Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs

Chen, Mingyang; Zhang, Wen; Geng, Yuxia; Xu, Zezhong; Pan, Jeff Z.; Chen, Huajun

doi:10.48550/arxiv.2302.01859

Cited by 2 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graph neural networks (GNNs) are widely available in the real world [37,52,53] and are attracting the attention of researchers [51,56,87,89]. By treating samples as nodes and relationships between samples as edges, GNNs can easily capture the underlying relationships and rules between samples through message propagation mechanisms, which are suitable to various types of graphs [9,26,38,41,43,44]. GNNs have gained significant popularity and are widely employed in various real-world applications, including recommendation [81], community discovery [25,50], fake news detection [29,85], multi-view clustering [24,74,78,92], bioinformatics [22], hyper-graph analysis [82], image processing [27,30], etc, because they can find the relationship between samples in changing and multivariate data [28,75,88].…”

Section: Temporal Graph Learningmentioning

confidence: 99%

TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification

Liu,

Liang,

et al. 2023

Proceedings of the 31st ACM International Conference on Multimedia

View full text Add to dashboard Cite

Audiovisual data is everywhere in this digital age, which raises higher requirements for the deep learning models developed on them. To well handle the information of the multi-modal data is the key to a better audiovisual modal. We observe that these audiovisual data naturally have temporal attributes, such as the time information for each frame in the video. More concretely, such data is inherently multi-modal according to both audio and visual cues, which proceed in a strict chronological order. It indicates that temporal information is important in multi-modal acoustic event modeling for both intra-and inter-modal. However, existing methods deal with each modal feature independently and simply fuse them together, which neglects the mining of temporal relation and thus leads to sub-optimal performance. With this motivation, we propose a Temporal Multi-modal graph learning method for Acoustic event Classification, called TMac, by modeling such temporal information via graph learning techniques. In particular, we construct a temporal graph for each acoustic event, dividing its audio data and video data into multiple segments. Each segment can be considered as a node, and the temporal relationships between nodes can be considered as timestamps on their edges. In this case, we can smoothly capture the dynamic information in intra-modal and inter-modal. Several experiments are conducted to demonstrate

show abstract

Section: Temporal Graph Learningmentioning

confidence: 99%

TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification

Liu,

Liang,

et al. 2023

Proceedings of the 31st ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…However, most KGs suffer from incompleteness issues. As an essential way to address the problem, relation reasoning, i.e., relation prediction, can be generally divided into two categories (Chen et al 2023a), including transductive relation reasoning and inductive relation reasoning (See Fig. 1).…”

Section: Introductionmentioning

confidence: 99%

MINES: Message Intercommunication for Inductive Relation Reasoning over Neighbor-Enhanced Subgraphs

Liang,

Meng,

Zhou

et al. 2024

AAAI

View full text Add to dashboard Cite

GraIL and its variants have shown their promising capacities for inductive relation reasoning on knowledge graphs. However, the uni-directional message-passing mechanism hinders such models from exploiting hidden mutual relations between entities in directed graphs. Besides, the enclosing subgraph extraction in most GraIL-based models restricts the model from extracting enough discriminative information for reasoning. Consequently, the expressive ability of these models is limited. To address the problems, we propose a novel GraIL-based framework, termed MINES, by introducing a Message Intercommunication mechanism on the Neighbor-Enhanced Subgraph. Concretely, the message intercommunication mechanism is designed to capture the omitted hidden mutual information. It introduces bi-directed information interactions between connected entities by inserting an undirected/bi-directed GCN layer between uni-directed RGCN layers. Moreover, inspired by the success of involving more neighbors in other graph-based tasks, we extend the neighborhood area beyond the enclosing subgraph to enhance the information collection for inductive relation reasoning. Extensive experiments prove the promising capacity of the proposed MINES from various aspects, especially for the superiority, effectiveness, and transfer ability.

show abstract

Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs

Cited by 2 publications

References 4 publications

TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification

TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification

MINES: Message Intercommunication for Inductive Relation Reasoning over Neighbor-Enhanced Subgraphs

Contact Info

Product

Resources

About