Search Results for author: Cheng Zhang

Found 134 papers, 49 papers with code

MovieChats: Chat like Humans in a Closed Domain

no code implementations EMNLP 2020 Hui Su, Xiaoyu Shen, Zhou Xiao, Zheng Zhang, Ernie Chang, Cheng Zhang, Cheng Niu, Jie zhou

In this work, we take a close look at the movie domain and present a large-scale high-quality corpus with fine-grained annotations in hope of pushing the limit of movie-domain chatbots.

Chatbot Retrieval

Crossroads, Buildings and Neighborhoods: A Dataset for Fine-grained Location Recognition

1 code implementation NAACL 2022 Pei Chen, Haotian Xu, Cheng Zhang, Ruihong Huang

General domain Named Entity Recognition (NER) datasets like CoNLL-2003 mostly annotate coarse-grained location entities such as a country or a city.

named-entity-recognition Named Entity Recognition +1

Learned Causal Method Prediction

no code implementations7 Nov 2023 Shantanu Gupta, Cheng Zhang, Agrin Hilmkil

In this work, we propose CAusal Method Predictor (CAMP), a framework for predicting the best method for a given dataset.

Causal Discovery Causal Inference

ARTree: A Deep Autoregressive Model for Phylogenetic Inference

1 code implementation NeurIPS 2023 Tianyu Xie, Cheng Zhang

Designing flexible probabilistic models over tree topologies is important for developing efficient phylogenetic inference methods.

Density Estimation

Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?

1 code implementation8 Oct 2023 Cheng Zhang, Jianyi Cheng, Ilia Shumailov, George A. Constantinides, Yiren Zhao

In this work, we explore the statistical and learning properties of the LLM layer and attribute the bottleneck of LLM quantisation to numerical scaling offsets.

1D-CapsNet-LSTM: A Deep Learning-Based Model for Multi-Step Stock Index Forecasting

no code implementations3 Oct 2023 Cheng Zhang, Nilam Nur Amir Sjarif, Roslina Ibrahim

Given the superiority of capsule network (CapsNet) over CNN in various forecasting and classification tasks, this study investigates the potential of integrating a 1D CapsNet with an LSTM network for multi-step stock index forecasting.

Decision Making

Towards Causal Foundation Model: on Duality between Causal Inference and Attention

no code implementations1 Oct 2023 JiaQi Zhang, Joel Jennings, Cheng Zhang, Chao Ma

Foundation models have brought changes to the landscape of machine learning, demonstrating sparks of human-level intelligence across a diverse array of tasks.

Causal Inference

ProAgent: Building Proactive Cooperative AI with Large Language Models

no code implementations22 Aug 2023 Ceyao Zhang, Kaijie Yang, Siyi Hu, ZiHao Wang, Guanghe Li, Yihang Sun, Cheng Zhang, Zhaowei Zhang, Anji Liu, Song-Chun Zhu, Xiaojun Chang, Junge Zhang, Feng Yin, Yitao Liang, Yaodong Yang

Experimental evaluations conducted within the framework of \textit{Overcook-AI} unveil the remarkable performance superiority of ProAgent, outperforming five methods based on self-play and population-based training in cooperation with AI agents.

Semi-Implicit Variational Inference via Score Matching

1 code implementation19 Aug 2023 Longlin Yu, Cheng Zhang

Semi-implicit variational inference (SIVI) greatly enriches the expressiveness of variational families by considering implicit variational distributions defined in a hierarchical manner.

Bayesian Inference Denoising +1

All-in-one Multi-degradation Image Restoration Network via Hierarchical Degradation Representation

no code implementations6 Aug 2023 Cheng Zhang, Yu Zhu, Qingsen Yan, Jinqiu Sun, Yanning Zhang

To address this issue, we propose a novel All-in-one Multi-degradation Image Restoration Network (AMIRNet) that can effectively capture and utilize accurate degradation representation for image restoration.

Contrastive Learning Deblurring +3

BayesDAG: Gradient-Based Posterior Sampling for Causal Discovery

1 code implementation26 Jul 2023 Yashas Annadani, Nick Pawlowski, Joel Jennings, Stefan Bauer, Cheng Zhang, Wenbo Gong

Bayesian causal discovery aims to infer the posterior distribution over causal models from observed data, quantifying epistemic uncertainty and benefiting downstream tasks.

Causal Discovery Variational Inference

One for All: Unified Workload Prediction for Dynamic Multi-tenant Edge Cloud Platforms

1 code implementation2 Jun 2023 Shaoyuan Huang, Zheng Wang, Heng Zhang, Xiaofei Wang, Cheng Zhang, Wenyu Wang

In this paper, we propose an end-to-end framework with global pooling and static content awareness, DynEformer, to provide a unified workload prediction scheme for dynamic MT-ECP.

Time Series Time Series Prediction

OVO: Open-Vocabulary Occupancy

1 code implementation25 May 2023 Zhiyu Tan, ZiChao Dong, Cheng Zhang, Weikun Zhang, Hang Ji, Hao Li

Semantic occupancy prediction aims to infer dense geometry and semantics of surroundings for an autonomous agent to operate safely in the 3D environment.

