Search Results for author: Yichi Zhang

Found 63 papers, 38 papers with code

How Robust is Google's Bard to Adversarial Image Attacks?

1 code implementation21 Sep 2023 Yinpeng Dong, Huanran Chen, Jiawei Chen, Zhengwei Fang, Xiao Yang, Yichi Zhang, Yu Tian, Hang Su, Jun Zhu

By attacking white-box surrogate vision encoders or MLLMs, the generated adversarial examples can mislead Bard to output wrong image descriptions with a 22% success rate based solely on the transferability.

Adversarial Robustness Chatbot +1

Dynamic Time Warping for Lead-Lag Relationships in Lagged Multi-Factor Models

no code implementations15 Sep 2023 Yichi Zhang, Mihai Cucuringu, Alexander Y. Shestopaloff, Stefan Zohren

In multivariate time series systems, lead-lag relationships reveal dependencies between time series when they are shifted in time relative to each other.

Dynamic Time Warping Time Series

MACO: A Modality Adversarial and Contrastive Framework for Modality-missing Multi-modal Knowledge Graph Completion

1 code implementation13 Aug 2023 Yichi Zhang, Zhuo Chen, Wen Zhang

Nevertheless, existing methods emphasize the design of elegant KGC models to facilitate modality interaction, neglecting the real-life problem of missing modalities in KGs.

Multi-modal Knowledge Graph

Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment

1 code implementation30 Jul 2023 Zhuo Chen, Lingbing Guo, Yin Fang, Yichi Zhang, Jiaoyan Chen, Jeff Z. Pan, Yangning Li, Huajun Chen, Wen Zhang

As a crucial extension of entity alignment (EA), multi-modal entity alignment (MMEA) aims to identify identical entities across disparate knowledge graphs (KGs) by exploiting associated visual information.

 Ranked #1 on Multi-modal Entity Alignment on UMVM-oea-d-w-v2 (using extra training data)

Benchmarking Knowledge Graph Embeddings +2

CausE: Towards Causal Knowledge Graph Embedding

1 code implementation21 Jul 2023 Yichi Zhang, Wen Zhang

Knowledge graph embedding (KGE) focuses on representing the entities and relations of a knowledge graph (KG) into the continuous vector spaces, which can be employed to predict the missing triples to achieve knowledge graph completion (KGC).

Disentanglement Knowledge Graph Completion +1

PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs

1 code implementation15 Jun 2023 Zhongkai Hao, Jiachen Yao, Chang Su, Hang Su, Ziao Wang, Fanzhi Lu, Zeyu Xia, Yichi Zhang, Songming Liu, Lu Lu, Jun Zhu

In addition to providing a standardized means of assessing performance, PINNacle also offers an in-depth analysis to guide future research, particularly in areas such as domain decomposition methods and loss reweighting for handling multi-scale problems and complex geometry.


Robust Detection of Lead-Lag Relationships in Lagged Multi-Factor Models

no code implementations11 May 2023 Yichi Zhang, Mihai Cucuringu, Alexander Y. Shestopaloff, Stefan Zohren

In multivariate time series systems, key insights can be obtained by discovering lead-lag relationships inherent in the data, which refer to the dependence between two time series shifted in time relative to one another, and which can be leveraged for the purposes of control, forecasting or clustering.

Clustering Time Series

Towards Segment Anything Model (SAM) for Medical Image Segmentation: A Survey

1 code implementation5 May 2023 Yichi Zhang, Rushi Jiao

Due to the flexibility of prompting, foundation models have become the dominant force in the domains of natural language processing and image generation.

Benchmarking Image Generation +3

Modality-Aware Negative Sampling for Multi-modal Knowledge Graph Embedding

1 code implementation23 Apr 2023 Yichi Zhang, Mingyang Chen, Wen Zhang

Negative sampling (NS) is widely used in knowledge graph embedding (KGE), which aims to generate negative triples to make a positive-negative contrast during training.

Knowledge Graph Embedding Multi-modal Knowledge Graph

Mastering Asymmetrical Multiplayer Game with Multi-Agent Asymmetric-Evolution Reinforcement Learning

no code implementations20 Apr 2023 Chenglu Sun, Yichi Zhang, Yu Zhang, Ziling Lu, Jingbin Liu, Sijia Xu, Weidong Zhang

We propose asymmetric-evolution training (AET), a novel multi-agent reinforcement learning framework that can train multiple kinds of agents simultaneously in AMP game.

