Search Results for author: Peng Xu

Found 95 papers, 38 papers with code

CAiRE in DialDoc21: Data Augmentation for Information Seeking Dialogue System

1 code implementation ACL (dialdoc) 2021 Yan Xu, Etsuko Ishii, Genta Indra Winata, Zhaojiang Lin, Andrea Madotto, Zihan Liu, Peng Xu, Pascale Fung

Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on users’ needs, which.

Data Augmentation Response Generation

Multimodal Learning with Transformers: A Survey

no code implementations13 Jun 2022 Peng Xu, Xiatian Zhu, David A. Clifton

Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks.

Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner

no code implementations18 May 2022 Danilo Ribeiro, Shen Wang, Xiaofei Ma, Rui Dong, Xiaokai Wei, Henry Zhu, Xinchi Chen, Zhiheng Huang, Peng Xu, Andrew Arnold, Dan Roth

Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises.

Question Answering

Attention Mechanism based Cognition-level Scene Understanding

no code implementations17 Apr 2022 Xuejiao Tang, Tai Le Quy, Eirini Ntoutsi, Kea Turner, Vasile Palade, Israat Haque, Peng Xu, Chris Brown, Wenbin Zhang

Given a question-image input, the Visual Commonsense Reasoning (VCR) model can predict an answer with the corresponding rationale, which requires inference ability from the real world.

Question Answering Scene Understanding +2

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

no code implementations4 Apr 2022 Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, Daniel Ho, Jasmine Hsu, Julian Ibarz, Brian Ichter, Alex Irpan, Eric Jang, Rosario Jauregui Ruano, Kyle Jeffrey, Sally Jesmonth, Nikhil J Joshi, Ryan Julian, Dmitry Kalashnikov, Yuheng Kuang, Kuang-Huei Lee, Sergey Levine, Yao Lu, Linda Luu, Carolina Parada, Peter Pastor, Jornell Quiambao, Kanishka Rao, Jarek Rettinghouse, Diego Reyes, Pierre Sermanet, Nicolas Sievers, Clayton Tan, Alexander Toshev, Vincent Vanhoucke, Fei Xia, Ted Xiao, Peng Xu, Sichun Xu, Mengyuan Yan

We show how low-level skills can be combined with large language models so that the language model provides high-level knowledge about the procedures for performing complex and temporally-extended instructions, while value functions associated with these skills provide the grounding necessary to connect this knowledge to a particular physical environment.

Decision Making Language Modelling

QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation

no code implementations14 Feb 2022 Dan Su, Peng Xu, Pascale Fung

Multi-hop question generation (MQG) aims to generate complex questions which require reasoning over multiple pieces of information of the input passage.

Multi-hop Question Answering Question Answering +1

How to Understand Masked Autoencoders

no code implementations8 Feb 2022 Shuhao Cao, Peng Xu, David A. Clifton

"Masked Autoencoders (MAE) Are Scalable Vision Learners" revolutionizes the self-supervised learning method in that it not only achieves the state-of-the-art for image pre-training, but is also a milestone that bridges the gap between visual and linguistic masked autoencoding (BERT-style) pre-trainings.

Self-Supervised Learning

Unsupervised Long-Term Person Re-Identification with Clothes Change

no code implementations7 Feb 2022 Mingkun Li, Peng Xu, Xiatian Zhu, Jun Guo

We investigate unsupervised person re-identification (Re-ID) with clothes change, a new challenging problem with more practical usability and scalability to real-world deployment.

Unsupervised Person Re-Identification

Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset

1 code implementation7 Jan 2022 Tiezheng Yu, Rita Frieske, Peng Xu, Samuel Cahyawijaya, Cheuk Tung Shadow Yiu, Holy Lovenia, Wenliang Dai, Elham J. Barezi, Qifeng Chen, Xiaojuan Ma, Bertram E. Shi, Pascale Fung

We further conduct experiments with Fairseq S2T Transformer, a state-of-the-art ASR model, on the biggest existing dataset, Common Voice zh-HK, and our proposed MDCC, and the results show the effectiveness of our dataset.

Automatic Speech Recognition

ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation

1 code implementation12 Dec 2021 Holy Lovenia, Samuel Cahyawijaya, Genta Indra Winata, Peng Xu, Xu Yan, Zihan Liu, Rita Frieske, Tiezheng Yu, Wenliang Dai, Elham J. Barezi, Qifeng Chen, Xiaojuan Ma, Bertram E. Shi, Pascale Fung

ASCEND (A Spontaneous Chinese-English Dataset) is a high-quality Mandarin Chinese-English code-switching corpus built on spontaneous multi-turn conversational dialogue sources collected in Hong Kong.