Knowledge Distillation

Neural-PBIR Reconstruction of Shape, Material, and Illumination

no code implementations ICCV 2023 Cheng Sun, Guangyan Cai, Zhengqin Li, Kai Yan, Cheng Zhang, Carl Marshall, Jia-Bin Huang, Shuang Zhao, Zhao Dong

In the last stage, initialized by the neural predictions, we perform PBIR to refine the initial results and obtain the final high-quality reconstruction of object shape, material, and illumination.

Inverse Rendering Object Reconstruction

Understanding Causality with Large Language Models: Feasibility and Opportunities

no code implementations11 Apr 2023 Cheng Zhang, Stefan Bauer, Paul Bennett, Jiangfeng Gao, Wenbo Gong, Agrin Hilmkil, Joel Jennings, Chao Ma, Tom Minka, Nick Pawlowski, James Vaughan

We assess the ability of large language models (LLMs) to answer causal questions by analyzing their strengths and weaknesses against three types of causal question.

Decision Making

Automatic Generation of Multiple-Choice Questions

no code implementations25 Mar 2023 Cheng Zhang

Moreover, we present a novel approach to automatically generate adequate distractors for a given QAP.

Multiple-choice Part-Of-Speech Tagging +5

Causal Reasoning in the Presence of Latent Confounders via Neural ADMG Learning

1 code implementation22 Mar 2023 Matthew Ashman, Chao Ma, Agrin Hilmkil, Joel Jennings, Cheng Zhang

In this work, we further extend the existing body of work and develop a novel gradient-based approach to learning an ADMG with non-linear functional relations from observational data.

CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design

1 code implementation27 Feb 2023 Desi R. Ivanova, Joel Jennings, Tom Rainforth, Cheng Zhang, Adam Foster

We formalize the problem of contextual optimization through the lens of Bayesian experimental design and propose CO-BED -- a general, model-agnostic framework for designing contextual experiments using information-theoretic principles.

Experimental Design

Learnable Topological Features for Phylogenetic Inference via Graph Neural Networks

1 code implementation17 Feb 2023 Cheng Zhang

Structural information of phylogenetic tree topologies plays an important role in phylogenetic inference.

Graph Representation Learning

Causal-Discovery Performance of ChatGPT in the context of Neuropathic Pain Diagnosis

no code implementations24 Jan 2023 Ruibo Tu, Chao Ma, Cheng Zhang

ChatGPT has demonstrated exceptional proficiency in natural language conversation, e. g., it can answer a wide range of questions while no previous large language models can.

Causal Discovery

TokenHPE: Learning Orientation Tokens for Efficient Head Pose Estimation via Transformers

1 code implementation CVPR 2023 Cheng Zhang, Hai Liu, Yongjian Deng, Bochen Xie, Youfu Li

To leverage the observed findings, we propose a novel critical minority relationship-aware method based on the Transformer architecture in which the facial part relationships can be learned.

Head Pose Estimation

TransIFC: Invariant Cues-aware Feature Concentration Learning for Efficient Fine-grained Bird Image Classification

no code implementations TIP 2022 Hai Liu, Cheng Zhang, Yongjian Deng, Bochen Xie, Tingting Liu, Zhaoli Zhang, You-Fu Li

To this end, two novel modules are proposed to leverage the characteristics of bird images, namely, the hierarchy stage feature aggregation (HSFA) module and the feature in feature abstraction (FFA) module.

feature selection Fine-Grained Image Classification

WSC-Trans: A 3D network model for automatic multi-structural segmentation of temporal bone CT

no code implementations14 Nov 2022 Xin Hua, Zhijiang Du, Hongjian Yu, Jixin Ma, Fanjun Zheng, Cheng Zhang, Qiaohui Lu, Hui Zhao

Cochlear implantation is currently the most effective treatment for patients with severe deafness, but mastering cochlear implantation is extremely challenging because the temporal bone has extremely complex and small three-dimensional anatomical structures, and it is important to avoid damaging the corresponding structures when performing surgery.


Rhino: Deep Causal Temporal Relationship Learning With History-dependent Noise

no code implementations26 Oct 2022 Wenbo Gong, Joel Jennings, Cheng Zhang, Nick Pawlowski

Given the complexity of real-world relationships and the nature of observations in discrete time, causal discovery methods need to consider non-linear relations between variables, instantaneous effects and history-dependent noise (the change of noise distribution due to past actions).

Causal Discovery Time Series +2

Tag-Set-Sequence Learning for Generating Question-Answer Pairs

no code implementations20 Oct 2022 Cheng Zhang, Jie Wang

Transformer-based QG models can generate question-answer pairs (QAPs) with high qualities, but may also generate silly questions for certain texts.

named-entity-recognition Named Entity Recognition +3

Learn the Time to Learn: Replay Scheduling in Continual Learning

1 code implementation18 Sep 2022 Marcus Klasson, Hedvig Kjellström, Cheng Zhang

In such settings, we propose that continual learning systems should learn the time to learn and schedule which tasks to replay at different time steps.

Continual Learning Scheduling

Optimistic Optimization of Gaussian Process Samples

no code implementations2 Sep 2022 Julia Grosse, Cheng Zhang, Philipp Hennig

Bayesian optimization is a popular formalism for global optimization, but its computational costs limit it to expensive-to-evaluate functions.

Bayesian Optimization

NeurIPS Competition Instructions and Guide: Causal Insights for Learning Paths in Education

no code implementations17 Aug 2022 Wenbo Gong, Digory Smith, Zichao Wang, Craig Barton, Simon Woodhead, Nick Pawlowski, Joel Jennings, Cheng Zhang

In this competition, participants will address two fundamental causal challenges in machine learning in the context of education using time-series data.

