Search Results for author: Xiaotian Han

Found 23 papers, 9 papers with code

CORE-MM: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models

no code implementations20 Nov 2023 Xiaotian Han, Quanzeng You, Yongfei Liu, Wentao Chen, Huangjie Zheng, Khalil Mrini, Xudong Lin, Yiqi Wang, Bohan Zhai, Jianbo Yuan, Heng Wang, Hongxia Yang

To mitigate this issue, we manually curate a benchmark dataset specifically designed for MLLMs, with a focus on complex reasoning tasks.

Marginal Nodes Matter: Towards Structure Fairness in Graphs

no code implementations23 Oct 2023 Xiaotian Han, Kaixiong Zhou, Ting-Hsiang Wang, Jundong Li, Fei Wang, Na Zou

Specifically, we first analyzed multiple graphs and observed that marginal nodes in graphs have a worse performance of downstream tasks than others in graph neural networks.


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.

On the Equivalence of Graph Convolution and Mixup

no code implementations29 Sep 2023 Xiaotian Han, Hanqing Zeng, Yu Chen, Shaoliang Nie, Jingzhou Liu, Kanika Narang, Zahra Shakeri, Karthik Abinav Sankararaman, Song Jiang, Madian Khabsa, Qifan Wang, Xia Hu

We establish this equivalence mathematically by demonstrating that graph convolution networks (GCN) and simplified graph convolution (SGC) can be expressed as a form of Mixup.

Data Augmentation

Beyond Fairness: Age-Harmless Parkinson's Detection via Voice

no code implementations23 Sep 2023 Yicheng Wang, Xiaotian Han, Leisheng Yu, Na Zou

Through our investigation, the discrepancy between the elderly and the young arises due to 1) an imbalanced dataset and 2) the milder symptoms often seen in early-onset patients.


Towards Assumption-free Bias Mitigation

no code implementations9 Jul 2023 Chia-Yuan Chang, Yu-Neng Chuang, Kwei-Herng Lai, Xiaotian Han, Xia Hu, Na Zou

Those studies face challenges, either in inaccurate predictions of sensitive attributes or the need to mitigate unequal distribution of manually defined non-sensitive attributes related to bias.


FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods

1 code implementation15 Jun 2023 Xiaotian Han, Jianfeng Chi, Yu Chen, Qifan Wang, Han Zhao, Na Zou, Xia Hu

This paper introduces the Fair Fairness Benchmark (\textsf{FFB}), a benchmarking framework for in-processing group fairness methods.

Benchmarking Fairness

Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond

1 code implementation26 Apr 2023 Jingfeng Yang, Hongye Jin, Ruixiang Tang, Xiaotian Han, Qizhang Feng, Haoming Jiang, Bing Yin, Xia Hu

This paper presents a comprehensive and practical guide for practitioners and end-users working with Large Language Models (LLMs) in their downstream natural language processing (NLP) tasks.

Language Modelling Natural Language Understanding +1

Does Synthetic Data Generation of LLMs Help Clinical Text Mining?

no code implementations8 Mar 2023 Ruixiang Tang, Xiaotian Han, Xiaoqian Jiang, Xia Hu

Our method has resulted in significant improvements in the performance of downstream tasks, improving the F1-score from 23. 37% to 63. 99% for the named entity recognition task and from 75. 86% to 83. 59% for the relation extraction task.

Code Generation named-entity-recognition +5

Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach

1 code implementation NeurIPS 2023 Zhimeng Jiang, Xiaotian Han, Hongye Jin, Guanchu Wang, Rui Chen, Na Zou, Xia Hu

Motivated by these sufficient conditions, we propose robust fairness regularization (RFR) by considering the worst case within the model weight perturbation ball for each sensitive attribute group.


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.


Auto-PINN: Understanding and Optimizing Physics-Informed Neural Architecture

no code implementations27 May 2022 Yicheng Wang, Xiaotian Han, Chia-Yuan Chang, Daochen Zha, Ulisses Braga-Neto, Xia Hu

Physics-informed neural networks (PINNs) are revolutionizing science and engineering practice by bringing together the power of deep learning to bear on scientific computation.

Hyperparameter Optimization Neural Architecture Search

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

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.


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

Image Scene Graph Generation (SGG) Benchmark

1 code implementation27 Jul 2021 Xiaotian Han, Jianwei Yang, Houdong Hu, Lei Zhang, Jianfeng Gao, Pengchuan Zhang

There is a surge of interest in image scene graph generation (object, attribute and relationship detection) due to the need of building fine-grained image understanding models that go beyond object detection.

Graph Generation object-detection +4

AutoRec: An Automated Recommender System

1 code implementation26 Jun 2020 Ting-Hsiang Wang, Qingquan Song, Xiaotian Han, Zirui Liu, Haifeng Jin, Xia Hu

To address the need, we present AutoRec, an open-source automated machine learning (AutoML) platform extended from the TensorFlow ecosystem and, to our knowledge, the first framework to leverage AutoML for model search and hyperparameter tuning in deep recommendation models.

AutoML Click-Through Rate Prediction +1

Deep Collaborative Filtering with Multi-Aspect Information in Heterogeneous Networks

no code implementations14 Sep 2019 Chuan Shi, Xiaotian Han, Li Song, Xiao Wang, Senzhang Wang, Junping Du, Philip S. Yu

However, the characteristics of users and the properties of items may stem from different aspects, e. g., the brand-aspect and category-aspect of items.

Collaborative Filtering Recommendation Systems

DMGroup at EmoInt-2017: Emotion Intensity Using Ensemble Method

no code implementations WS 2017 Song Jiang, Xiaotian Han

In stage1, we employ both linear and nonlinear regression models to obtain a more diverse emotion intensity representation.

Emotion Classification Emotion Recognition +2

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