Hierarchical Neural Data Synthesis for Semantic Parsing

no code implementations4 Dec 2021 Wei Yang, Peng Xu, Yanshuai Cao

Moreover, even the questions pertinent to a given domain, which are the input of a semantic parsing system, might not be readily available, especially in cross-domain semantic parsing.

Data Augmentation Semantic Parsing +1

Attention-guided Generative Models for Extractive Question Answering

no code implementations12 Oct 2021 Peng Xu, Davis Liang, Zhiheng Huang, Bing Xiang

We propose a simple strategy to obtain an extractive answer span from the generative model by leveraging the decoder cross-attention patterns.

Open-Domain Question Answering

Multiplicative Position-aware Transformer Models for Language Understanding

no code implementations27 Sep 2021 Zhiheng Huang, Davis Liang, Peng Xu, Bing Xiang

Transformer models, which leverage architectural improvements like self-attention, perform remarkably well on Natural Language Processing (NLP) tasks.

Natural Language Processing

Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering

1 code implementation ACL 2021 Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, Bing Xiang

However, a large amount of world's knowledge is stored in structured databases, and need to be accessed using query languages such as SQL.

Open-Domain Question Answering

CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System

1 code implementation7 Jun 2021 Etsuko Ishii, Yan Xu, Genta Indra Winata, Zhaojiang Lin, Andrea Madotto, Zihan Liu, Peng Xu, Pascale Fung

Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on users' needs, which.

Data Augmentation Response Generation

X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing

1 code implementation ACL (RepL4NLP) 2021 Zihan Liu, Genta Indra Winata, Peng Xu, Pascale Fung

Experimental results illustrate that our model can significantly outperform existing strong baselines in cross-lingual and cross-domain settings, and our model can also achieve a good generalization ability on target languages of target domains.

Semantic Parsing

BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling

1 code implementation5 Jun 2021 Zhaojiang Lin, Andrea Madotto, Genta Indra Winata, Peng Xu, Feijun Jiang, Yuxiang Hu, Chen Shi, Pascale Fung

However, existing datasets for end-to-end ToD modeling are limited to a single language, hindering the development of robust end-to-end ToD systems for multilingual countries and regions.

Cross-Lingual Transfer Transfer Learning

DeepChange: A Large Long-Term Person Re-Identification Benchmark with Clothes Change

1 code implementation31 May 2021 Peng Xu, Xiatian Zhu

Currently, one of the most significant limitations in this field is the lack of a large realistic benchmark.

Person Identification Person Re-Identification

Revealing and controlling nuclear dynamics following inner-shell photoionization of N2

no code implementations11 Mar 2021 Qingli Jing, Hong Qian, Peng Xu

In this work, we apply the Monte Carlo wave packet method to study the ultrafast nuclear dynamics following inner-shell photoionization of N2 exposed to an ultrashort intense X-ray pulse.

Atomic Physics Atomic and Molecular Clusters

Optimizing Deeper Transformers on Small Datasets

1 code implementation ACL 2021 Peng Xu, Dhruv Kumar, Wei Yang, Wenjie Zi, Keyi Tang, Chenyang Huang, Jackie Chi Kit Cheung, Simon J. D. Prince, Yanshuai Cao

This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension.

Reading Comprehension Semantic Parsing +2

Mobile Robots Exploration via Deep Reinforcement Learning

no code implementations CUHK Course IERG5350 2020 Han Ma, Peng Xu

n this paper, we try to solve the mobile robot exploration problem in a 2D indoor office environment by deep reinforcement learning.


Unsupervised Regionalization of Particle-resolved Aerosol Mixing State Indices on the Global Scale

no code implementations6 Dec 2020 Zhonghua Zheng, Joseph Ching, Jeffrey H. Curtis, Yu Yao, Peng Xu, Matthew West, Nicole Riemer

Here we developed a simple but effective unsupervised learning approach to regionalize predictions of global aerosol mixing state indices.

Cross-lingual Spoken Language Understanding with Regularized Representation Alignment

1 code implementation EMNLP 2020 Zihan Liu, Genta Indra Winata, Peng Xu, Zhaojiang Lin, Pascale Fung

Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the performance sub-optimal.

