Search Results for author: Zihan Wang

Found 40 papers, 18 papers with code

“Average” Approximates “First Principal Component”? An Empirical Analysis on Representations from Neural Language Models

no code implementations EMNLP 2021 Zihan Wang, chengyu dong, Jingbo Shang

In this paper, we present an empirical property of these representations—”average” approximates “first principal component”.

Esports Data-to-commentary Generation on Large-scale Data-to-text Dataset

no code implementations21 Dec 2022 Zihan Wang, Naoki Yoshinaga

Therefore, in this study, we introduce a task of generating game commentaries from structured data records to address the problem.

League of Legends

Reconstructing Training Data from Model Gradient, Provably

no code implementations7 Dec 2022 Zihan Wang, Jason Lee, Qi Lei

Understanding when and how much a model gradient leaks information about the training sample is an important question in privacy.

Federated Learning Tensor Decomposition

Multilingual Speech Emotion Recognition With Multi-Gating Mechanism and Neural Architecture Search

no code implementations31 Oct 2022 Zihan Wang, Qi Meng, HaiFeng Lan, Xinrui Zhang, Kehao Guo, Akshat Gupta

While Speech Emotion Recognition (SER) is a common application for popular languages, it continues to be a problem for low-resourced languages, i. e., languages with no pretrained speech-to-text recognition models.

Neural Architecture Search Speech Emotion Recognition

Waveformer: Linear-Time Attention with Forward and Backward Wavelet Transform

no code implementations5 Oct 2022 Yufan Zhuang, Zihan Wang, Fangbo Tao, Jingbo Shang

We propose Waveformer that learns attention mechanism in the wavelet coefficient space, requires only linear time complexity, and enjoys universal approximating power.

M^4I: Multi-modal Models Membership Inference

1 code implementation15 Sep 2022 Pingyi Hu, Zihan Wang, Ruoxi Sun, Hu Wang, Minhui Xue

To achieve this, we propose Multi-modal Models Membership Inference (M^4I) with two attack methods to infer the membership status, named metric-based (MB) M^4I and feature-based (FB) M^4I, respectively.

Image Captioning Inference Attack +2

CV 3315 Is All You Need : Semantic Segmentation Competition

1 code implementation25 Jun 2022 Akide Liu, Zihan Wang

This competition focus on Urban-Sense Segmentation based on the vehicle camera view.

Semantic Segmentation

Debiasing Learning for Membership Inference Attacks Against Recommender Systems

1 code implementation24 Jun 2022 Zihan Wang, Na Huang, Fei Sun, Pengjie Ren, Zhumin Chen, Hengliang Luo, Maarten de Rijke, Zhaochun Ren

To address the above limitations, we propose a Debiasing Learning for Membership Inference Attacks against recommender systems (DL-MIA) framework that has four main components: (1) a difference vector generator, (2) a disentangled encoder, (3) a weight estimator, and (4) an attack model.

Recommendation Systems

SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space

no code implementations4 Jun 2022 Zihan Wang, Ruimin Chen, Mengxuan Liu, Guanfang Dong, Anup Basu

We propose a method SPGNet for 3D human pose estimation that mixes multi-dimensional re-projection into supervised learning.

3D Human Pose Estimation

Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition

1 code implementation24 May 2022 Zihan Wang, Kewen Zhao, Zilong Wang, Jingbo Shang

Fine-tuning pre-trained language models has recently become a common practice in building NLP models for various tasks, especially few-shot tasks.

Few-shot NER Language Modelling +1

WeDef: Weakly Supervised Backdoor Defense for Text Classification

no code implementations24 May 2022 Lesheng Jin, Zihan Wang, Jingbo Shang

Inspired by this observation, in WeDef, we define the reliability of samples based on whether the predictions of the weak classifier agree with their labels in the poisoned training set.

Classification text-classification +1

Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking

1 code implementation ACL 2022 Jinyu Guo, Kai Shuang, Jijie Li, Zihan Wang, Yixuan Liu

However, no matter how the dialogue history is used, each existing model uses its own consistent dialogue history during the entire state tracking process, regardless of which slot is updated.

Dialogue State Tracking

Effectively Using Long and Short Sessions for Multi-Session-based Recommendations

no code implementations9 May 2022 Zihan Wang, Gang Wu, Yan Wang

The RNN often used in previous work is not suitable to process short sessions, because RNN only focuses on the sequential relationship, which we find is not the only relationship between items in short sessions.

Session-Based Recommendations

HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification

1 code implementation28 Apr 2022 Zihan Wang, Peiyi Wang, Tianyu Liu, Binghuai Lin, Yunbo Cao, Zhifang Sui, Houfeng Wang

However, in this paradigm, there exists a huge gap between the classification tasks with sophisticated label hierarchy and the masked language model (MLM) pretraining tasks of PLMs and thus the potentials of PLMs can not be fully tapped.

Classification Language Modelling +4

Weakly Supervised Correspondence Learning

no code implementations2 Mar 2022 Zihan Wang, Zhangjie Cao, Yilun Hao, Dorsa Sadigh

Correspondence learning is a fundamental problem in robotics, which aims to learn a mapping between state, action pairs of agents of different dynamics or embodiments.

