Search Results for author: Chenghu Zhou

Found 39 papers, 21 papers with code

RFBFN: A Relation-First Blank Filling Network for Joint Relational Triple Extraction

1 code implementation ACL 2022 Zhe Li, Luoyi Fu, Xinbing Wang, Haisong Zhang, Chenghu Zhou

However, most existing works either ignore the semantic information of relations or predict subjects and objects sequentially.

Relation

AceParse: A Comprehensive Dataset with Diverse Structured Texts for Academic Literature Parsing

1 code implementation16 Sep 2024 Huawei Ji, Cheng Deng, Bo Xue, Zhouyang Jin, Jiaxin Ding, Xiaoying Gan, Luoyi Fu, Xinbing Wang, Chenghu Zhou

With the development of data-centric AI, the focus has shifted from model-driven approaches to improving data quality.

Good Idea or Not, Representation of LLM Could Tell

no code implementations7 Sep 2024 Yi Xu, Bo Xue, Shuqian Sheng, Cheng Deng, Jiaxin Ding, Zanwei Shen, Luoyi Fu, Xinbing Wang, Chenghu Zhou

Our findings suggest that the representations of large language models hold more potential in quantifying the value of ideas than their generative outputs, demonstrating a promising avenue for automating the idea assessment process.

MTSCI: A Conditional Diffusion Model for Multivariate Time Series Consistent Imputation

1 code implementation11 Aug 2024 Jianping Zhou, Junhao Li, Guanjie Zheng, Xinbing Wang, Chenghu Zhou

A key research question is how to ensure imputation consistency, i. e., intra-consistency between observed and imputed values, and inter-consistency between adjacent windows after imputation.

Denoising Inductive Bias +3

AutoFAIR : Automatic Data FAIRification via Machine Reading

no code implementations7 Aug 2024 Tingyan Ma, Wei Liu, Bin Lu, Xiaoying Gan, Yunqiang Zhu, Luoyi Fu, Chenghu Zhou

Subsequently, FAIR Alignment is employed to make metadata comply with FAIR principles by ontology guidance and semantic matching.

Fairness Reading Comprehension

Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints

1 code implementation22 Jul 2024 Shiqing Gao, Jiaxin Ding, Luoyi Fu, Xinbing Wang, Chenghu Zhou

The penalty function method has recently been studied as an effective approach for handling constraints, which imposes constraints penalties on the objective to transform the constrained problem into an unconstrained one.

Safe Exploration

MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data

no code implementations5 Jun 2024 Jianping Zhou, Bin Lu, Zhanyu Liu, Siyu Pan, Xuejun Feng, Hua Wei, Guanjie Zheng, Xinbing Wang, Chenghu Zhou

Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data.

Decision Making Decoder +2

CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection

1 code implementation26 May 2024 Lin Zhu, Yifeng Yang, Qinying Gu, Xinbing Wang, Chenghu Zhou, Nanyang Ye

In this paper, we propose a novel objective function of OOD detection that also serves to improve OOD generalization.

General Knowledge

RepEval: Effective Text Evaluation with LLM Representation

no code implementations30 Apr 2024 Shuqian Sheng, Yi Xu, Tianhang Zhang, Zanwei Shen, Luoyi Fu, Jiaxin Ding, Lei Zhou, Xiaoying Gan, Xinbing Wang, Chenghu Zhou

Besides, previous LLM-based metrics ignore the fact that, within the space of LLM representations, there exist direction vectors that indicate the estimation of text quality.

Characterizing the Influence of Topology on Graph Learning Tasks

no code implementations11 Apr 2024 Kailong Wu, Yule Xie, Jiaxin Ding, Yuxiang Ren, Luoyi Fu, Xinbing Wang, Chenghu Zhou

Graph neural networks (GNN) have achieved remarkable success in a wide range of tasks by encoding features combined with topology to create effective representations.

Graph Learning Stochastic Block Model

Temporal Generalization Estimation in Evolving Graphs

no code implementations7 Apr 2024 Bin Lu, Tingyan Ma, Xiaoying Gan, Xinbing Wang, Yunqiang Zhu, Chenghu Zhou, Shiyu Liang

In synthetic random graphs, we further refine the former lower bound to show the inevitable distortion over time and empirically observe that Smart achieves good estimation performance.

