A survey of imbalanced learning on graphs: Problems, techniques, and future directions

Z Liu, Y Li, N Chen, Q Wang, B Hooi, B He - arxiv preprint arxiv …, 2023‏ - arxiv.org
Graphs represent interconnected structures prevalent in a myriad of real-world scenarios.
Effective graph analytics, such as graph learning methods, enables users to gain profound …

A survey of inductive knowledge graph completion

X Liang, G Si, J Li, P Tian, Z An, F Zhou - Neural Computing and …, 2024‏ - Springer
Abstract Knowledge graph completion (KGC) can enhance the completeness of the
knowledge graph (KG). Traditional transductive KGC assumes that all entities and relations …

Normalizing flow-based neural process for few-shot knowledge graph completion

L Luo, YF Li, G Haffari, S Pan - … of the 46th international ACM SIGIR …, 2023‏ - dl.acm.org
Knowledge graphs (KGs), as a structured form of knowledge representation, have been
widely applied in the real world. Recently, few-shot knowledge graph completion (FKGC) …

Task-adaptive few-shot node classification

S Wang, K Ding, C Zhang, C Chen, J Li - Proceedings of the 28th ACM …, 2022‏ - dl.acm.org
Node classification is of great importance among various graph mining tasks. In practice,
real-world graphs generally follow the long-tail distribution, where a large number of classes …

Few-shot learning on graphs

C Zhang, K Ding, J Li, X Zhang, Y Ye… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Graph representation learning has attracted tremendous attention due to its remarkable
performance in many real-world applications. However, prevailing supervised graph …

Federated few-shot learning

S Wang, X Fu, K Ding, C Chen, H Chen… - Proceedings of the 29th …, 2023‏ - dl.acm.org
Federated Learning (FL) enables multiple clients to collaboratively learn a machine learning
model without exchanging their own local data. In this way, the server can exploit the …

Integrating entity attributes for error-aware knowledge graph embedding

Q Zhang, J Dong, Q Tan… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Knowledge graphs (KGs) can structurally organize large-scale information in the form of
triples and significantly support many real-world applications. While most KG embedding …

Scene-driven multimodal knowledge graph construction for embodied ai

Y Song, P Sun, H Liu, Z Li, W Song… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Embodied AI is one of the most popular studies in artificial intelligence and robotics, which
can effectively improve the intelligence of real-world agents (ie robots) serving human …

Transductive linear probing: A novel framework for few-shot node classification

Z Tan, S Wang, K Ding, J Li… - Learning on Graphs …, 2022‏ - proceedings.mlr.press
Few-shot node classification is tasked to provide accurate predictions for nodes from novel
classes with only few representative labeled nodes. This problem has drawn tremendous …

Contrastive meta-learning for few-shot node classification

S Wang, Z Tan, H Liu, J Li - Proceedings of the 29th ACM SIGKDD …, 2023‏ - dl.acm.org
Few-shot node classification, which aims to predict labels for nodes on graphs with only
limited labeled nodes as references, is of great significance in real-world graph mining …