activity
20232025
most citedGrowLength: Accelerating LLMs Pretraining by Progressively Growing Training Length

4 citations · 4 across the 2 of their papers we have counts for

collaborators

8 papers

cs.LG2025

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…

cs.LG2024

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…

cs.CL2024

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

Hongye Jin, Xiaotian Han, Jingfeng Yang +5

It is well known that LLMs cannot generalize well to long contexts whose lengths are larger than the training sequence length. This poses challenges when employing LLMs for process…

cs.LG2023

Chasing Fairness in Graphs: A GNN Architecture Perspective

Zhimeng Jiang, Xiaotian Han, Chao Fan +4

There has been significant progress in improving the performance of graph neural networks (GNNs) through enhancements in graph data, model architecture design, and training strateg…

cs.CL2023

PokeMQA: Programmable knowledge editing for Multi-hop Question Answering

Hengrui Gu, Kaixiong Zhou, Xiaotian Han +3

Multi-hop question answering (MQA) is one of the challenging tasks to evaluate machine's comprehension and reasoning abilities, where large language models (LLMs) have widely achie…

cs.LG2023

Marginal Nodes Matter: Towards Structure Fairness in Graphs

Xiaotian Han, Kaixiong Zhou, Ting-Hsiang Wang +3

In social network, a person located at the periphery region (marginal node) is likely to be treated unfairly when compared with the persons at the center. While existing fairness w…