Search Results for author:
Found 12 papers, 9 papers with code
Improving Out-of-Vocabulary Handling in Recommendation Systems
This work focuses on a complementary problem: recommending new users and items unseen (out-of-vocabulary, or OOV) at training time.
How Does Message Passing Improve Collaborative Filtering?
A branch of research enhances CF methods by message passing used in graph neural networks, due to its strong capabilities of extracting knowledge from graph-structured data, like user-item bipartite graphs that naturally exist in CF.
Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions
Contrast consistency, the ability of a model to make consistently correct predictions in the presence of perturbations, is an essential aspect in NLP.
Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learning
Whereas for the node injection attack, though being more practical, current approaches require training surrogate models to simulate a white-box setting, which results in significant performance downgrade when the surrogate architecture diverges from the actual victim model.
Self-Supervised Graph Structure Refinement for Graph Neural Networks
Specifically, The pre-training phase aims to comprehensively estimate the underlying graph structure by a multi-view contrastive learning framework with both intra- and inter-view link prediction tasks.
Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering
In light of this, we propose a novel knowledge Graph enhanced passage reader, namely Grape, to improve the reader performance for open-domain QA.
Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization
Besides, we observe that learning from multiple philosophies enhances not only the task generalization but also the single task performances, demonstrating that PARETOGNN achieves better task generalization via the disjoint yet complementary knowledge learned from different philosophies.
Generate rather than Retrieve: Large Language Models are Strong Context Generators
We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.
Black-box Node Injection Attack for Graph Neural Networks
Graph Neural Networks (GNNs) have drawn significant attentions over the years and been broadly applied to vital fields that require high security standard such as product recommendation and traffic forecasting.
Adaptive Kernel Graph Neural Network
To solve this problem, in this paper, we propose a novel framework - i. e., namely Adaptive Kernel Graph Neural Network (AKGNN) - which learns to adapt to the optimal graph kernel in a unified manner at the first attempt.
Heterogeneous Temporal Graph Neural Network
To retain the heterogeneity, intra-relation aggregation is first performed over each slice of HTG to attentively aggregate information of neighbors with the same type of relation, and then intra-relation aggregation is exploited to gather information over different types of relations; to handle temporal dependencies, across-time aggregation is conducted to exchange information across different graph slices over the HTG.
heterogeneous temporal graph transformer: an intelligent system for evolving android malware detection
To capture malware evolution, we further consider the temporal dependence and introduce a heterogeneous temporal graph to jointly model malware propagation and evolution by considering heterogeneous spatial dependencies with temporal dimensions.