Spoken Language Understanding

Embedding-based Zero-shot Retrieval through Query Generation

1 code implementation22 Sep 2020 Davis Liang, Peng Xu, Siamak Shakeri, Cicero Nogueira dos Santos, Ramesh Nallapati, Zhiheng Huang, Bing Xiang

In some cases, our model trained on synthetic data can even outperform the same model trained on real data

Passage Retrieval

EmoGraph: Capturing Emotion Correlations using Graph Networks

no code implementations21 Aug 2020 Peng Xu, Zihan Liu, Genta Indra Winata, Zhaojiang Lin, Pascale Fung

Most emotion recognition methods tackle the emotion understanding task by considering individual emotion independently while ignoring their fuzziness nature and the interconnections among them.

Classification Emotion Classification +3

Extension of causal decomposition in the mutual complex dynamic process

no code implementations17 Aug 2020 Yi Zhang, Qin Yang, Lifu Zhang, Branko Celler, Steven Su, Peng Xu, Dezhong Yao

Causal decomposition depicts a cause-effect relationship that is not based on the concept of prediction, but based on the phase dependence of time series.

Time Series

On Learning Semantic Representations for Million-Scale Free-Hand Sketches

1 code implementation7 Jul 2020 Peng Xu, Yongye Huang, Tongtong Yuan, Tao Xiang, Timothy M. Hospedales, Yi-Zhe Song, Liang Wang

Specifically, we use our dual-branch architecture as a universal representation framework to design two sketch-specific deep models: (i) We propose a deep hashing model for sketch retrieval, where a novel hashing loss is specifically designed to accommodate both the abstract and messy traits of sketches.

Learning Semantic Representations Zero-Shot Learning

Variational Transformers for Diverse Response Generation

2 code implementations28 Mar 2020 Zhaojiang Lin, Genta Indra Winata, Peng Xu, Zihan Liu, Pascale Fung

Despite the great promise of Transformers in many sequence modeling tasks (e. g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation.

Machine Translation Response Generation +1

TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding

no code implementations16 Mar 2020 Zhiheng Huang, Peng Xu, Davis Liang, Ajay Mishra, Bing Xiang

Prior to the transformer era, bidirectional Long Short-Term Memory (BLSTM) has been the dominant modeling architecture for neural machine translation and question answering.

Machine Translation Natural Language Inference +4

Learning Fast Adaptation on Cross-Accented Speech Recognition

1 code implementation4 Mar 2020 Genta Indra Winata, Samuel Cahyawijaya, Zihan Liu, Zhaojiang Lin, Andrea Madotto, Peng Xu, Pascale Fung

The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic speech recognition (ASR) system.

Audio and Speech Processing Sound

Learning to Walk in the Real World with Minimal Human Effort

1 code implementation20 Feb 2020 Sehoon Ha, Peng Xu, Zhenyu Tan, Sergey Levine, Jie Tan

In this paper, we develop a system for learning legged locomotion policies with deep RL in the real world with minimal human effort.

Legged Robots Multi-Task Learning +1

Deep Self-Supervised Representation Learning for Free-Hand Sketch

1 code implementation3 Feb 2020 Peng Xu, Zeyu Song, Qiyue Yin, Yi-Zhe Song, Liang Wang

In this paper, we tackle for the first time, the problem of self-supervised representation learning for free-hand sketches.

Representation Learning Self-Supervised Learning

EEG-based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and their Applications

no code implementations28 Jan 2020 Xiaotong Gu, Zehong Cao, Alireza Jolfaei, Peng Xu, Dongrui Wu, Tzyy-Ping Jung, Chin-Teng Lin

Recent technological advances such as wearable sensing devices, real-time data streaming, machine learning, and deep learning approaches have increased interest in electroencephalographic (EEG) based BCI for translational and healthcare applications.

EEG Transfer Learning

Deep Learning for Free-Hand Sketch: A Survey

2 code implementations8 Jan 2020 Peng Xu, Timothy M. Hospedales, Qiyue Yin, Yi-Zhe Song, Tao Xiang, Liang Wang

Free-hand sketches are highly illustrative, and have been widely used by humans to depict objects or stories from ancient times to the present.

Multi-Graph Transformer for Free-Hand Sketch Recognition

1 code implementation24 Dec 2019 Peng Xu, Chaitanya K. Joshi, Xavier Bresson

In this work, we propose a new representation of sketches as multiple sparsely connected graphs.

