Institute for AI<p>Advances in temporal graph reasoning to be presented at <a href="https://xn--baw-joa.social/tags/ECAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ECAI</span></a></p><p>Researchers from the AI Institute at the University of Stuttgart <span class="h-card" translate="no"><a href="https://xn--baw-joa.social/@Uni_Stuttgart" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>Uni_Stuttgart</span></a></span> will present a paper tackling key challenges in temporal graph learning. The work, titled “Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning,” will be presented at <a href="https://xn--baw-joa.social/tags/ECAI2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ECAI2025</span></a>, a premier conference in artificial intelligence.</p><p>Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning</p><p>Temporal graphs are key to understanding dynamic systems—from traffic flow to financial fraud. ETDNet introduces a dual-branch temporal graph neural network that decouples spatial (intra-frame) and temporal (inter-frame) edges.</p><p>This design avoids over-smoothing and allows effective long-range reasoning. ETDNet improves driver-intention prediction (75.6% joint accuracy on Waymo) and illicit-transfer detection (88.1% F1 on Elliptic++), while outperforming transformers and memory-bank baselines with fewer parameters and faster training.</p><p>O. Mohammed (<span class="h-card" translate="no"><a href="https://mastodon.social/@osamamohammed" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>osamamohammed</span></a></span>), J. Pan, M. Nayyeri, D. Hernández (<span class="h-card" translate="no"><a href="https://mstdn.degu.cl/@daniel" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>daniel</span></a></span>), S. Staab. Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning. Proceedings of the 28th European Conference on Artificial Intelligence (ECAI2025). <a href="https://arxiv.org/abs/2508.03251" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2508.03251</span><span class="invisible"></span></a></p><p><a href="https://xn--baw-joa.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://xn--baw-joa.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://xn--baw-joa.social/tags/TemporalGraphs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TemporalGraphs</span></a> <a href="https://xn--baw-joa.social/tags/TemporalReasoning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TemporalReasoning</span></a> <a href="https://xn--baw-joa.social/tags/ECAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ECAI</span></a></p>