Causal Discovery Selection bias +2

Efficient Real-world Testing of Causal Decision Making via Bayesian Experimental Design for Contextual Optimisation

no code implementations12 Jul 2022 Desi R. Ivanova, Joel Jennings, Cheng Zhang, Adam Foster

In this paper we introduce a model-agnostic framework for gathering data to evaluate and improve contextual decision making through Bayesian Experimental Design.

Decision Making Experimental Design

Downstream Transformer Generation of Question-Answer Pairs with Preprocessing and Postprocessing Pipelines

1 code implementation15 May 2022 Cheng Zhang, Hao Zhang, Jie Wang

We present a system called TP3 to perform a downstream task of transformers on generating question-answer pairs (QAPs) from a given article.

A Variational Approach to Bayesian Phylogenetic Inference

1 code implementation16 Apr 2022 Cheng Zhang, Frederick A. Matsen IV

Bayesian phylogenetic inference is currently done via Markov chain Monte Carlo (MCMC) with simple proposal mechanisms.

Efficient Exploration Variational Inference

Exploring and Evaluating Image Restoration Potential in Dynamic Scenes

1 code implementation CVPR 2022 Cheng Zhang, Shaolin Su, Yu Zhu, Qingsen Yan, Jinqiu Sun, Yanning Zhang

In this paper, to better study an image's potential value that can be explored for restoration, we propose a novel concept, referring to image restoration potential (IRP).

Image Restoration

Upsampling Autoencoder for Self-Supervised Point Cloud Learning

no code implementations21 Mar 2022 Cheng Zhang, Jian Shi, Xuan Deng, Zizhao Wu

In computer-aided design (CAD) community, the point cloud data is pervasively applied in reverse engineering, where the point cloud analysis plays an important role.

Local Constraint-Based Causal Discovery under Selection Bias

1 code implementation3 Mar 2022 Philip Versteeg, Cheng Zhang, Joris M. Mooij

We consider the problem of discovering causal relations from independence constraints selection bias in addition to confounding is present.

Causal Discovery Selection bias

Learning with Free Object Segments for Long-Tailed Instance Segmentation

no code implementations22 Feb 2022 Cheng Zhang, Tai-Yu Pan, Tianle Chen, Jike Zhong, WenJin Fu, Wei-Lun Chao

One fundamental challenge in building an instance segmentation model for a large number of classes in complex scenes is the lack of training examples, especially for rare objects.

Instance Segmentation Semantic Segmentation

Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations

no code implementations CVPR 2022 Zirui Peng, Shaofeng Li, Guoxing Chen, Cheng Zhang, Haojin Zhu, Minhui Xue

In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction attacks.

Contrastive Learning Model extraction

Deep End-to-end Causal Inference

1 code implementation4 Feb 2022 Tomas Geffner, Javier Antoran, Adam Foster, Wenbo Gong, Chao Ma, Emre Kiciman, Amit Sharma, Angus Lamb, Martin Kukla, Nick Pawlowski, Miltiadis Allamanis, Cheng Zhang

Causal inference is essential for data-driven decision making across domains such as business engagement, medical treatment and policy making.

Causal Discovery Causal Inference +1

Optimal transport for causal discovery

no code implementations ICLR 2022 Ruibo Tu, Kun Zhang, Hedvig Kjellström, Cheng Zhang

With this criterion, we propose a novel optimal transport-based algorithm for ANMs which is robust to the choice of models and extend it to post-nonlinear models.

Causal Discovery

Identifiable Generative Models for Missing Not at Random Data Imputation

1 code implementation NeurIPS 2021 Chao Ma, Cheng Zhang

In this work, we fill in this gap by systematically analyzing the identifiability of generative models under MNAR.


Simultaneous Missing Value Imputation and Structure Learning with Groups

1 code implementation15 Oct 2021 Pablo Morales-Alvarez, Wenbo Gong, Angus Lamb, Simon Woodhead, Simon Peyton Jones, Nick Pawlowski, Miltiadis Allamanis, Cheng Zhang

Learning structures between groups of variables from data with missing values is an important task in the real world, yet difficult to solve.

Causal Discovery Imputation

FCause: Flow-based Causal Discovery

no code implementations29 Sep 2021 Tomas Geffner, Emre Kiciman, Angus Lamb, Martin Kukla, Miltiadis Allamanis, Cheng Zhang

Current causal discovery methods either fail to scale, model only limited forms of functional relationships, or cannot handle missing values.

Causal Discovery

Learn the Time to Learn: Replay Scheduling for Continual Learning

no code implementations29 Sep 2021 Marcus Klasson, Hedvig Kjellstrom, Cheng Zhang

Inspired by human learning, we illustrate that scheduling over which tasks to revisit is critical to the final performance with finite memory resources.

Continual Learning Scheduling

Causal Triple Attention Time Series Forecasting

no code implementations29 Sep 2021 Zhixuan Chu, Tan Yan, Yue Wu, Yi Xu, Cheng Zhang, Yulin kang

Time series forecasting has historically been a key area of academic research and industrial applications.

Causal Inference Time Series +1

Intervention Adversarial Auto-Encoder

no code implementations29 Sep 2021 Yang Hu, Cheng Zhang

In this paper we propose a new method to stabilize the training process of the latent variables of adversarial auto-encoders, which we name Intervention Adversarial auto-encoder (IVAAE).

DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions

1 code implementation27 Aug 2021 Amit Sharma, Vasilis Syrgkanis, Cheng Zhang, Emre Kiciman

Estimation of causal effects involves crucial assumptions about the data-generating process, such as directionality of effect, presence of instrumental variables or mediators, and whether all relevant confounders are observed.

Causal Discovery

DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization

1 code implementation ICCV 2021 Cheng Zhang, Zhaopeng Cui, Cai Chen, Shuaicheng Liu, Bing Zeng, Hujun Bao, yinda zhang

Panorama images have a much larger field-of-view thus naturally encode enriched scene context information compared to standard perspective images, which however is not well exploited in the previous scene understanding methods.

Scene Understanding

On Incorrectness Logic and Kleene Algebra with Top and Tests

no code implementations17 Aug 2021 Cheng Zhang, Arthur Azevedo de Amorim, Marco Gaboardi

In his seminal work, Kozen proved that KAT subsumes propositional Hoare logic, showing that one can reason about the (partial) correctness of while programs by means of the equational theory of KAT.

PVT: Point-Voxel Transformer for Point Cloud Learning

2 code implementations13 Aug 2021 Cheng Zhang, Haocheng Wan, Xinyi Shen, Zizhao Wu

The recently developed pure Transformer architectures have attained promising accuracy on point cloud learning benchmarks compared to convolutional neural networks.

3D Object Detection 3D Part Segmentation +2

Toward Integrated Human-machine Intelligence for Civil Engineering: An Interdisciplinary Perspective

no code implementations28 Jul 2021 Cheng Zhang, Jinwoo Kim, JungHo Jeon, Jinding Xing, Changbum Ahn, Pingbo Tang, Hubo Cai

This paper will lay the foundation for identifying relevant studies to form a research roadmap to address the four knowledge gaps identified.

Decision Making

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

1 code implementation NeurIPS 2021 Tai-Yu Pan, Cheng Zhang, Yandong Li, Hexiang Hu, Dong Xuan, Soravit Changpinyo, Boqing Gong, Wei-Lun Chao

We propose NorCal, Normalized Calibration for long-tailed object detection and instance segmentation, a simple and straightforward recipe that reweighs the predicted scores of each class by its training sample size.

Instance Segmentation Long-tailed Object Detection +4

Countering Adversarial Examples: Combining Input Transformation and Noisy Training

no code implementations25 Jun 2021 Cheng Zhang, Pan Gao

Prior work has shown that JPEG compression can combat the drop in classification accuracy on adversarial examples to some extent.

Data Augmentation Quantization

Defending Adversaries Using Unsupervised Feature Clustering VAE

no code implementations ICML Workshop AML 2021 Cheng Zhang, Pan Gao

We propose a modified VAE (variational autoencoder) as a denoiser to remove adversarial perturbations for image classification.

Clustering Image Classification

Probabilistic DAG Search

no code implementations16 Jun 2021 Julia Grosse, Cheng Zhang, Philipp Hennig

Exciting contemporary machine learning problems have recently been phrased in the classic formalism of tree search -- most famously, the game of Go.

Decision Making feature selection +1

Sparse Uncertainty Representation in Deep Learning with Inducing Weights

no code implementations NeurIPS 2021 Hippolyt Ritter, Martin Kukla, Cheng Zhang, Yingzhen Li

Bayesian neural networks and deep ensembles represent two modern paradigms of uncertainty quantification in deep learning.

Variational Bayesian Supertrees

no code implementations22 Apr 2021 Michael Karcher, Cheng Zhang, Frederick A Matsen IV

Given overlapping subsets of a set of taxa (e. g. species), and posterior distributions on phylogenetic tree topologies for each of these taxon sets, how can we infer a posterior distribution on phylogenetic tree topologies for the entire taxon set?

Contextual HyperNetworks for Novel Feature Adaptation

no code implementations12 Apr 2021 Angus Lamb, Evgeny Saveliev, Yingzhen Li, Sebastian Tschiatschek, Camilla Longden, Simon Woodhead, José Miguel Hernández-Lobato, Richard E. Turner, Pashmina Cameron, Cheng Zhang

While deep learning has obtained state-of-the-art results in many applications, the adaptation of neural network architectures to incorporate new output features remains a challenge, as neural networks are commonly trained to produce a fixed output dimension.

Few-Shot Learning Imputation +1

Holistic 3D Scene Understanding from a Single Image with Implicit Representation

1 code implementation CVPR 2021 Cheng Zhang, Zhaopeng Cui, yinda zhang, Bing Zeng, Marc Pollefeys, Shuaicheng Liu

We not only propose an image-based local structured implicit network to improve the object shape estimation, but also refine the 3D object pose and scene layout via a novel implicit scene graph neural network that exploits the implicit local object features.

 Ranked #1 on Monocular 3D Object Detection on SUN RGB-D (using extra training data)

3D Shape Reconstruction Monocular 3D Object Detection +3

Pointwise Weyl Laws for Schrödinger operators with singular potentials

no code implementations9 Mar 2021 Xiaoqi Huang, Cheng Zhang

We consider the Schr\"odinger operators $H_V=-\Delta_g+V$ with singular potentials $V$ on general $n$-dimensional Riemannian manifolds and study whether various forms of pointwise Weyl law remain valid under this pertubation.

