Search Results for author:
Found 10 papers, 5 papers with code
Continuous Geometry-Aware Graph Diffusion via Hyperbolic Neural PDE
While Hyperbolic Graph Neural Network (HGNN) has recently emerged as a powerful tool dealing with hierarchical graph data, the limitations of scalability and efficiency hinder itself from generalizing to deep models.
Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning
Meanwhile, based on the diffusion model, preferred actions within the same behavior distribution are automatically generated through the critic function.
Towards Fairness-Aware Adversarial Learning
As a generalization of conventional AT, we re-define the problem of adversarial training as a min-max-max framework, to ensure both robustness and fairness of the trained model.
Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching
Specifically, we employ a curriculum learning strategy to train expert trajectories with more diverse supervision signals from the original graph, and then effectively transfer the information into the condensed graph with expanding window matching.
Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching
Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have raised growing concerns.
Reward Certification for Policy Smoothed Reinforcement Learning
Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks.
Can pre-trained models assist in dataset distillation?
Dataset Distillation (DD) is a prominent technique that encapsulates knowledge from a large-scale original dataset into a small synthetic dataset for efficient training.
Symplectic Structure-Aware Hamiltonian (Graph) Embeddings
In traditional Graph Neural Networks (GNNs), the assumption of a fixed embedding manifold often limits their adaptability to diverse graph geometries.
PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning
Furthermore, we introduce a novel paradigm named Personalized Training with Distilled Execution (PTDE), wherein agent-personalized global information is distilled into the agent's local information.
PRoA: A Probabilistic Robustness Assessment against Functional Perturbations
Our experiments demonstrate the effectiveness and flexibility of PRoA in terms of evaluating the probabilistic robustness against a broad range of functional perturbations, and PRoA can scale well to various large-scale deep neural networks compared to existing state-of-the-art baselines.