Multi-agent Reinforcement Learning reinforcement-learning

Revisiting the Evaluation of Image Synthesis with GANs

no code implementations4 Apr 2023 Mengping Yang, Ceyuan Yang, Yichi Zhang, Qingyan Bai, Yujun Shen, Bo Dai

A good metric, which promises a reliable comparison between solutions, is essential to a well-defined task.

Image Generation

Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving

1 code implementation CVPR 2023 Zijian Zhu, Yichi Zhang, Hai Chen, Yinpeng Dong, Shu Zhao, Wenbo Ding, Jiachen Zhong, Shibao Zheng

However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems.

3D Object Detection Adversarial Robustness +2

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

2 code implementations16 Mar 2023 Huanran Chen, Yichi Zhang, Yinpeng Dong, Jun Zhu

Transfer-based adversarial attacks attract tremendous attention as they can identify the weaknesses of deep learning models in a black-box manner.

Image Classification object-detection +1

To Make Yourself Invisible with Adversarial Semantic Contours

no code implementations1 Mar 2023 Yichi Zhang, Zijian Zhu, Hang Su, Jun Zhu, Shibao Zheng, Yuan He, Hui Xue

In this paper, we propose Adversarial Semantic Contour (ASC), an MAP estimate of a Bayesian formulation of sparse attack with a deceived prior of object contour.

Autonomous Driving object-detection +1

DA-VEGAN: Differentiably Augmenting VAE-GAN for microstructure reconstruction from extremely small data sets

no code implementations17 Feb 2023 Yichi Zhang, Paul Seibert, Alexandra Otto, Alexander Raßloff, Marreddy Ambati, Markus Kästner

Microstructure reconstruction is an important and emerging field of research and an essential foundation to improving inverse computational materials engineering (ICME).

Data Augmentation

Binarized Neural Machine Translation

no code implementations9 Feb 2023 Yichi Zhang, Ankush Garg, Yuan Cao, Łukasz Lew, Behrooz Ghorbani, Zhiru Zhang, Orhan Firat

In this work, we propose a novel binarization technique for Transformers applied to machine translation (BMT), the first of its kind.

Binarization Machine Translation +2

MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid

1 code implementation29 Dec 2022 Zhuo Chen, Jiaoyan Chen, Wen Zhang, Lingbing Guo, Yin Fang, Yufeng Huang, Yichi Zhang, Yuxia Geng, Jeff Z. Pan, Wenting Song, Huajun Chen

Multi-modal entity alignment (MMEA) aims to discover identical entities across different knowledge graphs (KGs) whose entities are associated with relevant images.

 Ranked #1 on Entity Alignment on FBYG15k (using extra training data)

Knowledge Graphs Multi-modal Entity Alignment

Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications

1 code implementation15 Nov 2022 Zhongkai Hao, Songming Liu, Yichi Zhang, Chengyang Ying, Yao Feng, Hang Su, Jun Zhu

Recent work shows that it provides potential benefits for machine learning models by incorporating the physical prior and collected data, which makes the intersection of machine learning and physics become a prevailing paradigm.

Physics-informed machine learning

Tele-Knowledge Pre-training for Fault Analysis

1 code implementation20 Oct 2022 Zhuo Chen, Wen Zhang, Yufeng Huang, Mingyang Chen, Yuxia Geng, Hongtao Yu, Zhen Bi, Yichi Zhang, Zhen Yao, Wenting Song, Xinliang Wu, Yi Yang, Mingyi Chen, Zhaoyang Lian, YingYing Li, Lei Cheng, Huajun Chen

In this work, we share our experience on tele-knowledge pre-training for fault analysis, a crucial task in telecommunication applications that requires a wide range of knowledge normally found in both machine log data and product documents.

Language Modelling

Knowledge Graph Completion with Pre-trained Multimodal Transformer and Twins Negative Sampling

no code implementations15 Sep 2022 Yichi Zhang, Wen Zhang

Twins negative sampling is suitable for multimodal scenarios and could align different embeddings for entities.