Analysis of PDEs Mathematical Physics Classical Analysis and ODEs Functional Analysis Mathematical Physics Spectral Theory 58J50, 35P15

WLAN-Log-Based Superspreader Detection in the COVID-19 Pandemic

no code implementations22 Feb 2021 Cheng Zhang, Yunze Pan, Yunqi Zhang, Adam C. Champion, Zhaohui Shen, Dong Xuan, Zhiqiang Lin, Ness B. Shroff

Further, the evaluation shows no consistent differences among three vertex centrality measures for long-term (i. e., weekly) contact graphs, which necessitates the inclusion of SEIR simulation in our framework.

Social and Information Networks Computers and Society

MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

1 code implementation ICCV 2021 Cheng Zhang, Tai-Yu Pan, Yandong Li, Hexiang Hu, Dong Xuan, Soravit Changpinyo, Boqing Gong, Wei-Lun Chao

Many objects do not appear frequently enough in complex scenes (e. g., certain handbags in living rooms) for training an accurate object detector, but are often found frequently by themselves (e. g., in product images).

Imputation Instance Segmentation +4

Estimating $α$-Rank by Maximizing Information Gain

1 code implementation22 Jan 2021 Tabish Rashid, Cheng Zhang, Kamil Ciosek

We show the benefits of using information gain as compared to the confidence interval criterion of ResponseGraphUCB (Rowland et al. 2019), and provide theoretical results justifying our method.

Intervention Generative Adversarial Nets

no code implementations1 Jan 2021 Jiadong Liang, Liangyu Zhang, Cheng Zhang, Zhihua Zhang

In this paper we propose a novel approach for stabilizing the training process of Generative Adversarial Networks as well as alleviating the mode collapse problem.

Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows

1 code implementation NeurIPS 2020 Cheng Zhang

By handling the non-Euclidean branch length space of phylogenetic models with carefully designed permutation equivariant transformations, VBPI-NF uses normalizing flows to provide a rich family of flexible branch length distributions that generalize across different tree topologies.

True-data Testbed for 5G/B5G Intelligent Network

no code implementations26 Nov 2020 Yongming Huang, Shengheng Liu, Cheng Zhang, Xiaohu You, Hequan Wu

Future beyond fifth-generation (B5G) and sixth-generation (6G) mobile communications will shift from facilitating interpersonal communications to supporting Internet of Everything (IoE), where intelligent communications with full integration of big data and artificial intelligence (AI) will play an important role in improving network efficiency and providing high-quality service.

A Study on Efficiency in Continual Learning Inspired by Human Learning

no code implementations28 Oct 2020 Philip J. Ball, Yingzhen Li, Angus Lamb, Cheng Zhang

We study a setting where the pruning phase is given a time budget, and identify connections between iterative pruning and multiple sleep cycles in humans.

Continual Learning

Extracting Body Text from Academic PDF Documents for Text Mining

no code implementations23 Oct 2020 Changfeng Yu, Cheng Zhang, Jie Wang

Accurate extraction of body text from PDF-formatted academic documents is essential in text-mining applications for deeper semantic understandings.

Generating Adequate Distractors for Multiple-Choice Questions

no code implementations23 Oct 2020 Cheng Zhang, Yicheng Sun, Hejia Chen, Jie Wang

This paper presents a novel approach to automatic generation of adequate distractors for a given question-answer pair (QAP) generated from a given article to form an adequate multiple-choice question (MCQ).

Multiple-choice Part-Of-Speech Tagging +2

How Do Fair Decisions Fare in Long-term Qualification?

1 code implementation NeurIPS 2020 Xueru Zhang, Ruibo Tu, Yang Liu, Mingyan Liu, Hedvig Kjellström, Kun Zhang, Cheng Zhang

Our results show that static fairness constraints can either promote equality or exacerbate disparity depending on the driving factor of qualification transitions and the effect of sensitive attributes on feature distributions.

Decision Making Fairness

Progressive Defense Against Adversarial Attacks for Deep Learning as a Service in Internet of Things

no code implementations15 Oct 2020 Ling Wang, Cheng Zhang, Zejian Luo, ChenGuang Liu, Jie Liu, Xi Zheng, Athanasios Vasilakos

To reduce the computational cost without loss of generality, we present a defense strategy called a progressive defense against adversarial attacks (PDAAA) for efficiently and effectively filtering out the adversarial pixel mutations, which could mislead the neural network towards erroneous outputs, without a-priori knowledge about the attack type.

Weakly-supervised Fine-grained Event Recognition on Social Media Texts for Disaster Management

1 code implementation4 Oct 2020 Wenlin Yao, Cheng Zhang, Shiva Saravanan, Ruihong Huang, Ali Mostafavi

People increasingly use social media to report emergencies, seek help or share information during disasters, which makes social networks an important tool for disaster management.


Meta Sequence Learning for Generating Adequate Question-Answer Pairs

no code implementations4 Oct 2020 Cheng Zhang, Jie Wang

Creating multiple-choice questions to assess reading comprehension of a given article involves generating question-answer pairs (QAPs) on the main points of the document.