Sketch Recognition

SPIN: A High Speed, High Resolution Vision Dataset for Tracking and Action Recognition in Ping Pong

no code implementations13 Dec 2019 Steven Schwarcz, Peng Xu, David D'Ambrosio, Juhana Kangaspunta, Anelia Angelova, Huong Phan, Navdeep Jaitly

The corpus consists of ping pong play with three main annotation streams that can be used to learn tracking and action recognition models -- tracking of the ping pong ball and poses of humans in the videos and the spin of the ball being hit by humans.

Action Recognition Pose Estimation

Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables

no code implementations IJCNLP 2019 Zihan Liu, Jamin Shin, Yan Xu, Genta Indra Winata, Peng Xu, Andrea Madotto, Pascale Fung

Despite the surging demands for multilingual task-oriented dialog systems (e. g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios.

Intent Detection Natural Language Understanding +1

Fault Detection and Identification using Bayesian Recurrent Neural Networks

no code implementations11 Nov 2019 Weike Sun, Antonio R. C. Paiva, Peng Xu, Anantha Sundaram, Richard D. Braatz

In processing and manufacturing industries, there has been a large push to produce higher quality products and ensure maximum efficiency of processes.

Fault Detection

Domain Adaptation with BERT-based Domain Classification and Data Selection

no code implementations WS 2019 Xiaofei Ma, Peng Xu, Zhiguo Wang, Ramesh Nallapati, Bing Xiang

The performance of deep neural models can deteriorate substantially when there is a domain shift between training and test data.

Classification Domain Adaptation +1

Generalizing Question Answering System with Pre-trained Language Model Fine-tuning

no code implementations WS 2019 Dan Su, Yan Xu, Genta Indra Winata, Peng Xu, Hyeondey Kim, Zihan Liu, Pascale Fung

With a large number of datasets being released and new techniques being proposed, Question answering (QA) systems have witnessed great breakthroughs in reading comprehension (RC)tasks.

Language Modelling Multi-Task Learning +2

Boosting Image Recognition with Non-differentiable Constraints

no code implementations2 Oct 2019 Xuan Li, Yuchen Lu, Peng Xu, Jizong Peng, Christian Desrosiers, Xue Liu

In this paper, we study the problem of image recognition with non-differentiable constraints.

Inductive Bias

MoEL: Mixture of Empathetic Listeners

3 code implementations IJCNLP 2019 Zhaojiang Lin, Andrea Madotto, Jamin Shin, Peng Xu, Pascale Fung

Previous research on empathetic dialogue systems has mostly focused on generating responses given certain emotions.

Getting To Know You: User Attribute Extraction from Dialogues

1 code implementation LREC 2020 Chien-Sheng Wu, Andrea Madotto, Zhaojiang Lin, Peng Xu, Pascale Fung

User attributes provide rich and useful information for user understanding, yet structured and easy-to-use attributes are often sparsely populated.

Multi-view Clustering with the Cooperation of Visible and Hidden Views

no code implementations12 Aug 2019 Zhaohong Deng, Ruixiu Liu, Te Zhang, Peng Xu, Kup-Sze Choi, Bin Qin, Shitong Wang

The existing algorithms usually focus on the cooperation of different views in the original space but neglect the influence of the hidden information among these different visible views, or they only consider the hidden information between the views.

Multi-View Fuzzy Clustering with The Alternative Learning between Shared Hidden Space and Partition

no code implementations12 Aug 2019 Zhaohong Deng, Chen Cui, Peng Xu, Ling Liang, Haoran Chen, Te Zhang, Shitong Wang

How to exploit the relation-ship between different views effectively using the characteristic of multi-view data has become a crucial challenge.

Generating Empathetic Responses by Looking Ahead the User's Sentiment

1 code implementation20 Jun 2019 Jamin Shin, Peng Xu, Andrea Madotto, Pascale Fung

Hence, in this paper, we propose Sentiment Look-ahead, which is a novel perspective for empathy that models the future user emotional state.

On Variational Learning of Controllable Representations for Text without Supervision

1 code implementation ICML 2020 Peng Xu, Jackie Chi Kit Cheung, Yanshuai Cao

The variational autoencoder (VAE) can learn the manifold of natural images on certain datasets, as evidenced by meaningful interpolating or extrapolating in the continuous latent space.