Link Prediction

Perturbation Analysis of Randomized SVD and its Applications to High-dimensional Statistics

no code implementations19 Mar 2022 Yichi Zhang, Minh Tang

We first derive upper bounds for the $\ell_2$ (spectral norm) and $\ell_{2\to\infty}$ (maximum row-wise $\ell_2$ norm) distances between the approximate singular vectors of $\hat{\mathbf{M}}$ and the true singular vectors of the signal matrix $\mathbf{M}$.

Community Detection Matrix Completion

Understanding Hyperdimensional Computing for Parallel Single-Pass Learning

1 code implementation10 Feb 2022 Tao Yu, Yichi Zhang, Zhiru Zhang, Christopher De Sa

Using representation theory, we characterize which similarity matrices can be "expressed" by finite group VSA hypervectors, and we show how these VSAs can be constructed.

Uncertainty-Guided Mutual Consistency Learning for Semi-Supervised Medical Image Segmentation

no code implementations5 Dec 2021 Yichi Zhang, Rushi Jiao, Qingcheng Liao, Dongyang Li, Jicong Zhang

In this paper, we propose a novel uncertainty-guided mutual consistency learning framework to effectively exploit unlabeled data by integrating intra-task consistency learning from up-to-date predictions for self-ensembling and cross-task consistency learning from task-level regularization to exploit geometric shape information.

Brain Tumor Segmentation Image Segmentation +3

PokeBNN: A Binary Pursuit of Lightweight Accuracy

1 code implementation CVPR 2022 Yichi Zhang, Zhiru Zhang, Lukasz Lew

In order to enable joint optimization of the cost together with accuracy, we define arithmetic computation effort (ACE), a hardware- and energy-inspired cost metric for quantized and binarized networks.


Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework

1 code implementation28 Oct 2021 Lifan Yuan, Yichi Zhang, Yangyi Chen, Wei Wei

In this paper, we instantiate our framework with an attack algorithm named Textual Projected Gradient Descent (T-PGD).

Adversarial Attack Language Modelling

Adversarial Semantic Contour for Object Detection

no code implementations ICML Workshop AML 2021 Yichi Zhang, Zijian Zhu, Xiao Yang, Jun Zhu

To address this issue, we propose a novel method of Adversarial Semantic Contour (ASC) guided by object contour as prior.

object-detection Object Detection

Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding

1 code implementation Findings (EMNLP) 2021 Shane Storks, Qiaozi Gao, Yichi Zhang, Joyce Chai

However, evaluations only based on end task performance shed little light on machines' true ability in language understanding and reasoning.

U-Net-and-a-half: Convolutional network for biomedical image segmentation using multiple expert-driven annotations

1 code implementation10 Aug 2021 Yichi Zhang, Jesper Kers, Clarissa A. Cassol, Joris J. Roelofs, Najia Idrees, Alik Farber, Samir Haroon, Kevin P. Daly, Suvranu Ganguli, Vipul C. Chitalia, Vijaya B. Kolachalama

If more than a single expert is involved in the annotation of the same images, then the inter-expert agreement is not necessarily perfect, and no single expert annotation can precisely capture the so-called ground truth of the regions of interest on all images.

Image Segmentation Semantic Segmentation +1

Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining

1 code implementation ICCV 2021 Xunlin Zhan, Yangxin Wu, Xiao Dong, Yunchao Wei, Minlong Lu, Yichi Zhang, Hang Xu, Xiaodan Liang

In this paper, we investigate a more realistic setting that aims to perform weakly-supervised multi-modal instance-level product retrieval among fine-grained product categories.


Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making

1 code implementation ACL 2021 Zijun Yao, Chengjiang Li, Tiansi Dong, Xin Lv, Jifan Yu, Lei Hou, Juanzi Li, Yichi Zhang, Zelin Dai

Using a set of comparison features and a limited amount of annotated data, KAT Induction learns an efficient decision tree that can be interpreted by generating entity matching rules whose structure is advocated by domain experts.

Decision Making Language Modelling +1

Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring

1 code implementation Findings (ACL) 2021 Yichi Zhang, Joyce Chai

On the ALFRED benchmark for task learning, the published state-of-the-art system only achieves a task success rate of less than 10% in an unseen environment, compared to the human performance of over 90%.

