Search Results for author: Zhimeng Jiang

Found 18 papers, 8 papers with code

CODA: Temporal Domain Generalization via Concept Drift Simulator

no code implementations2 Oct 2023 Chia-Yuan Chang, Yu-Neng Chuang, Zhimeng Jiang, Kwei-Herng Lai, Anxiao Jiang, Na Zou

In real-world applications, machine learning models often become obsolete due to shifts in the joint distribution arising from underlying temporal trends, a phenomenon known as the "concept drift".

Domain Generalization

GrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length

no code implementations1 Oct 2023 Hongye Jin, Xiaotian Han, Jingfeng Yang, Zhimeng Jiang, Chia-Yuan Chang, Xia Hu

Our method progressively increases the training length throughout the pretraining phase, thereby mitigating computational costs and enhancing efficiency.

Graph Mixup with Soft Alignments

1 code implementation11 Jun 2023 Hongyi Ling, Zhimeng Jiang, Meng Liu, Shuiwang Ji, Na Zou

We conduct systematic experiments to show that S-Mixup can improve the performance and generalization of graph neural networks (GNNs) on various graph classification tasks.

Data Augmentation Graph Classification

Editable Graph Neural Network for Node Classifications

no code implementations24 May 2023 Zirui Liu, Zhimeng Jiang, Shaochen Zhong, Kaixiong Zhou, Li Li, Rui Chen, Soo-Hyun Choi, Xia Hu

However, model editing for graph neural networks (GNNs) is rarely explored, despite GNNs' widespread applicability.

Fake News Detection Model Editing

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

no code implementations24 May 2023 Zirui Liu, Guanchu Wang, Shaochen Zhong, Zhaozhuo Xu, Daochen Zha, Ruixiang Tang, Zhimeng Jiang, Kaixiong Zhou, Vipin Chaudhary, Shuai Xu, Xia Hu

While the model parameters do contribute to memory usage, the primary memory bottleneck during training arises from storing feature maps, also known as activations, as they are crucial for gradient calculation.

Language Modelling Stochastic Optimization

Data-centric Artificial Intelligence: A Survey

10 code implementations17 Mar 2023 Daochen Zha, Zaid Pervaiz Bhat, Kwei-Herng Lai, Fan Yang, Zhimeng Jiang, Shaochen Zhong, Xia Hu

Artificial Intelligence (AI) is making a profound impact in almost every domain.

Weight Perturbation Can Help Fairness under Distribution Shift

no code implementations6 Mar 2023 Zhimeng Jiang, Xiaotian Han, Hongye Jin, Guanchu Wang, Na Zou, Xia Hu

In this paper, we first theoretically demonstrate the inherent connection between distribution shift, data perturbation, and weight perturbation.


Retiring $Δ$DP: New Distribution-Level Metrics for Demographic Parity

1 code implementation31 Jan 2023 Xiaotian Han, Zhimeng Jiang, Hongye Jin, Zirui Liu, Na Zou, Qifan Wang, Xia Hu

Unfortunately, in this paper, we reveal that the fairness metric $\Delta DP$ can not precisely measure the violation of demographic parity, because it inherently has the following drawbacks: i) zero-value $\Delta DP$ does not guarantee zero violation of demographic parity, ii) $\Delta DP$ values can vary with different classification thresholds.


Adaptive Risk-Aware Bidding with Budget Constraint in Display Advertising

1 code implementation6 Dec 2022 Zhimeng Jiang, Kaixiong Zhou, Mi Zhang, Rui Chen, Xia Hu, Soo-Hyun Choi

In this work, we explicitly factor in the uncertainty of estimated ad impression values and model the risk preference of a DSP under a specific state and market environment via a sequential decision process.

reinforcement-learning Reinforcement Learning (RL)

Towards Generating Adversarial Examples on Mixed-type Data

no code implementations17 Oct 2022 Han Xu, Menghai Pan, Zhimeng Jiang, Huiyuan Chen, Xiaoting Li, Mahashweta Das, Hao Yang

The existence of adversarial attacks (or adversarial examples) brings huge concern about the machine learning (ML) model's safety issues.

Anomaly Detection Vocal Bursts Type Prediction

DIVISION: Memory Efficient Training via Dual Activation Precision

1 code implementation5 Aug 2022 Guanchu Wang, Zirui Liu, Zhimeng Jiang, Ninghao Liu, Na Zou, Xia Hu

Activation compressed training provides a solution towards reducing the memory cost of training deep neural networks~(DNNs).


G-Mixup: Graph Data Augmentation for Graph Classification

1 code implementation15 Feb 2022 Xiaotian Han, Zhimeng Jiang, Ninghao Liu, Xia Hu

To this end, we propose $\mathcal{G}$-Mixup to augment graphs for graph classification by interpolating the generator (i. e., graphon) of different classes of graphs.

Data Augmentation Graph Classification

Geometric Graph Representation Learning via Maximizing Rate Reduction

no code implementations13 Feb 2022 Xiaotian Han, Zhimeng Jiang, Ninghao Liu, Qingquan Song, Jundong Li, Xia Hu

Learning discriminative node representations benefits various downstream tasks in graph analysis such as community detection and node classification.

Community Detection Contrastive Learning +2

FMP: Toward Fair Graph Message Passing against Topology Bias

no code implementations8 Feb 2022 Zhimeng Jiang, Xiaotian Han, Chao Fan, Zirui Liu, Na Zou, Ali Mostafavi, Xia Hu

Despite recent advances in achieving fair representations and predictions through regularization, adversarial debiasing, and contrastive learning in graph neural networks (GNNs), the working mechanism (i. e., message passing) behind GNNs inducing unfairness issue remains unknown.

Contrastive Learning Fairness +1

G-Mixup: Graph Augmentation for Graph Classification

no code implementations29 Sep 2021 Xiaotian Han, Zhimeng Jiang, Ninghao Liu, Xia Hu

To this end, we propose $\mathcal{G}$-Mixup to augment graphs for graph classification by interpolating the generator (i. e., graphon) of different classes of graphs.

Graph Classification

Generalized Demographic Parity for Group Fairness

1 code implementation ICLR 2022 Zhimeng Jiang, Xiaotian Han, Chao Fan, Fan Yang, Ali Mostafavi, Xia Hu

We show the understanding of GDP from the probability perspective and theoretically reveal the connection between GDP regularizer and adversarial debiasing.


An Information Fusion Approach to Learning with Instance-Dependent Label Noise

no code implementations ICLR 2022 Zhimeng Jiang, Kaixiong Zhou, Zirui Liu, Li Li, Rui Chen, Soo-Hyun Choi, Xia Hu

Instance-dependent label noise (IDN) widely exists in real-world datasets and usually misleads the training of deep neural networks.

Cannot find the paper you are looking for? You can Submit a new open access paper.