Attribute Graph Reconstruction

Entity Alignment with Unlabeled Dangling Cases

no code implementations16 Mar 2024 Hang Yin, Dong Ding, Liyao Xiang, Yuheng He, Yihan Wu, Xinbing Wang, Chenghu Zhou

We investigate the entity alignment problem with unlabeled dangling cases, meaning that there are entities in the source or target graph having no counterparts in the other, and those entities remain unlabeled.

Entity Alignment Representation Learning

Label Informed Contrastive Pretraining for Node Importance Estimation on Knowledge Graphs

1 code implementation26 Feb 2024 Tianyu Zhang, Chengbin Hou, Rui Jiang, Xuegong Zhang, Chenghu Zhou, Ke Tang, Hairong Lv

Considering the NIE problem, LICAP adopts a novel sampling strategy called top nodes preferred hierarchical sampling to first group all interested nodes into a top bin and a non-top bin based on node importance scores, and then divide the nodes within top bin into several finer bins also based on the scores.

Contrastive Learning Graph Attention +1

Graph Parsing Networks

1 code implementation22 Feb 2024 Yunchong Song, Siyuan Huang, Xinbing Wang, Chenghu Zhou, Zhouhan Lin

GPN benefits from the discrete assignments generated by the graph parsing algorithm, allowing good memory efficiency while preserving node information intact.

Graph Classification Graph Reconstruction +2

G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection

1 code implementation7 Feb 2024 Fan Wu, Jinling Gao, Lanqing Hong, Xinbing Wang, Chenghu Zhou, Nanyang Ye

To address this issue, we propose the Generalizable loss (G-loss), which is an OoD-aware objective, preventing NAS from over-fitting by using gradient descent to optimize parameters not only on a subset of easy-to-learn features but also the remaining predictive features for generalization, and the overall framework is named G-NAS.

Domain Generalization Neural Architecture Search +2

Crafter: Facial Feature Crafting against Inversion-based Identity Theft on Deep Models

1 code implementation14 Jan 2024 Shiming Wang, Zhe Ji, Liyao Xiang, Hao Zhang, Xinbing Wang, Chenghu Zhou, Bo Li

However, such methods can not defend against adaptive attacks, in which an attacker takes a countermove against a known defence strategy.

Domain Invariant Learning for Gaussian Processes and Bayesian Exploration

1 code implementation18 Dec 2023 Xilong Zhao, Siyuan Bian, Yaoyun Zhang, Yuliang Zhang, Qinying Gu, Xinbing Wang, Chenghu Zhou, Nanyang Ye

We further demonstrate the effectiveness of the DIL-GP Bayesian optimization method on a PID parameters tuning experiment for a quadrotor.

Bayesian Optimization Gaussian Processes

HuRef: HUman-REadable Fingerprint for Large Language Models

1 code implementation8 Dec 2023 Boyi Zeng, Lizheng Wang, Yuncong Hu, Yi Xu, Chenghu Zhou, Xinbing Wang, Yu Yu, Zhouhan Lin

In this study, we introduce HuRef, a human-readable fingerprint for LLMs that uniquely identifies the base model without interfering with training or exposing model parameters to the public.

Towards Controlled Table-to-Text Generation with Scientific Reasoning

no code implementations8 Dec 2023 Zhixin Guo, Jianping Zhou, Jiexing Qi, Mingxuan Yan, Ziwei He, Guanjie Zheng, Zhouhan Lin, Xinbing Wang, Chenghu Zhou

The sheer volume of scientific experimental results and complex technical statements, often presented in tabular formats, presents a formidable barrier to individuals acquiring preferred information.

Table-to-Text Generation

Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus

1 code implementation22 Nov 2023 Tianhang Zhang, Lin Qiu, Qipeng Guo, Cheng Deng, Yue Zhang, Zheng Zhang, Chenghu Zhou, Xinbing Wang, Luoyi Fu

Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields.

Hallucination Retrieval

Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation

no code implementations29 Aug 2023 Yi Xu, Junjie Ou, Hui Xu, Luoyi Fu, Lei Zhou, Xinbing Wang, Chenghu Zhou

To this end, we investigate the limits of historical information for temporal knowledge graph extrapolation and propose a new event forecasting model called Contrastive Event Network (CENET) based on a novel training framework of historical contrastive learning.

