Search Results for author:
Found 28 papers, 16 papers with code
LW2G: Learning Whether to Grow for Prompt-based Continual Learning
To promote cross-task knowledge facilitation and form an effective and efficient prompt sets pool, we propose a plug-in module in the former stage to \textbf{Learn Whether to Grow (LW2G)} based on the disparities between tasks.
When Heterophily Meets Heterogeneity: New Graph Benchmarks and Effective Methods
However, existing benchmarks for graph learning often focus on heterogeneous graphs with homophily or homogeneous graphs with heterophily, leaving a gap in understanding how methods perform on graphs that are both heterogeneous and heterophilic.
Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning
Although most graph neural networks (GNNs) can operate on graphs of any size, their classification performance often declines on graphs larger than those encountered during training.
Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
However, in this paper, we discover that not all pixels contribute equally to the accuracy on AEs (i. e., robustness) and accuracy on natural images (i. e., accuracy).
Causality-Aware Spatiotemporal Graph Neural Networks for Spatiotemporal Time Series Imputation
In this paper, we first revisit spatiotemporal time series imputation from a causal perspective and show how to block the confounders via the frontdoor adjustment.
Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement
Deep neural networks are vulnerable to adversarial samples.
Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria
Deep neural networks are vulnerable to adversarial noise.
Ranked #1 on
Adversarial Attack
on CIFAR-10
(Attack: AutoAttack metric)
Gradient constrained sharpness-aware prompt learning for vision-language models
This paper targets a novel trade-off problem in generalizable prompt learning for vision-language models (VLM), i. e., improving the performance on unseen classes while maintaining the performance on seen classes.
Towards Reliable Rare Category Analysis on Graphs via Individual Calibration
In particular, to quantify the uncertainties in RCA, we develop a node-level uncertainty quantification algorithm to model the overlapping support regions with high uncertainty; to handle the rarity of minority classes in miscalibration calculation, we generalize the distribution-based calibration metric to the instance level and propose the first individual calibration measurement on graphs named Expected Individual Calibration Error (EICE).
HeroLT: Benchmarking Heterogeneous Long-Tailed Learning
To achieve this, we develop the most comprehensive (to the best of our knowledge) long-tailed learning benchmark named HeroLT, which integrates 13 state-of-the-art algorithms and 6 evaluation metrics on 14 real-world benchmark datasets across 4 tasks from 3 domains.
GPatcher: A Simple and Adaptive MLP Model for Alleviating Graph Heterophily
While graph heterophily has been extensively studied in recent years, a fundamental research question largely remains nascent: How and to what extent will graph heterophily affect the prediction performance of graph neural networks (GNNs)?
Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization
To bridge this gap, we propose a generalization bound for long-tail classification on graphs by formulating the problem in the fashion of multi-task learning, i. e., each task corresponds to the prediction of one particular class.
Personalized Federated Learning under Mixture of Distributions
The recent trend towards Personalized Federated Learning (PFL) has garnered significant attention as it allows for the training of models that are tailored to each client while maintaining data privacy.
EvoluNet: Advancing Dynamic Non-IID Transfer Learning on Graphs
To answer it, we propose a generalization bound for dynamic non-IID transfer learning on graphs, which implies the generalization performance is dominated by domain evolution and domain discrepancy between source and target graphs.
FairGen: Towards Fair Graph Generation
In addition, we propose a generic context sampling strategy for graph generative models, which is proven to be capable of fairly capturing the contextual information of each group with a high probability.
Augmenting Knowledge Transfer across Graphs
Given a resource-rich source graph and a resource-scarce target graph, how can we effectively transfer knowledge across graphs and ensure a good generalization performance?
Towards High-Order Complementary Recommendation via Logical Reasoning Network
Finally, we further propose a hybrid network that is jointly optimized for learning a more generic product representation.
Towards Accurate Subgraph Similarity Computation via Neural Graph Pruning
In this work, we convert graph pruning to a problem of node relabeling and then relax it to a differentiable problem.
Strength-Adaptive Adversarial Training
Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness disparity between natural and robust accuracies, which deviates from robust network's desideratum.
Hiding Visual Information via Obfuscating Adversarial Perturbations
Growing leakage and misuse of visual information raise security and privacy concerns, which promotes the development of information protection.
MentorGNN: Deriving Curriculum for Pre-Training GNNs
To comprehend heterogeneous graph signals at different granularities, we propose a curriculum learning paradigm that automatically re-weighs graph signals in order to ensure a good generalization in the target domain.
Improving Adversarial Robustness via Mutual Information Estimation
To alleviate this negative effect, in this paper, we investigate the dependence between outputs of the target model and input adversarial samples from the perspective of information theory, and propose an adversarial defense method.
Modeling Adversarial Noise for Adversarial Defense
Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks.
Modeling Adversarial Noise for Adversarial Training
Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks.
Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Training
However, pre-processing methods may suffer from the robustness degradation effect, in which the defense reduces rather than improving the adversarial robustness of a target model in a white-box setting.
Towards Defending against Adversarial Examples via Attack-Invariant Features
However, given the continuously evolving attacks, models trained on seen types of adversarial examples generally cannot generalize well to unseen types of adversarial examples.
Removing Adversarial Noise in Class Activation Feature Space
Then, we train a denoising model to minimize the distances between the adversarial examples and the natural examples in the class activation feature space.
ADD-Defense: Towards Defending Widespread Adversarial Examples via Perturbation-Invariant Representation
Motivated by this observation, we propose a defense framework ADD-Defense, which extracts the invariant information called \textit{perturbation-invariant representation} (PIR) to defend against widespread adversarial examples.
