BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Copenhagen BEGIN:DAYLIGHT DTSTART:20260329T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20251026T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20251210T140355Z UID:87E3239B-1C4D-4735-A540-D56FA965D238 DTSTART;TZID=Europe/Copenhagen:20251219T150000 DTEND;TZID=Europe/Copenhagen:20251219T200000 DESCRIPTION:Graph Neural Networks (GNNs) have emerged as a powerful paradig m for learning from complex graph-structured data\, yet their opaque decis ion processes hinder trustworthy deployment in high-stakes applications. T his dissertation advances the foundations of explainable and reliable GNN reasoning through four interrelated studies\, forming a cohesive framework for interpretable\, robust\, and multi-faceted GNN explanations. Together \, these works bridge theoretical understanding\, algorithmic development\ , and practical evaluation of GNN explainability.\n\nCo-sponsored by: Sean Bin Yang\n\nSpeaker(s): Dazhuo Qiu\n\nVirtual: https://events.vtools.ieee .org/m/521262 LOCATION:Virtual: https://events.vtools.ieee.org/m/521262 ORGANIZER:seany@cs.aau.dk SEQUENCE:12 SUMMARY:PhD. defense at the Department of Computer Science\, Aalborg Univer sity URL;VALUE=URI:https://events.vtools.ieee.org/m/521262 X-ALT-DESC:Description: <br /><p>Graph Neural Networks (GNNs) have emerged as a powerful paradigm for learning from complex graph-structured data\, y et their opaque decision processes hinder trustworthy deployment in high-s takes applications. This dissertation advances the foundations of explaina ble and reliable GNN reasoning through four interrelated studies\, forming a cohesive framework for interpretable\, robust\, and multi-faceted GNN e xplanations. Together\, these works bridge theoretical understanding\, alg orithmic development\, and practical evaluation of GNN explainability.</p> END:VEVENT END:VCALENDAR