Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Yin, Haoteng"'
Graphs offer unique insights into relationships and interactions between entities, complementing data modalities like text, images, and videos. By incorporating relational information from graph data, AI models can extend their capabilities beyond tr
Externí odkaz:
http://arxiv.org/abs/2410.08299
Pedestrian trajectory prediction is the key technology in many applications for providing insights into human behavior and anticipating human future motions. Most existing empirical models are explicitly formulated by observed human behaviors using e
Externí odkaz:
http://arxiv.org/abs/2402.17339
Graph neural networks (GNNs) have shown great potential in learning on graphs, but they are known to perform sub-optimally on link prediction tasks. Existing GNNs are primarily designed to learn node-wise representations and usually fail to capture p
Externí odkaz:
http://arxiv.org/abs/2312.16784
Autor:
Wei, Rongzhe, Kreačić, Eleonora, Wang, Haoyu, Yin, Haoteng, Chien, Eli, Potluru, Vamsi K., Li, Pan
Privacy concerns have led to a surge in the creation of synthetic datasets, with diffusion models emerging as a promising avenue. Although prior studies have performed empirical evaluations on these models, there has been a gap in providing a mathema
Externí odkaz:
http://arxiv.org/abs/2310.15524
Autor:
Mukherjee, Prasita, Yin, Haoteng
Model Checking is widely applied in verifying the correctness of complex and concurrent systems against a specification. Pure symbolic approaches while popular, suffer from the state space explosion problem due to cross product operations required th
Externí odkaz:
http://arxiv.org/abs/2308.13474
Subgraph-based graph representation learning (SGRL) has recently emerged as a powerful tool in many prediction tasks on graphs due to its advantages in model expressiveness and generalization ability. Most previous SGRL models face computational chal
Externí odkaz:
http://arxiv.org/abs/2303.03379
Model Checking is widely applied in verifying the correctness of complex and concurrent systems against a specification. Pure symbolic approaches while popular, still suffer from the state space explosion problem that makes them impractical for large
Externí odkaz:
http://arxiv.org/abs/2207.11649
Graph neural networks (GNNs) have shown superiority in many prediction tasks over graphs due to their impressive capability of capturing nonlinear relations in graph-structured data. However, for node classification tasks, often, only marginal improv
Externí odkaz:
http://arxiv.org/abs/2207.11311
Graph neural networks (GNN) have shown great advantages in many graph-based learning tasks but often fail to predict accurately for a task-based on sets of nodes such as link/motif prediction and so on. Many works have recently proposed to address th
Externí odkaz:
http://arxiv.org/abs/2203.00199
Subgraph-based graph representation learning (SGRL) has been recently proposed to deal with some fundamental challenges encountered by canonical graph neural networks (GNNs), and has demonstrated advantages in many important data science applications
Externí odkaz:
http://arxiv.org/abs/2202.13538