Improving Conversational Recommendation System by Pretraining on Billions Scale of Knowledge Graph

no code implementations30 Apr 2021 Chi-Man Wong, Fan Feng, Wen Zhang, Chi-Man Vong, Hui Chen, Yichi Zhang, Peng He, Huan Chen, Kun Zhao, Huajun Chen

We first construct a billion-scale conversation knowledge graph (CKG) from information about users, items and conversations, and then pretrain CKG by introducing knowledge graph embedding method and graph convolution network to encode semantic and structural information respectively. To make the CTR prediction model sensible of current state of users and the relationship between dialogues and items, we introduce user-state and dialogue-interaction representations based on pre-trained CKG and propose K-DCN. In K-DCN, we fuse the user-state representation, dialogue-interaction representation and other normal feature representations via deep cross network, which will give the rank of candidate items to be recommended. We experimentally prove that our proposal significantly outperforms baselines and show it's real application in Alime.

Click-Through Rate Prediction Knowledge Graph Embedding +1

Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability

1 code implementation EMNLP 2021 Xin Lv, Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu, Yichi Zhang, Zelin Dai

However, we find in experiments that many paths given by these models are actually unreasonable, while little works have been done on interpretability evaluation for them.

Benchmarking Link Prediction

Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation

1 code implementation19 Mar 2021 Zhe Xie, Chengxuan Liu, Yichi Zhang, Hongtao Lu, Dong Wang, Yue Ding

To solve the above problem, in this work, we propose a novel method called Adversarial and Contrastive Variational Autoencoder (ACVAE) for sequential recommendation.

Collaborative Filtering Sequential Recommendation

Dual-Task Mutual Learning for Semi-Supervised Medical Image Segmentation

1 code implementation8 Mar 2021 Yichi Zhang, Jicong Zhang

The success of deep learning methods in medical image segmentation tasks usually requires a large amount of labeled data.

Image Segmentation Semantic Segmentation +1

Exact Recovery of Community Structures Using DeepWalk and Node2vec

no code implementations18 Jan 2021 Yichi Zhang, Minh Tang

Random-walk based network embedding algorithms like DeepWalk and node2vec are widely used to obtain Euclidean representation of the nodes in a network prior to performing downstream inference tasks.

Clustering Community Detection +1

Exploiting Shared Knowledge from Non-COVID Lesions for Annotation-Efficient COVID-19 CT Lung Infection Segmentation

no code implementations31 Dec 2020 Yichi Zhang, Qingcheng Liao, Lin Yuan, He Zhu, Jiezhen Xing, Jicong Zhang

In this paper, we propose a novel relation-driven collaborative learning model to exploit shared knowledge from non-COVID lesions for annotation-efficient COVID-19 CT lung infection segmentation.

Computed Tomography (CT) Lesion Segmentation

Cascaded Convolutional Neural Network for Automatic Myocardial Infarction Segmentation from Delayed-Enhancement Cardiac MRI

no code implementations28 Dec 2020 Yichi Zhang

Automatic segmentation of myocardial contours and relevant areas like infraction and no-reflow is an important step for the quantitative evaluation of myocardial infarction.

AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?

1 code implementation28 Oct 2020 Jun Ma, Yao Zhang, Song Gu, Cheng Zhu, Cheng Ge, Yichi Zhang, Xingle An, Congcong Wang, Qiyuan Wang, Xin Liu, Shucheng Cao, Qi Zhang, Shangqing Liu, Yunpeng Wang, Yuhui Li, Jian He, Xiaoping Yang

With the unprecedented developments in deep learning, automatic segmentation of main abdominal organs seems to be a solved problem as state-of-the-art (SOTA) methods have achieved comparable results with inter-rater variability on many benchmark datasets.

Continual Learning Organ Segmentation +1

Bridging 2D and 3D Segmentation Networks for Computation Efficient Volumetric Medical Image Segmentation: An Empirical Study of 2.5D Solutions

no code implementations13 Oct 2020 Yichi Zhang, Qingcheng Liao, Le Ding, Jicong Zhang

Despite these works lead to improvements on a variety of segmentation tasks, to the best of our knowledge, there has not previously been a large-scale empirical comparison of these methods.

Image Segmentation Semantic Segmentation +1

Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph

1 code implementation EMNLP 2020 Xin Lv, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu, Wei zhang, Yichi Zhang, Hao Kong, Suhui Wu

On the one hand, sparse KGs contain less information, which makes it difficult for the model to choose correct paths.