Multiple-choice named-entity-recognition +5

Spatio-Temporal Hierarchical Adaptive Dispatching for Ridesharing Systems

no code implementations4 Sep 2020 Chang Liu, Jiahui Sun, Haiming Jin, Meng Ai, Qun Li, Cheng Zhang, Kehua Sheng, Guobin Wu, XiaoHu Qie, Xinbing Wang

Thus, in this paper, we exploit adaptive dispatching intervals to boost the platform's profit under a guarantee of the maximum passenger waiting time.

Intervention Generative Adversarial Networks

no code implementations9 Aug 2020 Jiadong Liang, Liangyu Zhang, Cheng Zhang, Zhihua Zhang

In this paper we propose a novel approach for stabilizing the training process of Generative Adversarial Networks as well as alleviating the mode collapse problem.

Instructions and Guide for Diagnostic Questions: The NeurIPS 2020 Education Challenge

no code implementations23 Jul 2020 Zichao Wang, Angus Lamb, Evgeny Saveliev, Pashmina Cameron, Yordan Zaykov, José Miguel Hernández-Lobato, Richard E. Turner, Richard G. Baraniuk, Craig Barton, Simon Peyton Jones, Simon Woodhead, Cheng Zhang

In this competition, participants will focus on the students' answer records to these multiple-choice diagnostic questions, with the aim of 1) accurately predicting which answers the students provide; 2) accurately predicting which questions have high quality; and 3) determining a personalized sequence of questions for each student that best predicts the student's answers.

Misconceptions Multiple-choice

Meta-Learning Divergences of Variational Inference

no code implementations6 Jul 2020 Ruqi Zhang, Yingzhen Li, Christopher De Sa, Sam Devlin, Cheng Zhang

Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and broad applicability.

Bayesian Inference Few-Shot Learning +3

Dynamic gesture retrieval: searching videos by human pose sequence

no code implementations13 Jun 2020 Cheng Zhang

The number of static human poses is limited, it is hard to retrieve the exact videos using one single pose as the clue.


Thoracic Disease Identification and Localization using Distance Learning and Region Verification

no code implementations7 Jun 2020 Cheng Zhang, Francine Chen, Yan-Ying Chen

In this paper, we propose an alternative approach that learns discriminative features among triplets of images and cyclically trains on region features to verify whether attentive regions contain information indicative of a disease.

Classification General Classification

Attention-based network for low-light image enhancement

no code implementations20 May 2020 Cheng Zhang, Qingsen Yan, Yu Zhu, Xianjun Li, Jinqiu Sun, Yanning Zhang

Extensive experiments demonstrate the superiority of the proposed network in terms of suppressing the chromatic aberration and noise artifacts in enhancement, especially when the low-light image has severe noise.

Denoising Low-Light Image Enhancement

A Causal View on Robustness of Neural Networks

no code implementations3 May 2020 Cheng Zhang, Kun Zhang, Yingzhen Li

We present a causal view on the robustness of neural networks against input manipulations, which applies not only to traditional classification tasks but also to general measurement data.

Data Augmentation

AMRL: Aggregated Memory For Reinforcement Learning

no code implementations ICLR 2020 Jacob Beck, Kamil Ciosek, Sam Devlin, Sebastian Tschiatschek, Cheng Zhang, Katja Hofmann

In many partially observable scenarios, Reinforcement Learning (RL) agents must rely on long-term memory in order to learn an optimal policy.

reinforcement-learning Reinforcement Learning (RL)

Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight

no code implementations ACL 2020 Hengyi Cai, Hongshen Chen, Yonghao Song, Cheng Zhang, Xiaofang Zhao, Dawei Yin

In this paper, we propose a data manipulation framework to proactively reshape the data distribution towards reliable samples by augmenting and highlighting effective learning samples as well as reducing the effect of inefficient samples simultaneously.

Dialogue Generation

Educational Question Mining At Scale: Prediction, Analysis and Personalization

no code implementations12 Mar 2020 Zichao Wang, Sebastian Tschiatschek, Simon Woodhead, Jose Miguel Hernandez-Lobato, Simon Peyton Jones, Richard G. Baraniuk, Cheng Zhang

Online education platforms enable teachers to share a large number of educational resources such as questions to form exercises and quizzes for students.

Assessing the Memory Ability of Recurrent Neural Networks

no code implementations18 Feb 2020 Cheng Zhang, Qiuchi Li, Lingyu Hua, Dawei Song

To tackle the problem, in this paper, we identify and analyze the internal and external factors that affect the memory ability of RNNs, and propose a Semantic Euclidean Space to represent the semantics expressed by a sequence.

Adaptive Parameterization for Neural Dialogue Generation

1 code implementation IJCNLP 2019 Hengyi Cai, Hongshen Chen, Cheng Zhang, Yonghao Song, Xiaofang Zhao, Dawei Yin

For each conversation, the model generates parameters of the encoder-decoder by referring to the input context.

Dialogue Generation

Icebreaker: Element-wise Efficient Information Acquisition with a Bayesian Deep Latent Gaussian Model

1 code implementation NeurIPS 2019 Wenbo Gong, Sebastian Tschiatschek, Sebastian Nowozin, Richard E. Turner, José Miguel Hernández-Lobato, Cheng Zhang

In this paper, we address the ice-start problem, i. e., the challenge of deploying machine learning models when only a little or no training data is initially available, and acquiring each feature element of data is associated with costs.