Contrastive Learning Knowledge Graphs

Graph Out-of-Distribution Generalization with Controllable Data Augmentation

no code implementations16 Aug 2023 Bin Lu, Xiaoying Gan, Ze Zhao, Shiyu Liang, Luoyi Fu, Xinbing Wang, Chenghu Zhou

The spurious correlations over hybrid distribution deviation degrade the performance of previous GNN methods and show large instability among different datasets.

Data Augmentation Graph Classification +3

Exploring and Verbalizing Academic Ideas by Concept Co-occurrence

1 code implementation4 Jun 2023 Yi Xu, Shuqian Sheng, Bo Xue, Luoyi Fu, Xinbing Wang, Chenghu Zhou

The results demonstrate that our system has broad prospects and can assist researchers in expediting the process of discovering new ideas.

Language Modelling Link Prediction

Prediction with Incomplete Data under Agnostic Mask Distribution Shift

no code implementations18 May 2023 Yichen Zhu, Jian Yuan, Bo Jiang, Tao Lin, Haiming Jin, Xinbing Wang, Chenghu Zhou

We focus on the case where the underlying joint distribution of complete features and label is invariant, but the missing pattern, i. e., mask distribution may shift agnostically between training and testing.

Missing Values

Covidia: COVID-19 Interdisciplinary Academic Knowledge Graph

no code implementations14 Apr 2023 Cheng Deng, Jiaxin Ding, Luoyi Fu, Weinan Zhang, Xinbing Wang, Chenghu Zhou

In this work, we propose Covidia, COVID-19 interdisciplinary academic knowledge graph to bridge the gap between knowledge of COVID-19 on different domains.

Classification Contrastive Learning +2

PK-Chat: Pointer Network Guided Knowledge Driven Generative Dialogue Model

2 code implementations2 Apr 2023 Cheng Deng, Bo Tong, Luoyi Fu, Jiaxin Ding, Dexing Cao, Xinbing Wang, Chenghu Zhou

In the research of end-to-end dialogue systems, using real-world knowledge to generate natural, fluent, and human-like utterances with correct answers is crucial.

Knowledge Graphs Language Modelling +1

Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset

1 code implementation19 Feb 2023 Jiexing Qi, Shuhao Li, Zhixin Guo, Yusheng Huang, Chenghu Zhou, Weinan Zhang, Xinbing Wang, Zhouhan Lin

In this work, we first collect a large-scale institution name normalization dataset LoT-insts1, which contains over 25k classes that exhibit a naturally long-tailed distribution.

Long-tail Learning open-set classification +4

Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing

1 code implementation3 Feb 2023 Yunchong Song, Chenghu Zhou, Xinbing Wang, Zhouhan Lin

This is achieved by aligning the hierarchy of the rooted-tree of a central node with the ordered neurons in its node representation.

Node Classification

KnowledgeShovel: An AI-in-the-Loop Document Annotation System for Scientific Knowledge Base Construction

1 code implementation6 Oct 2022 Shao Zhang, Yuting Jia, Hui Xu, Dakuo Wang, Toby Jia-Jun Li, Ying Wen, Xinbing Wang, Chenghu Zhou

Constructing a comprehensive, accurate, and useful scientific knowledge base is crucial for human researchers synthesizing scientific knowledge and for enabling Al-driven scientific discovery.

scientific discovery

Disentangled Graph Contrastive Learning for Review-based Recommendation

no code implementations4 Sep 2022 Yuyang Ren, Haonan Zhang, Qi Li, Luoyi Fu, Jiaxin Ding, Xinde Cao, Xinbing Wang, Chenghu Zhou

In review-based recommendation methods, review data is considered as auxiliary information that can improve the quality of learned user/item or interaction representations for the user rating prediction task.

Contrastive Learning Recommendation Systems

RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

1 code implementation14 May 2022 Jiexing Qi, Jingyao Tang, Ziwei He, Xiangpeng Wan, Yu Cheng, Chenghu Zhou, Xinbing Wang, Quanshi Zhang, Zhouhan Lin

Our model can incorporate almost all types of existing relations in the literature, and in addition, we propose introducing co-reference relations for the multi-turn scenario.

Dialogue State Tracking Text-To-SQL

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