Search Results for author: Ge Zhang

Found 19 papers, 6 papers with code

Aligning Generative Language Models with Human Values

no code implementations Findings (NAACL) 2022 Ruibo Liu, Ge Zhang, Xinyu Feng, Soroush Vosoughi

Although current large-scale generative language models (LMs) can show impressive insights about factual knowledge, they do not exhibit similar success with respect to human values judgements (e. g., whether or not the generations of an LM are moral).

Text Generation Transfer Learning

A Comprehensive Survey of Graph-level Learning

1 code implementation14 Jan 2023 Zhenyu Yang, Ge Zhang, Jia Wu, Jian Yang, Quan Z. Sheng, Shan Xue, Chuan Zhou, Charu Aggarwal, Hao Peng, Wenbin Hu, Edwin Hancock, Pietro Li`o

Traditional approaches to learning a set of graphs tend to rely on hand-crafted features, such as substructures.

Graph Learning

CORGI-PM: A Chinese Corpus For Gender Bias Probing and Mitigation

1 code implementation1 Jan 2023 Ge Zhang, Yizhi Li, Yaoyao Wu, Linyuan Zhang, Chenghua Lin, Jiayi Geng, Shi Wang, Jie Fu

As natural language processing (NLP) for gender bias becomes a significant interdisciplinary topic, the prevalent data-driven techniques such as large-scale language models suffer from data inadequacy and biased corpus, especially for languages with insufficient resources such as Chinese.

HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models

1 code implementation5 Nov 2022 Yizhi Li, Ge Zhang, Bohao Yang, Chenghua Lin, Shi Wang, Anton Ragni, Jie Fu

In addition to verifying the existence of regional bias in LMs, we find that the biases on regional groups can be strongly influenced by the geographical clustering of the groups.

Fairness

1Cademy @ Causal News Corpus 2022: Leveraging Self-Training in Causality Classification of Socio-Political Event Data

1 code implementation4 Nov 2022 Adam Nik, Ge Zhang, Xingran Chen, Mingyu Li, Jie Fu

This paper details our participation in the Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE) workshop @ EMNLP 2022, where we take part in Subtask 1 of Shared Task 3.

1Cademy @ Causal News Corpus 2022: Enhance Causal Span Detection via Beam-Search-based Position Selector

1 code implementation31 Oct 2022 Xingran Chen, Ge Zhang, Adam Nik, Mingyu Li, Jie Fu

In this paper, we present our approach and empirical observations for Cause-Effect Signal Span Detection -- Subtask 2 of Shared task 3~\cite{tan-etal-2022-event} at CASE 2022.

Data Augmentation Language Modelling +1

Correlation between entropy and generalizability in a neural network

no code implementations5 Jul 2022 Ge Zhang

Although neural networks can solve very complex machine-learning problems, the theoretical reason for their generalizability is still not fully understood.

Graph-level Neural Networks: Current Progress and Future Directions

no code implementations31 May 2022 Ge Zhang, Jia Wu, Jian Yang, Shan Xue, Wenbin Hu, Chuan Zhou, Hao Peng, Quan Z. Sheng, Charu Aggarwal

To frame this survey, we propose a systematic taxonomy covering GLNNs upon deep neural networks, graph neural networks, and graph pooling.

Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attacks

no code implementations21 Nov 2021 Kaiyuan Liu, Xingyu Li, Yurui Lai, Ge Zhang, Hang Su, Jiachen Wang, Chunxu Guo, Jisong Guan, Yi Zhou

Despite its great success, deep learning severely suffers from robustness; that is, deep neural networks are very vulnerable to adversarial attacks, even the simplest ones.

Spectral Variability Augmented Sparse Unmixing of Hyperspectral Images

no code implementations19 Oct 2021 Ge Zhang, Shaohui Mei, Mingyang Ma, Yan Feng, Qian Du

Spectral unmixing (SU) expresses the mixed pixels existed in hyperspectral images as the product of endmember and abundance, which has been widely used in hyperspectral imagery analysis.

Spectral Reconstruction

StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects

no code implementations17 May 2021 Ge Zhang, Or Litany, Srinath Sridhar, Leonidas Guibas

We present StrobeNet, a method for category-level 3D reconstruction of articulating objects from one or more unposed RGB images.

3D Reconstruction

Tilting the playing field: Dynamical loss functions for machine learning

1 code implementation7 Feb 2021 Miguel Ruiz-Garcia, Ge Zhang, Samuel S. Schoenholz, Andrea J. Liu

In underparameterized networks, such dynamical loss functions can lead to successful training for networks that fail to find a deep minima of the standard cross-entropy loss.

BIG-bench Machine Learning

Diverse Melody Generation from Chinese Lyrics via Mutual Information Maximization

no code implementations7 Dec 2020 Ruibin Yuan, Ge Zhang, Anqiao Yang, Xinyue Zhang

In this paper, we propose to adapt the method of mutual information maximization into the task of Chinese lyrics conditioned melody generation to improve the generation quality and diversity.

CORAL: COde RepresentAtion Learning with Weakly-Supervised Transformers for Analyzing Data Analysis

no code implementations28 Aug 2020 Ge Zhang, Mike A. Merrill, Yang Liu, Jeffrey Heer, Tim Althoff

Large scale analysis of source code, and in particular scientific source code, holds the promise of better understanding the data science process, identifying analytical best practices, and providing insights to the builders of scientific toolkits.

Representation Learning

Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues

no code implementations17 Jun 2020 Jianrong Wang, Ge Zhang, Zhen-Yu Wu, XueWei Li, Li Liu

Compared with static views, abundant dynamic properties between video frames are beneficial to refined depth estimation, especially for dynamic objects.

Monocular Depth Estimation

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