82 citations · 307 across the 38 of their papers we have counts for
30 papers · 1 filter
A Replicate-and-Quantize Strategy for Plug-and-Play Load Balancing of Sparse Mixture-of-Experts LLMs
Zijie Liu, Jie Peng, Jinhao Duan +7
Sparse Mixture-of-Experts (SMoE) architectures are increasingly used to scale large language models efficiently, delivering strong accuracy under fixed compute budgets. However, SM…
When Domains Interact: Asymmetric and Order-Sensitive Cross-Domain Effects in Reinforcement Learning for Reasoning
Wang Yang, Shouren Wang, Chaoda Song +6
Group Relative Policy Optimization (GRPO) has become a key technique for improving reasoning abilities in large language models, yet its behavior under different domain sequencing…
Catastrophic Forgetting in Kolmogorov-Arnold Networks
Mohammad Marufur Rahman, Guanchu Wang, Kaixiong Zhou +2
Catastrophic forgetting is a longstanding challenge in continual learning, where models lose knowledge from earlier tasks when learning new ones. While various mitigation strategie…
Gradient-based Model Shortcut Detection for Time Series Classification
Salomon Ibarra, Frida Cantu, Kaixiong Zhou +1
Deep learning models have attracted lots of research attention in time series classification (TSC) task in the past two decades. Recently, deep neural networks (DNN) have surpassed…
You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time
Xiaotian Han, Tianlong Chen, Kaixiong Zhou +3
Deep neural networks are prone to various bias issues, jeopardizing their applications for high-stake decision-making. Existing fairness methods typically offer a fixed accuracy-fa…
LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models
Xi Zhu, Haochen Xue, Ziwei Zhao +7
Text-Attributed Graphs (TAGs), where each node is associated with text descriptions, are ubiquitous in real-world scenarios. They typically exhibit distinctive structure and domain…
Gradient Rewiring for Editable Graph Neural Network Training
Zhimeng Jiang, Zirui Liu, Xiaotian Han +6
Deep neural networks are ubiquitously adopted in many applications, such as computer vision, natural language processing, and graph analytics. However, well-trained neural networks…
TVE: Learning Meta-attribution for Transferable Vision Explainer
Guanchu Wang, Yu-Neng Chuang, Fan Yang +8
Explainable machine learning significantly improves the transparency of deep neural networks. However, existing work is constrained to explaining the behavior of individual model p…
ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning
Yucheng Shi, Kaixiong Zhou, Ninghao Liu
The recent contrastive learning methods, due to their effectiveness in representation learning, have been widely applied to modeling graph data. Random perturbation is widely used…
Editable Graph Neural Network for Node Classifications
Zirui Liu, Zhimeng Jiang, Shaochen Zhong +5
Despite Graph Neural Networks (GNNs) have achieved prominent success in many graph-based learning problem, such as credit risk assessment in financial networks and fake news detect…
Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
Zirui Liu, Guanchu Wang, Shaochen Zhong +8
With the rapid growth in model size, fine-tuning the large pre-trained language model has become increasingly difficult due to its extensive memory usage. Previous works usually fo…
Context-aware Domain Adaptation for Time Series Anomaly Detection
Kwei-Herng Lai, Lan Wang, Huiyuan Chen +4
Time series anomaly detection is a challenging task with a wide range of real-world applications. Due to label sparsity, training a deep anomaly detector often relies on unsupervis…
A Survey of Graph Prompting Methods: Techniques, Applications, and Challenges
Xuansheng Wu, Kaixiong Zhou, Mingchen Sun +2
The recent "pre-train, prompt, predict training" paradigm has gained popularity as a way to learn generalizable models with limited labeled data. The approach involves using a pre-…
MolCPT: Molecule Continuous Prompt Tuning to Generalize Molecular Representation Learning
Cameron Diao, Kaixiong Zhou, Zirui Liu +2
Molecular representation learning is crucial for the problem of molecular property prediction, where graph neural networks (GNNs) serve as an effective solution due to their struct…
RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computations
Zirui Liu, Shengyuan Chen, Kaixiong Zhou +3
The training of graph neural networks (GNNs) is extremely time consuming because sparse graph-based operations are hard to be accelerated by hardware. Prior art explores trading of…
A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking
Keyu Duan, Zirui Liu, Peihao Wang +5
Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs). Due to the nature of evolving graph structures into the training process, vanilla…
Differentially Private Counterfactuals via Functional Mechanism
Fan Yang, Qizhang Feng, Kaixiong Zhou +2
Counterfactual, serving as one emerging type of model explanation, has attracted tons of attentions recently from both industry and academia. Different from the conventional featur…
Towards Similarity-Aware Time-Series Classification
Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou +1
We study time-series classification (TSC), a fundamental task of time-series data mining. Prior work has approached TSC from two major directions: (1) similarity-based methods that…
CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks
Haotian Xue, Kaixiong Zhou, Tianlong Chen +4
Despite the recent advances of graph neural networks (GNNs) in modeling graph data, the training of GNNs on large datasets is notoriously hard due to the overfitting. Adversarial t…
Orthogonal Graph Neural Networks
Kai Guo, Kaixiong Zhou, Xia Hu +3
Graph neural networks (GNNs) have received tremendous attention due to their superiority in learning node representations. These models rely on message passing and feature transfor…
Adaptive Label Smoothing To Regularize Large-Scale Graph Training
Kaixiong Zhou, Ninghao Liu, Fan Yang +5
Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many d…
Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study
Tianlong Chen, Kaixiong Zhou, Keyu Duan +4
Training deep graph neural networks (GNNs) is notoriously hard. Besides the standard plights in training deep architectures such as vanishing gradients and overfitting, it also uni…
Dirichlet Energy Constrained Learning for Deep Graph Neural Networks
Kaixiong Zhou, Xiao Huang, Daochen Zha +4
Graph neural networks (GNNs) integrate deep architectures and topological structure modeling in an effective way. However, the performance of existing GNNs would decrease significa…
Simplifying Deep Reinforcement Learning via Self-Supervision
Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou +1
Supervised regression to demonstrations has been demonstrated to be a stable way to train deep policy networks. We are motivated to study how we can take full advantage of supervis…