Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Lovisotto, Giulio"'
Learning Continuous-Time Dynamic Graphs (C-TDGs) requires accurately modeling spatio-temporal information on streams of irregularly sampled events. While many methods have been proposed recently, we find that most message passing-, recurrent- or self
Externí odkaz:
http://arxiv.org/abs/2406.02740
Anomaly detection in continuous-time dynamic graphs is an emerging field yet under-explored in the context of learning algorithms. In this paper, we pioneer structured analyses of link-level anomalies and graph representation learning for identifying
Externí odkaz:
http://arxiv.org/abs/2405.18050
Graph Neural Networks (GNNs) are well-suited for learning on homophilous graphs, i.e., graphs in which edges tend to connect nodes of the same type. Yet, achievement of consistent GNN performance on heterophilous graphs remains an open research probl
Externí odkaz:
http://arxiv.org/abs/2304.10896
Graph Neural Networks (GNNs) achieve state-of-the-art performance on graph-structured data across numerous domains. Their underlying ability to represent nodes as summaries of their vicinities has proven effective for homophilous graphs in particular
Externí odkaz:
http://arxiv.org/abs/2212.13202
Autor:
Lovisotto, Giulio, Finnie, Nicole, Munoz, Mauricio, Mummadi, Chaithanya Kumar, Metzen, Jan Hendrik
Neural architectures based on attention such as vision transformers are revolutionizing image recognition. Their main benefit is that attention allows reasoning about all parts of a scene jointly. In this paper, we show how the global reasoning of (s
Externí odkaz:
http://arxiv.org/abs/2203.13639
In this paper, we present AltVoice -- a system designed to help user's protect their privacy when using remotely accessed voice services. The system allows a user to conceal their true voice identity information with no cooperation from the remote vo
Externí odkaz:
http://arxiv.org/abs/2202.06278
In this paper, we investigate common pitfalls affecting the evaluation of authentication systems based on touch dynamics. We consider different factors that lead to misrepresented performance, are incompatible with stated system and threat models or
Externí odkaz:
http://arxiv.org/abs/2201.10606
As collaborative learning and the outsourcing of data collection become more common, malicious actors (or agents) which attempt to manipulate the learning process face an additional obstacle as they compete with each other. In backdoor attacks, where
Externí odkaz:
http://arxiv.org/abs/2110.04571
In this paper, we describe how the electronic rolling shutter in CMOS image sensors can be exploited using a bright, modulated light source (e.g., an inexpensive, off-the-shelf laser), to inject fine-grained image disruptions. We demonstrate the atta
Externí odkaz:
http://arxiv.org/abs/2101.10011
In this paper, we present a Distribution-Preserving Voice Anonymization technique, as our submission to the VoicePrivacy Challenge 2020. We observe that the challenge baseline system generates fake X-vectors which are very similar to each other, sign
Externí odkaz:
http://arxiv.org/abs/2010.13457