Learning from Imperfect Demonstrations via Adversarial Confidence Transfer

no code implementations7 Feb 2022 Zhangjie Cao, Zihan Wang, Dorsa Sadigh

Existing learning from demonstration algorithms usually assume access to expert demonstrations.

An Interactive Visualization Tool for Understanding Active Learning

1 code implementation9 Nov 2021 Zihan Wang, Jialin Lu, Oliver Snow, Martin Ester

Despite recent progress in artificial intelligence and machine learning, many state-of-the-art methods suffer from a lack of explainability and transparency.

Active Learning BIG-bench Machine Learning

Membership Inference Attacks Against Recommender Systems

1 code implementation16 Sep 2021 Minxing Zhang, Zhaochun Ren, Zihan Wang, Pengjie Ren, Zhumin Chen, Pengfei Hu, Yang Zhang

In this paper, we make the first attempt on quantifying the privacy leakage of recommender systems through the lens of membership inference.

Recommendation Systems

Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking

no code implementations ACL 2021 Jinyu Guo, Kai Shuang, Jijie Li, Zihan Wang

However, the overwhelming majority of the slots in each turn should simply inherit the slot values from the previous turn.

Dialogue State Tracking

UCPhrase: Unsupervised Context-aware Quality Phrase Tagging

2 code implementations28 May 2021 Xiaotao Gu, Zihan Wang, Zhenyu Bi, Yu Meng, Liyuan Liu, Jiawei Han, Jingbo Shang

Training a conventional neural tagger based on silver labels usually faces the risk of overfitting phrase surface names.

Keyphrase Extraction Language Modelling +2

XCrossNet: Feature Structure-Oriented Learning for Click-Through Rate Prediction

1 code implementation22 Apr 2021 Runlong Yu, Yuyang Ye, Qi Liu, Zihan Wang, Chunfeng Yang, Yucheng Hu, Enhong Chen

Motivated by this, we propose a novel Extreme Cross Network, abbreviated XCrossNet, which aims at learning dense and sparse feature interactions in an explicit manner.

Click-Through Rate Prediction Feature Engineering +1

"Average" Approximates "First Principal Component"? An Empirical Analysis on Representations from Neural Language Models

1 code implementation18 Apr 2021 Zihan Wang, chengyu dong, Jingbo Shang

In this paper, we present an empirical property of these representations -- "average" approximates "first principal component".

Low-Power Wireless Wearable ECG Monitoring Chestbelt Based on Ferroelectric Microprocessor

no code implementations6 Nov 2020 Zhendong Ai, Zihan Wang, Wei Cui

The ECG monitoring device, abbreviated as ECGM, is designed based on ferroelectric microprocessor which provides ultra-low power consumption and contains four parts-MCU, BLE, Sensors and Power.

Emora: An Inquisitive Social Chatbot Who Cares For You

no code implementations10 Sep 2020 Sarah E. Finch, James D. Finch, Ali Ahmadvand, Ingyu, Choi, Xiangjue Dong, Ruixiang Qi, Harshita Sahijwani, Sergey Volokhin, Zihan Wang, ZiHao Wang, Jinho D. Choi

Inspired by studies on the overwhelming presence of experience-sharing in human-human conversations, Emora, the social chatbot developed by Emory University, aims to bring such experience-focused interaction to the current field of conversational AI.

Chatbot intent-classification +1

Cross-Lingual Ability of Multilingual BERT: An Empirical Study

no code implementations ICLR 2020 Karthikeyan K, Zihan Wang, Stephen Mayhew, Dan Roth

Recent work has exhibited the surprising cross-lingual abilities of multilingual BERT (M-BERT) -- surprising since it is trained without any cross-lingual objective and with no aligned data.

named-entity-recognition Named Entity Recognition +1

Discriminative Topic Mining via Category-Name Guided Text Embedding

1 code implementation20 Aug 2019 Yu Meng, Jiaxin Huang, Guangyuan Wang, Zihan Wang, Chao Zhang, Yu Zhang, Jiawei Han

We propose a new task, discriminative topic mining, which leverages a set of user-provided category names to mine discriminative topics from text corpora.

Document Classification General Classification +3

Raw-to-End Name Entity Recognition in Social Media

1 code implementation14 Aug 2019 Liyuan Liu, Zihan Wang, Jingbo Shang, Dandong Yin, Heng Ji, Xiang Ren, Shaowen Wang, Jiawei Han

Our model neither requires the conversion from character sequences to word sequences, nor assumes tokenizer can correctly detect all word boundaries.

named-entity-recognition NER

ECG Identification under Exercise and Rest Situations via Various Learning Methods

no code implementations11 May 2019 Zihan Wang, Yaoguang Li, Wei Cui

By applying various existing learning methods to our ECG dataset, we find that current methods which can well support the identification of individuals under rests, do not suffice to present satisfying ECGID performance under exercise situations, therefore exposing the deficiency of existing ECG identification methods.

A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies

no code implementations11 Oct 2018 Homanga Bharadhwaj, Zihan Wang, Yoshua Bengio, Liam Paull

Learning effective visuomotor policies for robots purely from data is challenging, but also appealing since a learning-based system should not require manual tuning or calibration.


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