Topic RNA@DKFZ
- Cross Program Topic Epigenetics@dkfz
- Cross Program Topic Single Cell Sequencing
- WHO Collaborating Centers
- DKFZ Site Dresden
- Health + Life Science Alliance Heidelberg Mannheim
Learning Equivariant and Hybrid Message Passing on Graphs
In this talk I will extend graph neural nets in two directions. First, we will ask if we can formulate a GNN on meshes of two dimensional manifolds. Previous approaches mostly used standard GNNs which are invariant to permutations of the input nodes. However, we show this is unnecessarily restrictive. Instead, we define mesh-CNNs which are equivariant and allow more general kernels. Second we will study how to incorporate information about the data generating process into GNNs. Belief propagation is a form of GNN with no learnable parameters that performs inference in a generative graphical model. We subsequently augment BP by a trainable GNN to correct the mistakes of BP, in order to improve predictive performance. Experiments show the increased power of both methods.
Wednesday, 6th Mai 2020, 11 am
live streaming link: https://www.conf.dfn.de/stream/nr5h8pp6e87k3
Biosketch Dr. Max Welling
Prof. Dr. Max Welling is a research chair in Machine Learning at the University of Amsterdam and a VP Technologies at Qualcomm. He has a secondary appointment as a senior fellow at the Canadian Institute for Advanced Research (CIFAR). He is co-founder of “Scyfer BV” a university spin-off in deep learning which got acquired by Qualcomm in summer 2017. In the past he held postdoctoral positions at Caltech (’98-’00), UCL (’00-’01) and the U. Toronto (’01-’03). He received his PhD in ’98 under supervision of Nobel laureate Prof. G. ‘t Hooft. Max Welling has served as associate editor in chief of IEEE TPAMI from 2011-2015 (impact factor 4.8). He serves on the board of the NIPS foundation since 2015 (the largest conference in machine learning) and has been program chair and general chair of NIPS in 2013 and 2014 respectively. He was also program chair of AISTATS in 2009 and ECCV in 2016 and general chair of MIDL 2018. He has served on the editorial boards of JMLR and JML and was an associate editor for Neurocomputing, JCGS and TPAMI. He received multiple grants from Google, Facebook, Yahoo, NSF, NIH, NWO and ONR-MURI among which an NSF career grant in 2005. He is recipient of the ECCV Koenderink Prize in 2010. Welling is in the board of the Data Science Research Center in Amsterdam, he directs the Amsterdam Machine Learning Lab (AMLAB), and co-directs the Qualcomm-UvA deep learning lab (QUVA) and the Bosch-UvA Deep Learning lab (DELTA). Max Welling has over 250 scientific publications in machine learning, computer vision, statistics and physics and an h-index of 62.
Joint event with heidelberg.ai