A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning

1 code implementation EMNLP 2020 Yichi Zhang, Zhijian Ou, Huixin Wang, Junlan Feng

In this paper we aim at alleviating the reliance on belief state labels in building end-to-end dialog systems, by leveraging unlabeled dialog data towards semi-supervised learning.

End-To-End Dialogue Modelling

Paraphrase Augmented Task-Oriented Dialog Generation

1 code implementation ACL 2020 Silin Gao, Yichi Zhang, Zhijian Ou, Zhou Yu

Neural generative models have achieved promising performance on dialog generation tasks if given a huge data set.

Data Augmentation Response Generation

Covariance Estimation for Matrix-valued Data

no code implementations11 Apr 2020 Yichi Zhang, Weining Shen, Dehan Kong

Covariance estimation for matrix-valued data has received an increasing interest in applications.

Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations

1 code implementation ICLR 2020 Yichi Zhang, Ritchie Zhao, Weizhe Hua, Nayun Xu, G. Edward Suh, Zhiru Zhang

The proposed approach is applicable to a variety of DNN architectures and significantly reduces the computational cost of DNN execution with almost no accuracy loss.


SAU-Net: Efficient 3D Spine MRI Segmentation Using Inter-Slice Attention

no code implementations MIDL 2019 Yichi Zhang, Lin Yuan, Yujia Wang, Jicong Zhang

Accurate segmentation of spine Magnetic Resonance Imaging (MRI) is highly demanded in morphological research, quantitative analysis, and diseases identification, such as spinal canal stenosis, disc herniation and degeneration.

MRI segmentation

Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context

5 code implementations24 Nov 2019 Yichi Zhang, Zhijian Ou, Zhou Yu

Conversations have an intrinsic one-to-many property, which means that multiple responses can be appropriate for the same dialog context.

Data Augmentation End-To-End Dialogue Modelling

Meta-Learning with Dynamic-Memory-Based Prototypical Network for Few-Shot Event Detection

1 code implementation25 Oct 2019 Shumin Deng, Ningyu Zhang, Jiaojian Kang, Yichi Zhang, Wei zhang, Huajun Chen

Differing from vanilla prototypical networks simply computing event prototypes by averaging, which only consume event mentions once, our model is more robust and is capable of distilling contextual information from event mentions for multiple times due to the multi-hop mechanism of DMNs.

Event Detection Event Extraction +1

Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models

1 code implementation EACL 2021 Qingyang Wu, Yichi Zhang, Yu Li, Zhou Yu

Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks.

Language Modelling Response Generation

Bayesian Optimization for Materials Design with Mixed Quantitative and Qualitative Variables

no code implementations3 Oct 2019 Yichi Zhang, Daniel Apley, Wei Chen

We present in this paper the integration of a novel latent-variable (LV) approach for mixed-variable GP modeling with the BO framework for materials design.

Bayesian Optimization

Data-Centric Mixed-Variable Bayesian Optimization For Materials Design

no code implementations4 Jul 2019 Akshay Iyer, Yichi Zhang, Aditya Prasad, Siyu Tao, Yixing Wang, Linda Schadler, L Catherine Brinson, Wei Chen

To this end, we present a data-centric, mixed-variable Bayesian Optimization framework that integrates data from literature, experiments, and simulations for knowledge discovery and computational materials design.

Bayesian Optimization Navigate

Elastic CRFs for Open-ontology Slot Filling

no code implementations4 Nov 2018 Yinpei Dai, Yichi Zhang, Zhijian Ou, Yanmeng Wang, Junlan Feng

Second, the one-hot encoding of slot labels ignores the semantic meanings and relations for slots, which are implicit in their natural language descriptions.

slot-filling Slot Filling

Learning Sparse Structured Ensembles with SG-MCMC and Network Pruning

no code implementations ICLR 2018 Yichi Zhang, Zhijian Ou

An ensemble of neural networks is known to be more robust and accurate than an individual network, however usually with linearly-increased cost in both training and testing.

Language Modelling Network Pruning

Face Alignment Assisted by Head Pose Estimation

1 code implementation11 Jul 2015 Heng Yang, Wenxuan Mou, Yichi Zhang, Ioannis Patras, Hatice Gunes, Peter Robinson

In this paper we propose a supervised initialization scheme for cascaded face alignment based on explicit head pose estimation.

Face Alignment Head Pose Estimation

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