Yanmin Shang
YOU?
Author Swipe
View article: LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions
LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions Open
Driven by the rapid advancements of Large Language Models (LLMs), LLM-based agents have emerged as powerful intelligent systems capable of human-like cognition, reasoning, and interaction. These agents are increasingly being deployed acros…
View article: Deep Graph Neural Point Process For Learning Temporal Interactive Networks
Deep Graph Neural Point Process For Learning Temporal Interactive Networks Open
Learning temporal interaction networks(TIN) is previously regarded as a coarse-grained multi-sequence prediction problem, ignoring the network topology structure influence. This paper addresses this limitation and a Deep Graph Neural Point…
View article: VR-GNN: Variational Relation Vector Graph Neural Network for Modeling Homophily and Heterophily
VR-GNN: Variational Relation Vector Graph Neural Network for Modeling Homophily and Heterophily Open
Graph Neural Networks (GNNs) have achieved remarkable success in diverse real-world applications. Traditional GNNs are designed based on homophily, which leads to poor performance under heterophily scenarios. Most current solutions deal wi…
View article: Multi-Aspect Heterogeneous Graph Augmentation
Multi-Aspect Heterogeneous Graph Augmentation Open
Data augmentation has been widely studied as it can be used to improve the generalizability of graph representation learning models. However, existing works focus only on the data augmentation on homogeneous graphs. Data augmentation for h…
View article: VR-GNN: Variational Relation Vector Graph Neural Network for Modeling both Homophily and Heterophily
VR-GNN: Variational Relation Vector Graph Neural Network for Modeling both Homophily and Heterophily Open
Graph Neural Networks (GNNs) have achieved remarkable success in diverse real-world applications. Traditional GNNs are designed based on homophily, which leads to poor performance under heterophily scenarios. Current solutions deal with he…
View article: Explainable Hyperbolic Temporal Point Process for User-Item Interaction Sequence Generation
Explainable Hyperbolic Temporal Point Process for User-Item Interaction Sequence Generation Open
Recommender systems which captures dynamic user interest based on time-ordered user-item interactions plays a critical role in the real-world. Although existing deep learning-based recommendation systems show good performances, these metho…
View article: H2-FDetector: A GNN-based Fraud Detector with Homophilic and Heterophilic Connections
H2-FDetector: A GNN-based Fraud Detector with Homophilic and Heterophilic Connections Open
In the fraud graph, fraudsters often interact with a large number of benign entities to hide themselves. So, there are not only the homophilic connections formed by the same label nodes (similar nodes), but also the heterophilic connection…
View article: API-GNN: attribute preserving oriented interactive graph neural network
API-GNN: attribute preserving oriented interactive graph neural network Open
Attributed graph embedding aims to learn node representation based on the graph topology and node attributes. The current mainstream GNN-based methods learn the representation of the target node by aggregating the attributes of its neighbo…
View article: TEBNER: Domain Specific Named Entity Recognition with Type Expanded Boundary-aware Network
TEBNER: Domain Specific Named Entity Recognition with Type Expanded Boundary-aware Network Open
To alleviate label scarcity in Named Entity Recognition (NER) task, distantly supervised NER methods are widely applied to automatically label data and identify entities. Although the human effort is reduced, the generated incomplete and n…
View article: RLINK: Deep reinforcement learning for user identity linkage
RLINK: Deep reinforcement learning for user identity linkage Open
User identity linkage is a task of recognizing the identities of the same user across different social networks (SN). Previous works tackle this problem via estimating the pairwise similarity between identities from different SN, predictin…
View article: Type-Aware Anchor Link Prediction across Heterogeneous Networks Based on Graph Attention Network
Type-Aware Anchor Link Prediction across Heterogeneous Networks Based on Graph Attention Network Open
Anchor Link Prediction (ALP) across heterogeneous networks plays a pivotal role in inter-network applications. The difficulty of anchor link prediction in heterogeneous networks lies in how to consider the factors affecting nodes alignment…
View article: RLINK: Deep Reinforcement Learning for User Identity Linkage
RLINK: Deep Reinforcement Learning for User Identity Linkage Open
User identity linkage is a task of recognizing the identities of the same user across different social networks (SN). Previous works tackle this problem via estimating the pairwise similarity between identities from different SN, predictin…