Learning to represent the evolution of dynamic graphs with recurrent models
Graph representation learning for static graphs is a well studied topic. Recently, a few
studies have focused on learning temporal information in addition to the topology of a graph …
studies have focused on learning temporal information in addition to the topology of a graph …
Machine learning model to predict welding quality using air-coupled acoustic emission and weld inputs
K Asif, L Zhang, S Derrible, JE Indacochea… - Journal of Intelligent …, 2022 - Springer
Weld evaluation processes are usually conducted in the post-weld stage. In this way, defects
are found after the weld is completed, often resulting in disposal of expensive material or …
are found after the weld is completed, often resulting in disposal of expensive material or …
Predictive temporal embedding of dynamic graphs
A Taheri, T Berger-Wolf - Proceedings of the 2019 IEEE/ACM …, 2019 - dl.acm.org
In recent years, substantial effort has been devoted to learning to represent the static graphs
and their substructures. A few studies explored utilizing temporal information available in a …
and their substructures. A few studies explored utilizing temporal information available in a …
Ethogram-based automatic wild animal monitoring through inertial sensors and GPS data
Direct monitoring of wild animals' behavior is challenging and data tampering. Instrument
the animals with collars that embeds sensors, such as tri-axial accelerometer and GPS …
the animals with collars that embeds sensors, such as tri-axial accelerometer and GPS …
Multiclass Learning from Noisy Labels for Non-decomposable Performance Measures
M Zhang, S Agarwal - International Conference on Artificial …, 2024 - proceedings.mlr.press
There has been much interest in recent years in learning good classifiers from data with
noisy labels. Most work on learning from noisy labels has focused on standard loss-based …
noisy labels. Most work on learning from noisy labels has focused on standard loss-based …
Distributionally robust graphical models
In many structured prediction problems, complex relationships between variables are
compactly defined using graphical structures. The most prevalent graphical prediction …
compactly defined using graphical structures. The most prevalent graphical prediction …
Coordination event detection and initiator identification in time series data
C Amornbunchornvej, I Brugere… - ACM Transactions on …, 2018 - dl.acm.org
Behavior initiation is a form of leadership and is an important aspect of social organization
that affects the processes of group formation, dynamics, and decision-making in human …
that affects the processes of group formation, dynamics, and decision-making in human …
Arc: Adversarial robust cuts for semi-supervised and multi-label classification
S Behpour - Proceedings of the IEEE Conference on …, 2018 - openaccess.thecvf.com
Many structured prediction tasks arising in computer vision and natural language processing
tractably reduce to making minimum cost cuts in graphs with edge weights learned using …
tractably reduce to making minimum cost cuts in graphs with edge weights learned using …
Efficient and consistent adversarial bipartite matching
Many important structured prediction problems, including learning to rank items,
correspondence-based natural language processing, and multi-object tracking, can be …
correspondence-based natural language processing, and multi-object tracking, can be …
A framework for identifying group behavior of wild animals
Activity recognition and, more generally, behavior inference tasks are gaining a lot of
interest. Much of it is work in the context of human behavior. New available tracking …
interest. Much of it is work in the context of human behavior. New available tracking …