Style Transfer Text Style Transfer

Better Long-Range Dependency By Bootstrapping A Mutual Information Regularizer

1 code implementation28 May 2019 Yanshuai Cao, Peng Xu

In this work, we develop a novel regularizer to improve the learning of long-range dependency of sequence data.

General Classification Inductive Bias +2

Deep Image Feature Learning with Fuzzy Rules

no code implementations25 May 2019 Xiang Ma, Zhaohong Deng, Peng Xu, Kup-Sze Choi, Dongrui Wu, Shitong Wang

The method progressively learns image features through a layer-by-layer manner based on fuzzy rules, so the feature learning process can be better explained by the generated rules.

Multi-view Information-theoretic Co-clustering for Co-occurrence Data

1 code implementation25 May 2019 Peng Xu, Zhaohong Deng, Kup-Sze Choi, Longbing Cao, Shitong Wang

More specifically, it exploits the agreement and disagreement among views by sharing a common clustering results along the sample dimension and keeping the clustering results of each view specific along the feature dimension.

Joint Information Preservation for Heterogeneous Domain Adaptation

no code implementations22 May 2019 Peng Xu, Zhaohong Deng, Kup-Sze Choi, Jun Wang, Shitong Wang

The two domains often lie in different feature spaces due to diverse data collection methods, which leads to the more challenging task of heterogeneous domain adaptation (HDA).

Domain Adaptation

Passage Ranking with Weak Supervision

no code implementations ICLR Workshop LLD 2019 Peng Xu, Xiaofei Ma, Ramesh Nallapati, Bing Xiang

In this paper, we propose a \textit{weak supervision} framework for neural ranking tasks based on the data programming paradigm \citep{Ratner2016}, which enables us to leverage multiple weak supervision signals from different sources.

Passage Ranking

Deep Zero-Shot Learning for Scene Sketch

no code implementations11 May 2019 Yao Xie, Peng Xu, Zhanyu Ma

We introduce a novel problem of scene sketch zero-shot learning (SSZSL), which is a challenging task, since (i) different from photo, the gap between common semantic domain (e. g., word vector) and sketch is too huge to exploit common semantic knowledge as the bridge for knowledge transfer, and (ii) compared with single-object sketch, more expressive feature representation for scene sketch is required to accommodate its high-level of abstraction and complexity.

Transfer Learning Zero-Shot Learning

Concise Fuzzy System Modeling Integrating Soft Subspace Clustering and Sparse Learning

no code implementations24 Apr 2019 Peng Xu, Zhaohong Deng, Chen Cui, Te Zhang, Kup-Sze Choi, Gu Suhang, Jun Wang, Shitong Wang

Furthermore, for highly nonlinear modeling task, it is usually necessary to use a large number of rules which further weakens the clarity and interpretability of TSK FS.

Sparse Learning

A novel repetition normalized adversarial reward for headline generation

no code implementations19 Feb 2019 Peng Xu, Pascale Fung

While reinforcement learning can effectively improve language generation models, it often suffers from generating incoherent and repetitive phrases \cite{paulus2017deep}.

Headline generation reinforcement-learning +1

Transfer Representation Learning with TSK Fuzzy System

no code implementations9 Jan 2019 Peng Xu, Zhaohong Deng, Jun Wang, Qun Zhang, Shitong Wang

A core issue in transfer learning is to learn a shared feature space in where the distributions of the data from two domains are matched.

Dimensionality Reduction Representation Learning +1

Trust Region Based Adversarial Attack on Neural Networks

2 code implementations CVPR 2019 Zhewei Yao, Amir Gholami, Peng Xu, Kurt Keutzer, Michael Mahoney

To address this problem, we present a new family of trust region based adversarial attacks, with the goal of computing adversarial perturbations efficiently.

Adversarial Attack

Newton-MR: Inexact Newton Method With Minimum Residual Sub-problem Solver

no code implementations30 Sep 2018 Fred Roosta, Yang Liu, Peng Xu, Michael W. Mahoney

We consider a variant of inexact Newton Method, called Newton-MR, in which the least-squares sub-problems are solved approximately using Minimum Residual method.

Anomaly Detection for Skin Disease Images Using Variational Autoencoder

no code implementations3 Jul 2018 Yuchen Lu, Peng Xu

If we focus on specific diseases, the model is able to detect melanoma with 0. 864 AUCROC and detect actinic keratosis with 0. 872 AUCROC, even if it only sees the images of nevus.

