Master Thesis Open Access
Cung, Yee-Ying Christina
<?xml version='1.0' encoding='UTF-8'?> <record xmlns="http://www.loc.gov/MARC21/slim"> <leader>00000nam##2200000uu#4500</leader> <datafield tag="909" ind1="C" ind2="O"> <subfield code="o">oai:publish.etp.kit.edu:22148</subfield> <subfield code="p">user-cms</subfield> <subfield code="p">user-etp</subfield> </datafield> <datafield tag="542" ind1=" " ind2=" "> <subfield code="l">open</subfield> </datafield> <datafield tag="520" ind1=" " ind2=" "> <subfield code="a"><p>Graph neural networks (GNNs) are a novel machine learning technique dedicated to processing graph data. In fact, a lot of high energy physics data can be more naturally represented by graphs rather than, for instance, by vectors, which deep neural networks (DNNs) use. This applies to <span class="math-tex">\(\text{t}\bar{\text{t}}+\text{b}\bar{\text{b}}\)</span>, <span class="math-tex">\(\text{t}\bar{\text{t}}\text{H}(\text{b}\bar{\text{b}})\)</span> and <span class="math-tex">\(\text{t}\bar{\text{t}}\text{Z}(\text{b}\bar{\text{b}})\)</span> processes as well, which are irreducible backgrounds to each other and need to be separated with high efficiency due to the importance of each process in itself. Therefore, GNNs are presumably a promising approach for this classification task. To validate this assumption, the general feasibility of GNNs for multivariate <span class="math-tex">\(\text{t}\bar{\text{t}}+\text{X}\)</span> event classification as well as their reliability are examined. The studies are concluded with comparisons between GNNs and DNNs under fair conditions.</p></subfield> </datafield> <datafield tag="700" ind1=" " ind2=" "> <subfield code="a">Husemann, Ulrich</subfield> <subfield code="u">KIT/ETP</subfield> <subfield code="4">ths</subfield> </datafield> <datafield tag="700" ind1=" " ind2=" "> <subfield code="a">Wolf, Roger</subfield> <subfield code="u">KIT/ETP</subfield> <subfield code="4">ths</subfield> </datafield> <datafield tag="700" ind1=" " ind2=" "> <subfield code="a">Pfeffer, Emanuel</subfield> <subfield code="u">KIT/ETP</subfield> <subfield code="4">ths</subfield> </datafield> <controlfield tag="001">22148</controlfield> <datafield tag="260" ind1=" " ind2=" "> <subfield code="c">2022-12-06</subfield> </datafield> <datafield tag="980" ind1=" " ind2=" "> <subfield code="a">thesis</subfield> <subfield code="b">master-thesis</subfield> </datafield> <datafield tag="100" ind1=" " ind2=" "> <subfield code="a">Cung, Yee-Ying Christina</subfield> <subfield code="u">KIT/ETP</subfield> </datafield> <datafield tag="980" ind1=" " ind2=" "> <subfield code="a">user-cms</subfield> </datafield> <datafield tag="980" ind1=" " ind2=" "> <subfield code="a">user-etp</subfield> </datafield> <controlfield tag="005">20230110071653.0</controlfield> <datafield tag="245" ind1=" " ind2=" "> <subfield code="a">Feasibility and Reliability Studies of Graph Neural Networks for Multivariate tt+X Event Classification at the CMS Experiment at CERN</subfield> </datafield> <datafield tag="856" ind1="4" ind2=" "> <subfield code="s">7497788</subfield> <subfield code="u">https://publish.etp.kit.edu/record/22148/files/Master_Thesis_YC.pdf</subfield> <subfield code="z">md5:dd28a09d9aa4d46e269b76645501e62e</subfield> </datafield> <datafield tag="653" ind1=" " ind2=" "> <subfield code="a">Machine Learning</subfield> </datafield> <datafield tag="653" ind1=" " ind2=" "> <subfield code="a">Graph Neural Network</subfield> </datafield> <datafield tag="653" ind1=" " ind2=" "> <subfield code="a">Deep Neural Network</subfield> </datafield> <datafield tag="653" ind1=" " ind2=" "> <subfield code="a">Explainable AI</subfield> </datafield> <datafield tag="653" ind1=" " ind2=" "> <subfield code="a">GNNExplainer</subfield> </datafield> <datafield tag="653" ind1=" " ind2=" "> <subfield code="a">Taylor Coefficient Analysis</subfield> </datafield> <datafield tag="653" ind1=" " ind2=" "> <subfield code="a">Multivariate Classification</subfield> </datafield> <datafield tag="653" ind1=" " ind2=" "> <subfield code="a">GNN</subfield> </datafield> <datafield tag="653" ind1=" " ind2=" "> <subfield code="a">DNN</subfield> </datafield> </record>