Event Detection: Gate Diversity and Syntactic Importance Scoresfor Graph
Convolution Neural Networks
- URL: http://arxiv.org/abs/2010.14123v1
- Date: Tue, 27 Oct 2020 08:28:28 GMT
- Title: Event Detection: Gate Diversity and Syntactic Importance Scoresfor Graph
Convolution Neural Networks
- Authors: Viet Dac Lai, Tuan Ngo Nguyen, Thien Huu Nguyen
- Abstract summary: We propose a novel gating mechanism to filter noisy information in the hidden vec-tors of the graph convolution neural net-works.
The proposed model achieves state-of-the-art performance on two ED datasets.
- Score: 34.84340664039068
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Recent studies on event detection (ED) haveshown that the syntactic
dependency graph canbe employed in graph convolution neural net-works (GCN) to
achieve state-of-the-art per-formance. However, the computation of thehidden
vectors in such graph-based models isagnostic to the trigger candidate words,
po-tentially leaving irrelevant information for thetrigger candidate for event
prediction. In addi-tion, the current models for ED fail to exploitthe overall
contextual importance scores of thewords, which can be obtained via the
depen-dency tree, to boost the performance. In thisstudy, we propose a novel
gating mechanismto filter noisy information in the hidden vec-tors of the GCN
models for ED based on theinformation from the trigger candidate. Wealso
introduce novel mechanisms to achievethe contextual diversity for the gates and
theimportance score consistency for the graphsand models in ED. The experiments
show thatthe proposed model achieves state-of-the-artperformance on two ED
datasets
Related papers
- CORE: Data Augmentation for Link Prediction via Information Bottleneck [25.044734252779975]
Link prediction (LP) is a fundamental task in graph representation learning.
We propose a novel data augmentation method, COmplete and REduce (CORE) to learn compact and predictive augmentations for LP models.
arXiv Detail & Related papers (2024-04-17T03:20:42Z) - Data Augmentation for Supervised Graph Outlier Detection with Latent
Diffusion Models [42.19529054800729]
We introduce GODM, a novel data augmentation for mitigating class imbalance in supervised graph outlier detection with latent Diffusion Models.
Our proposed method consists of three key components: (1) Variantioanl maps the heterogeneous information inherent within the graph data into a unified latent space, (2) Graph Generator synthesizes graph data that are statistically similar to real outliers from latent space, and (3) Latent Diffusion Model learns the latent space distribution of real organic data by iterative denoising.
arXiv Detail & Related papers (2023-12-29T16:50:40Z) - GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels [81.93520935479984]
We study a new problem, GNN model evaluation, that aims to assess the performance of a specific GNN model trained on labeled and observed graphs.
We propose a two-stage GNN model evaluation framework, including (1) DiscGraph set construction and (2) GNNEvaluator training and inference.
Under the effective training supervision from the DiscGraph set, GNNEvaluator learns to precisely estimate node classification accuracy of the to-be-evaluated GNN model.
arXiv Detail & Related papers (2023-10-23T05:51:59Z) - DEGREE: Decomposition Based Explanation For Graph Neural Networks [55.38873296761104]
We propose DEGREE to provide a faithful explanation for GNN predictions.
By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction.
We also design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods.
arXiv Detail & Related papers (2023-05-22T10:29:52Z) - Resisting Graph Adversarial Attack via Cooperative Homophilous
Augmentation [60.50994154879244]
Recent studies show that Graph Neural Networks are vulnerable and easily fooled by small perturbations.
In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack.
We propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model.
arXiv Detail & Related papers (2022-11-15T11:44:31Z) - Model Inversion Attacks against Graph Neural Networks [65.35955643325038]
We study model inversion attacks against Graph Neural Networks (GNNs)
In this paper, we present GraphMI to infer the private training graph data.
Our experimental results show that such defenses are not sufficiently effective and call for more advanced defenses against privacy attacks.
arXiv Detail & Related papers (2022-09-16T09:13:43Z) - Robust Causal Graph Representation Learning against Confounding Effects [21.380907101361643]
We propose Robust Causal Graph Representation Learning (RCGRL) to learn robust graph representations against confounding effects.
RCGRL introduces an active approach to generate instrumental variables under unconditional moment restrictions, which empowers the graph representation learning model to eliminate confounders.
arXiv Detail & Related papers (2022-08-18T01:31:25Z) - A Graph-Enhanced Click Model for Web Search [67.27218481132185]
We propose a novel graph-enhanced click model (GraphCM) for web search.
We exploit both intra-session and inter-session information for the sparsity and cold-start problems.
arXiv Detail & Related papers (2022-06-17T08:32:43Z) - Attention-Based Recommendation On Graphs [9.558392439655012]
Graph Neural Networks (GNN) have shown remarkable performance in different tasks.
In this study, we propose GARec as a model-based recommender system.
The presented method outperforms existing model-based, non-graph neural networks and graph neural networks in different MovieLens datasets.
arXiv Detail & Related papers (2022-01-04T21:02:02Z) - Causal Incremental Graph Convolution for Recommender System Retraining [89.25922726558875]
Real-world recommender system needs to be regularly retrained to keep with the new data.
In this work, we consider how to efficiently retrain graph convolution network (GCN) based recommender models.
arXiv Detail & Related papers (2021-08-16T04:20:09Z) - A Graph Data Augmentation Strategy with Entropy Preserving [11.886325179121226]
We introduce a novel graph entropy definition as a quantitative index to evaluate feature information among a graph.
Under considerations of preserving graph entropy, we propose an effective strategy to generate training data using a perturbed mechanism.
Our proposed approach significantly enhances the robustness and generalization ability of GCNs during the training process.
arXiv Detail & Related papers (2021-07-13T12:58:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.