{"id":1382,"date":"2024-01-01T20:34:56","date_gmt":"2024-01-01T19:34:56","guid":{"rendered":"http:\/\/pages.di.unipi.it\/bacciu\/?page_id=1382"},"modified":"2024-01-02T11:19:07","modified_gmt":"2024-01-02T10:19:07","slug":"conferences-workshops","status":"publish","type":"page","link":"https:\/\/pages.di.unipi.it\/bacciu\/publications\/conferences-workshops\/","title":{"rendered":"Conferences & Workshops"},"content":{"rendered":"\n

<\/a><\/form>
149 entries<\/span> «<\/a> ‹<\/a> 1 of 3 ›<\/a> »<\/a> <\/div><\/div>

2024<\/h3>
1.<\/div>

Gravina, Alessio; Zambon, Daniele; Bacciu, Davide; Alippi, Cesare<\/p>

Temporal Graph ODEs for Irregularly-Sampled Time Series<\/a> Conference<\/span> <\/p>

Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI 2024), <\/span>2024<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@conference{nokey,
\r\ntitle = {Temporal Graph ODEs for Irregularly-Sampled Time Series},
\r\nauthor = {Alessio Gravina and Daniele Zambon and Davide Bacciu and Cesare Alippi},
\r\nurl = {https:\/\/arxiv.org\/abs\/2404.19508, Arxiv},
\r\nyear  = {2024},
\r\ndate = {2024-08-09},
\r\nurldate = {2024-08-09},
\r\nbooktitle = {Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI 2024)},
\r\nabstract = {Modern graph representation learning works mostly under the assumption of dealing with regularly sampled temporal graph snapshots, which is far from realistic, e.g., social networks and physical systems are characterized by continuous dynamics and sporadic observations. To address this limitation, we introduce the Temporal Graph Ordinary Differential Equation (TG-ODE) framework, which learns both the temporal and spatial dynamics from graph streams where the intervals between observations are not regularly spaced. We empirically validate the proposed approach on several graph benchmarks, showing that TG-ODE can achieve state-of-the-art performance in irregular graph stream tasks.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {conference}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>
Modern graph representation learning works mostly under the assumption of dealing with regularly sampled temporal graph snapshots, which is far from realistic, e.g., social networks and physical systems are characterized by continuous dynamics and sporadic observations. To address this limitation, we introduce the Temporal Graph Ordinary Differential Equation (TG-ODE) framework, which learns both the temporal and spatial dynamics from graph streams where the intervals between observations are not regularly spaced. We empirically validate the proposed approach on several graph benchmarks, showing that TG-ODE can achieve state-of-the-art performance in irregular graph stream tasks.<\/div>
Close<\/a><\/p><\/div>