Search Results for author:
Found 14 papers, 9 papers with code
Graph-Skeleton: ~1% Nodes are Sufficient to Represent Billion-Scale Graph
In this paper, we argue that properly fetching and condensing the background nodes from massive web graph data might be a more economical shortcut to tackle the obstacles fundamentally.
One Graph Model for Cross-domain Dynamic Link Prediction
Extensive experiments on eight untrained graphs demonstrate that DyExpert achieves state-of-the-art performance in cross-domain link prediction.
Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns
In this paper, we identify the fundamental cause of structural divergence as the discrepancy of generative patterns between the pre-training and downstream graphs.
Towards Fair Graph Federated Learning via Incentive Mechanisms
Extensive experiments show that our model achieves the best trade-off between accuracy and the fairness of model gradient, as well as superior payoff fairness.
Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks
The proposed pre-training pipeline is called the data-active graph pre-training (APT) framework, and is composed of a graph selector and a pre-training model.
Compositional Feature Augmentation for Unbiased Scene Graph Generation
Specifically, we first decompose each relation triplet feature into two components: intrinsic feature and extrinsic feature, which correspond to the intrinsic characteristics and extrinsic contexts of a relation triplet, respectively.
When to Pre-Train Graph Neural Networks? From Data Generation Perspective!
All convex combinations of graphon bases give rise to a generator space, from which graphs generated form the solution space for those downstream data that can benefit from pre-training.
Universal Prompt Tuning for Graph Neural Networks
In this paper, we introduce a universal prompt-based tuning method called Graph Prompt Feature (GPF) for pre-trained GNN models under any pre-training strategy.
DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection
Since GAD emphasizes the application and the rarity of anomalous samples, enriching the varieties of its datasets is fundamental work.
DropMessage: Unifying Random Dropping for Graph Neural Networks
First, it is challenging to find a universal method that are suitable for all cases considering the divergence of different datasets and models.
Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs
To bridge the gap between theoretical graph attacks and real-world scenarios, in this work, we propose a novel and more realistic setting: strict black-box graph attack, in which the attacker has no knowledge about the victim model at all and is not allowed to send any queries.
Unsupervised Adversarially-Robust Representation Learning on Graphs
Additionally, we explore a provable connection between the robustness of the unsupervised graph encoder and that of models on downstream tasks.
Learning Fair Representations via an Adversarial Framework
Fairness has become a central issue for our research community as classification algorithms are adopted in societally critical domains such as recidivism prediction and loan approval.
Particle Probability Hypothesis Density Filter based on Pairwise Markov Chains
Most multi-target tracking filters assume that one target and its observation follow a Hidden Markov Chain (HMC) model, but the implicit independence assumption of HMC model is invalid in many practical applications, and a Pairwise Markov Chain (PMC) model is more universally suitable than traditional HMC model.