BIG-bench Machine Learning Imputation +2

Meta-Learning for Variational Inference

no code implementations pproximateinference AABI Symposium 2019 Ruqi Zhang, Yingzhen Li, Chris De Sa, Sam Devlin, Cheng Zhang

Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and general applicability.

Bayesian Inference Meta-Learning +3

Generating an Overview Report over Many Documents

no code implementations17 Aug 2019 Jingwen Wang, Hao Zhang, Cheng Zhang, Wenjing Yang, Liqun Shao, Jie Wang

To overcome this obstacle, we present NDORGS (Numerous Documents' Overview Report Generation Scheme) that integrates text filtering, keyword scoring, single-document summarization (SDS), topic modeling, MDS, and title generation to generate a coherent, well-structured ORPT.

Decision Making Document Summarization +1

Icebreaker: Element-wise Active Information Acquisition with Bayesian Deep Latent Gaussian Model

1 code implementation13 Aug 2019 Wenbo Gong, Sebastian Tschiatschek, Richard Turner, Sebastian Nowozin, José Miguel Hernández-Lobato, Cheng Zhang

In this paper we introduce the ice-start problem, i. e., the challenge of deploying machine learning models when only little or no training data is initially available, and acquiring each feature element of data is associated with costs.

Active Learning BIG-bench Machine Learning +3

An Empirical Study on Leveraging Scene Graphs for Visual Question Answering

no code implementations28 Jul 2019 Cheng Zhang, Wei-Lun Chao, Dong Xuan

Specifically, we investigate the use of scene graphs derived from images for Visual QA: an image is abstractly represented by a graph with nodes corresponding to object entities and edges to object relationships.

Knowledge Graphs Question Answering +1

Interpretable Outcome Prediction with Sparse Bayesian Neural Networks in Intensive Care

2 code implementations7 May 2019 Hiske Overweg, Anna-Lena Popkes, Ari Ercole, Yingzhen Li, José Miguel Hernández-Lobato, Yordan Zaykov, Cheng Zhang

However, flexible tools such as artificial neural networks (ANNs) suffer from a lack of interpretability limiting their acceptability to clinicians.

Decision Making feature selection +1

Variational Bayesian Phylogenetic Inference

no code implementations ICLR 2019 Cheng Zhang, Frederick A. Matsen IV

Bayesian phylogenetic inference is currently done via Markov chain Monte Carlo with simple mechanisms for proposing new states, which hinders exploration efficiency and often requires long runs to deliver accurate posterior estimates.

Variational Inference

A Hierarchical Grocery Store Image Dataset with Visual and Semantic Labels

3 code implementations3 Jan 2019 Marcus Klasson, Cheng Zhang, Hedvig Kjellström

In this paper, we provide a new benchmark dataset for a challenging task in this application - classification of fruits, vegetables, and refrigerated products, e. g. milk packages and juice cartons, in grocery stores.

Classification General Classification +1

Continuous Word Embedding Fusion via Spectral Decomposition

no code implementations CONLL 2018 Tianfan Fu, Cheng Zhang, M, Stephan t

In this paper, we present an efficient method for including new words from a specialized corpus, containing new words, into pre-trained generic word embeddings.

Machine Translation Transfer Learning +1

EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE

1 code implementation ICLR 2019 Chao Ma, Sebastian Tschiatschek, Konstantina Palla, José Miguel Hernández-Lobato, Sebastian Nowozin, Cheng Zhang

Many real-life decision-making situations allow further relevant information to be acquired at a specific cost, for example, in assessing the health status of a patient we may decide to take additional measurements such as diagnostic tests or imaging scans before making a final assessment.

Decision Making Experimental Design +1

Simultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation

no code implementations8 Sep 2018 Charles Hamesse, Ruibo Tu, Paul Ackermann, Hedvig Kjellström, Cheng Zhang

However, it is challenging to train an automatic method for predicting the ATR rehabilitation outcome from treatment data, due to a massive amount of missing entries in the data recorded from ATR patients, as well as complex nonlinear relations between measurements and outcomes.


Dressing the boundary: on soliton solutions of the nonlinear Schrödinger equation on the half-line

no code implementations3 Sep 2018 Cheng Zhang

Based on the theory of integrable boundary conditions (BCs) developed by Sklyanin, we provide a direct method for computing soliton solutions of the focusing nonlinear Schr\"odinger (NLS) equation on the half-line.

Exactly Solvable and Integrable Systems High Energy Physics - Theory Mathematical Physics Mathematical Physics

Learning Discriminative 3D Shape Representations by View Discerning Networks

2 code implementations11 Aug 2018 Biao Leng, Cheng Zhang, Xiaocheng Zhou, Cheng Xu, Kai Xu

In this network, a Score Generation Unit is devised to evaluate the quality of each projected image with score vectors.

3D Shape Recognition 3D Shape Representation +1

Causal Discovery in the Presence of Missing Data

1 code implementation11 Jul 2018 Ruibo Tu, Kun Zhang, Paul Ackermann, Bo Christer Bertilson, Clark Glymour, Hedvig Kjellström, Cheng Zhang

When these data entries are not missing completely at random, the (conditional) independence relations in the observed data may be different from those in the complete data generated by the underlying causal process.

Causal Discovery

Non-bifurcating phylogenetic tree inference via the adaptive LASSO

1 code implementation28 May 2018 Cheng Zhang, Vu Dinh, Frederick A. Matsen IV

Phylogenetic tree inference using deep DNA sequencing is reshaping our understanding of rapidly evolving systems, such as the within-host battle between viruses and the immune system.

