Search Results for author:
Found 38 papers, 10 papers with code
Graph Machine Learning in the Era of Large Language Models (LLMs)
Meanwhile, graphs, especially knowledge graphs, are rich in reliable factual knowledge, which can be utilized to enhance the reasoning capabilities of LLMs and potentially alleviate their limitations such as hallucinations and the lack of explainability.
Manufacturing Service Capability Prediction with Graph Neural Networks
To address the need, this study proposes a Graph Neural Network-based method for manufacturing service capability identification over a knowledge graph.
Linear-Time Graph Neural Networks for Scalable Recommendations
In this paper, we propose a Linear-Time Graph Neural Network (LTGNN) to scale up GNN-based recommender systems to achieve comparable scalability as classic MF approaches while maintaining GNNs' powerful expressiveness for superior prediction accuracy.
Rethinking Large Language Model Architectures for Sequential Recommendations
This design stems from our empirical observation that beam search decoding is ultimately unnecessary for sequential recommendations.
Efficient Large Language Models Fine-Tuning On Graphs
In this work, we introduce a novel and efficient approach for the end-to-end fine-tuning of Large Language Models (LLMs) on TAGs, named LEADING.
Robust Graph Neural Networks via Unbiased Aggregation
The adversarial robustness of Graph Neural Networks (GNNs) has been questioned due to the false sense of security uncovered by strong adaptive attacks despite the existence of numerous defenses.
Automated Polynomial Filter Learning for Graph Neural Networks
Polynomial graph filters have been widely used as guiding principles in the design of Graph Neural Networks (GNNs).
Can Directed Graph Neural Networks be Adversarially Robust?
This work presents the first investigation into the robustness of GNNs in the context of directed graphs, aiming to harness the profound trust implications offered by directed graphs to bolster the robustness and resilience of GNNs.
LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation
Recent works have demonstrated the benefits of capturing long-distance dependency in graphs by deeper graph neural networks (GNNs).
Towards Fair Classification against Poisoning Attacks
We demonstrate that the fairly trained classifiers can be greatly vulnerable to such poisoning attacks, with much worse accuracy & fairness trade-off, even when we apply some of the most effective defenses (originally proposed to defend traditional classification tasks).
Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective
In this paper, we propose a new perspective to look at the performance degradation of deep GNNs, i. e., feature overcorrelation.
Alternately Optimized Graph Neural Networks
Extensive experiments demonstrate that the proposed method can achieve comparable or better performance with state-of-the-art baselines while it has significantly better computation and memory efficiency.
Defense Against Gradient Leakage Attacks via Learning to Obscure Data
However, federated learning is still under the risk of privacy leakage because of the existence of attackers who deliberately conduct gradient leakage attacks to reconstruct the client data.
Enhancing Adversarial Training with Feature Separability
Deep Neural Network (DNN) are vulnerable to adversarial attacks.
Graph Neural Networks with Adaptive Residual
Graph neural networks (GNNs) have shown the power in graph representation learning for numerous tasks.
Towards Feature Overcorrelation in Deeper Graph Neural Networks
In this paper, we observe a new issue in deeper GNNs, i. e., feature overcorrelation, and perform a thorough study to deepen our understanding on this issue.
Graph Trend Filtering Networks for Recommendations
The key of recommender systems is to predict how likely users will interact with items based on their historical online behaviors, e. g., clicks, add-to-cart, purchases, etc.
Decentralized Composite Optimization with Compression
Decentralized optimization and communication compression have exhibited their great potential in accelerating distributed machine learning by mitigating the communication bottleneck in practice.
Jointly Attacking Graph Neural Network and its Explanations
Despite the great success, recent studies have shown that GNNs are highly vulnerable to adversarial attacks, where adversaries can mislead the GNNs' prediction by modifying graphs.
Imbalanced Adversarial Training with Reweighting
Adversarial training has been empirically proven to be one of the most effective and reliable defense methods against adversarial attacks.
Trustworthy AI: A Computational Perspective
In the past few decades, artificial intelligence (AI) technology has experienced swift developments, changing everyone's daily life and profoundly altering the course of human society.
Elastic Graph Neural Networks
While many existing graph neural networks (GNNs) have been proven to perform $\ell_2$-based graph smoothing that enforces smoothness globally, in this work we aim to further enhance the local smoothness adaptivity of GNNs via $\ell_1$-based graph smoothing.
Is Homophily a Necessity for Graph Neural Networks?
We find that this claim is not quite true, and in fact, GCNs can achieve strong performance on heterophilous graphs under certain conditions.
Automated Self-Supervised Learning for Graphs
Then we propose the AutoSSL framework which can automatically search over combinations of various self-supervised tasks.
Towards the Memorization Effect of Neural Networks in Adversarial Training
In this work, we study the effect of memorization in adversarial trained DNNs and disclose two important findings: (a) Memorizing atypical samples is only effective to improve DNN's accuracy on clean atypical samples, but hardly improve their adversarial robustness and (b) Memorizing certain atypical samples will even hurt the DNN's performance on typical samples.
Graph Feature Gating Networks
Graph neural networks (GNNs) have received tremendous attention due to their power in learning effective representations for graphs.
Faster than Real-Time Simulation: Methods, Tools, and Applications
Namely, the provided acceleration can be used for improving system scheduling, assessing system vulnerabilities, and predicting system disruptions in real-time systems.
CHIMERA: A Hybrid Estimation Approach to Limit the Effects of False Data Injection Attacks
Our simulation experiments based on the load data from New York state demonstrate that CHIMERA can effectively mitigate 91. 74% of the cases in which FDIAs can maliciously modify the contingencies.
Cyber-Physical Energy Systems Security: Threat Modeling, Risk Assessment, Resources, Metrics, and Case Studies
Leveraging the threat model formulation, we present a CPS framework designed to delineate the hardware, software, and modeling resources required to simulate the CPS and construct high-fidelity models which can be used to evaluate the system's performance under adverse scenarios.
Cryptography and Security Systems and Control Systems and Control
To be Robust or to be Fair: Towards Fairness in Adversarial Training
However, we find that adversarial training algorithms tend to introduce severe disparity of accuracy and robustness between different groups of data.
A Unified View on Graph Neural Networks as Graph Signal Denoising
In this work, we establish mathematically that the aggregation processes in a group of representative GNN models including GCN, GAT, PPNP, and APPNP can be regarded as (approximately) solving a graph denoising problem with a smoothness assumption.
Yet Meta Learning Can Adapt Fast, It Can Also Break Easily
Thus, in this paper, we perform the initial study about adversarial attacks on meta learning under the few-shot classification problem.
Linear Convergent Decentralized Optimization with Compression
Communication compression has become a key strategy to speed up distributed optimization.
Graph Structure Learning for Robust Graph Neural Networks
A natural idea to defend adversarial attacks is to clean the perturbed graph.
A Double Residual Compression Algorithm for Efficient Distributed Learning
Large-scale machine learning models are often trained by parallel stochastic gradient descent algorithms.
Deep Adversarial Network Alignment
Network alignment, in general, seeks to discover the hidden underlying correspondence between nodes across two (or more) networks when given their network structure.
A Survey on Dialogue Systems: Recent Advances and New Frontiers
Dialogue systems have attracted more and more attention.
Fingertip in the Eye: A cascaded CNN pipeline for the real-time fingertip detection in egocentric videos
We introduce a new pipeline for hand localization and fingertip detection.