Anomaly Detection

PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and #hashtags

no code implementations SEMEVAL 2018 Ji Ho Park, Peng Xu, Pascale Fung

This paper describes our system that has been submitted to SemEval-2018 Task 1: Affect in Tweets (AIT) to solve five subtasks.

SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval

1 code implementation CVPR 2018 Peng Xu, Yongye Huang, Tongtong Yuan, Kaiyue Pang, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales, Zhanyu Ma, Jun Guo

Key to our network design is the embedding of unique characteristics of human sketch, where (i) a two-branch CNN-RNN architecture is adapted to explore the temporal ordering of strokes, and (ii) a novel hashing loss is specifically designed to accommodate both the temporal and abstract traits of sketches.

Sketch Recognition

Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss

3 code implementations NAACL 2018 Peng Xu, Denilson Barbosa

The task of Fine-grained Entity Type Classification (FETC) consists of assigning types from a hierarchy to entity mentions in text.

General Classification Multi-Label Classification +1

Investigations on Knowledge Base Embedding for Relation Prediction and Extraction

no code implementations6 Feb 2018 Peng Xu, Denilson Barbosa

We report an evaluation of the effectiveness of the existing knowledge base embedding models for relation prediction and for relation extraction on a wide range of benchmarks.

Relation Extraction

GIANT: Globally Improved Approximate Newton Method for Distributed Optimization

no code implementations NeurIPS 2018 Shusen Wang, Farbod Roosta-Khorasani, Peng Xu, Michael W. Mahoney

For distributed computing environment, we consider the empirical risk minimization problem and propose a distributed and communication-efficient Newton-type optimization method.

Distributed Computing Distributed Optimization

Second-Order Optimization for Non-Convex Machine Learning: An Empirical Study

no code implementations25 Aug 2017 Peng Xu, Farbod Roosta-Khorasani, Michael W. Mahoney

While first-order optimization methods such as stochastic gradient descent (SGD) are popular in machine learning (ML), they come with well-known deficiencies, including relatively-slow convergence, sensitivity to the settings of hyper-parameters such as learning rate, stagnation at high training errors, and difficulty in escaping flat regions and saddle points.

Second-order methods

Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information

no code implementations23 Aug 2017 Peng Xu, Fred Roosta, Michael W. Mahoney

In this light, we consider the canonical problem of finite-sum minimization, provide appropriate uniform and non-uniform sub-sampling strategies to construct such Hessian approximations, and obtain optimal iteration complexity for the corresponding sub-sampled trust-region and cubic regularization methods.

Accelerated Stochastic Power Iteration

2 code implementations10 Jul 2017 Christopher De Sa, Bryan He, Ioannis Mitliagkas, Christopher Ré, Peng Xu

We propose a simple variant of the power iteration with an added momentum term, that achieves both the optimal sample and iteration complexity.

Dimensionality Reduction

Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data

no code implementations25 Oct 2016 Paroma Varma, Bryan He, Dan Iter, Peng Xu, Rose Yu, Christopher De Sa, Christopher Ré

Prior work has explored learning accuracies for these sources even without ground truth labels, but they assume that a single accuracy parameter is sufficient to model the behavior of these sources over the entire training set.

Relation Extraction

Sub-sampled Newton Methods with Non-uniform Sampling

no code implementations NeurIPS 2016 Peng Xu, Jiyan Yang, Farbod Roosta-Khorasani, Christopher Ré, Michael W. Mahoney

As second-order methods prove to be effective in finding the minimizer to a high-precision, in this work, we propose randomized Newton-type algorithms that exploit \textit{non-uniform} sub-sampling of $\{\nabla^2 f_i(w)\}_{i=1}^{n}$, as well as inexact updates, as means to reduce the computational complexity.

Second-order methods

Learning Subclass Representations for Visually-varied Image Classification

no code implementations12 Jan 2016 Xinchao Li, Peng Xu, Yue Shi, Martha Larson, Alan Hanjalic

The novelty of the approach is that subclass representations make use of not only the content of the photos themselves, but also information on the co-occurrence of their tags, which determines membership in both subclasses and top-level classes.

Classification General Classification +2

Short-Term Depression in VLSI Stochastic Synapse

no code implementations NeurIPS 2008 Peng Xu, Timothy K. Horiuchi, Pamela A. Abshire

We report a compact realization of short-term depression (STD) in a VLSI stochastic synapse.

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