Generalizing Tree Probability Estimation via Bayesian Networks

1 code implementation NeurIPS 2018 Cheng Zhang, Frederick A. Matsen IV

Probability estimation is one of the fundamental tasks in statistics and machine learning.


Active Mini-Batch Sampling using Repulsive Point Processes

1 code implementation8 Apr 2018 Cheng Zhang, Cengiz Öztireli, Stephan Mandt, Giampiero Salvi

We first show that the phenomenon of variance reduction by diversified sampling generalizes in particular to non-stationary point processes.

Point Processes

Causality Refined Diagnostic Prediction

no code implementations29 Nov 2017 Marcus Klasson, Kun Zhang, Bo C. Bertilson, Cheng Zhang, Hedvig Kjellström

In this work, we explore the possibility of utilizing causal relationships to refine diagnostic prediction.

Causal Identification Decision Making

Advances in Variational Inference

no code implementations15 Nov 2017 Cheng Zhang, Judith Butepage, Hedvig Kjellstrom, Stephan Mandt

Many modern unsupervised or semi-supervised machine learning algorithms rely on Bayesian probabilistic models.

Variational Inference

Perturbative Black Box Variational Inference

no code implementations NeurIPS 2017 Robert Bamler, Cheng Zhang, Manfred Opper, Stephan Mandt

Black box variational inference (BBVI) with reparameterization gradients triggered the exploration of divergence measures other than the Kullback-Leibler (KL) divergence, such as alpha divergences.

Gaussian Processes Variational Inference

FontCode: Embedding Information in Text Documents using Glyph Perturbation

no code implementations28 Jul 2017 Chang Xiao, Cheng Zhang, Changxi Zheng

We then introduce an algorithm that embeds a user-provided message in the text document and produces an encoded document whose appearance is minimally perturbed from the original document.

Determinantal Point Processes for Mini-Batch Diversification

no code implementations1 May 2017 Cheng Zhang, Hedvig Kjellstrom, Stephan Mandt

The DPP relies on a similarity measure between data points and gives low probabilities to mini-batches which contain redundant data, and higher probabilities to mini-batches with more diverse data.

Point Processes

Probabilistic Path Hamiltonian Monte Carlo

3 code implementations ICML 2017 Vu Dinh, Arman Bilge, Cheng Zhang, Frederick A. Matsen IV

Hamiltonian Monte Carlo (HMC) is an efficient and effective means of sampling posterior distributions on Euclidean space, which has been extended to manifolds with boundary.

Bridging Medical Data Inference to Achilles Tendon Rupture Rehabilitation

no code implementations7 Dec 2016 An Qu, Cheng Zhang, Paul Ackermann, Hedvig Kjellström

Imputing incomplete medical tests and predicting patient outcomes are crucial for guiding the decision making for therapy, such as after an Achilles Tendon Rupture (ATR).

Collaborative Filtering Decision Making +3

Diagnostic Prediction Using Discomfort Drawings

no code implementations5 Dec 2016 Cheng Zhang, Hedvig Kjellstrom, Bo C. Bertilson

In this paper, we explore the possibility to apply machine learning to make diagnostic predictions using discomfort drawings.

BIG-bench Machine Learning

Viewpoint and Topic Modeling of Current Events

no code implementations14 Aug 2016 Kerry Zhang, Jussi Karlgren, Cheng Zhang, Jens Lagergren

There are multiple sides to every story, and while statistical topic models have been highly successful at topically summarizing the stories in corpora of text documents, they do not explicitly address the issue of learning the different sides, the viewpoints, expressed in the documents.

Topic Models

Diagnostic Prediction Using Discomfort Drawings with IBTM

no code implementations27 Jul 2016 Cheng Zhang, Hedvig Kjellstrom, Carl Henrik Ek, Bo C. Bertilson

The positive result indicates a significant potential of machine learning to be used for parts of the pain diagnostic process and to be a decision support system for physicians and other health care personnel.

BIG-bench Machine Learning Clustering

Inter-Battery Topic Representation Learning

no code implementations19 May 2016 Cheng Zhang, Hedvig Kjellstrom, Carl Henrik Ek

The structured representation leads to a model that marries benefits traditionally associated with a discriminative approach, such as feature selection, with those of a generative model, such as principled regularization and ability to handle missing data.

feature selection Representation Learning +1

Variational Hamiltonian Monte Carlo via Score Matching

no code implementations6 Feb 2016 Cheng Zhang, Babak Shahbaba, Hongkai Zhao

Traditionally, the field of computational Bayesian statistics has been divided into two main subfields: variational methods and Markov chain Monte Carlo (MCMC).

Bayesian Inference

Hamiltonian Monte Carlo Acceleration Using Surrogate Functions with Random Bases

1 code implementation18 Jun 2015 Cheng Zhang, Babak Shahbaba, Hongkai Zhao

To this end, we build a surrogate function to approximate the target distribution using properly chosen random bases and an efficient optimization process.

Additive models Bayesian Inference

Factorized Topic Models

no code implementations15 Jan 2013 Cheng Zhang, Carl Henrik Ek, Andreas Damianou, Hedvig Kjellstrom

In this paper we present a modification to a latent topic model, which makes the model exploit supervision to produce a factorized representation of the observed data.

General Classification Topic Models +1

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