Models, code, and papers for "Jiahao Chen":

Fair lending needs explainable models for responsible recommendation

Sep 12, 2018
Jiahao Chen

The financial services industry has unique explainability and fairness challenges arising from compliance and ethical considerations in credit decisioning. These challenges complicate the use of model machine learning and artificial intelligence methods in business decision processes.

* 4 pages, position paper accepted for FATREC 2018 conference at ACM RecSys 

  Click for Model/Code and Paper
Fast Flexible Function Dispatch in Julia

Aug 09, 2018
Jeff Bezanson, Jake Bolewski, Jiahao Chen

Technical computing is a challenging application area for programming languages to address. This is evinced by the unusually large number of specialized languages in the area (e.g. MATLAB, R), and the complexity of common software stacks, often involving multiple languages and custom code generators. We believe this is ultimately due to key characteristics of the domain: highly complex operators, a need for extensive code specialization for performance, and a desire for permissive high-level programming styles allowing productive experimentation. The Julia language attempts to provide a more effective structure for this kind of programming by allowing programmers to express complex polymorphic behaviors using dynamic multiple dispatch over parametric types. The forms of extension and reuse permitted by this paradigm have proven valuable for technical computing. We report on how this approach has allowed domain experts to express useful abstractions while simultaneously providing a natural path to better performance for high-level technical code.

* 15 pages, repository at 

  Click for Model/Code and Paper
Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved

Nov 27, 2018
Jiahao Chen, Nathan Kallus, Xiaojie Mao, Geoffry Svacha, Madeleine Udell

Assessing the fairness of a decision making system with respect to a protected class, such as gender or race, is challenging when class membership labels are unavailable. Probabilistic models for predicting the protected class based on observable proxies, such as surname and geolocation for race, are sometimes used to impute these missing labels for compliance assessments. Empirically, these methods are observed to exaggerate disparities, but the reason why is unknown. In this paper, we decompose the biases in estimating outcome disparity via threshold-based imputation into multiple interpretable bias sources, allowing us to explain when over- or underestimation occurs. We also propose an alternative weighted estimator that uses soft classification, and show that its bias arises simply from the conditional covariance of the outcome with the true class membership. Finally, we illustrate our results with numerical simulations and a public dataset of mortgage applications, using geolocation as a proxy for race. We confirm that the bias of threshold-based imputation is generally upward, but its magnitude varies strongly with the threshold chosen. Our new weighted estimator tends to have a negative bias that is much simpler to analyze and reason about.

* 13 pages, 11 figures, FAT*' 19: Conference on Fairness, Accountability, and Transparency (FAT*' 19), January 29-31, 2019, Atlanta, GA, USA 

  Click for Model/Code and Paper
Biologically inspired model simulating visual pathways and cerebellum function in human - Achieving visuomotor coordination and high precision movement with learning ability

Mar 08, 2016
Wei Wu, Hong Qiao, Jiahao Chen, Peijie Yin, Yinlin Li

In recent years, the interdisciplinary research between information science and neuroscience has been a hotspot. In this paper, based on recent biological findings, we proposed a new model to mimic visual information processing, motor planning and control in central and peripheral nervous systems of human. Main steps of the model are as follows: 1) Simulating "where" pathway in human: the Selective Search method is applied to simulate the function of human dorsal visual pathway to localize object candidates; 2) Simulating "what" pathway in human: a Convolutional Deep Belief Network is applied to simulate the hierarchical structure and function of human ventral visual pathway for object recognition; 3) Simulating motor planning process in human: habitual motion planning process in human is simulated, and motor commands are generated from the combination of control signals from past experiences; 4) Simulating precise movement control in human: calibrated control signals, which mimic the adjustment for movement from cerebellum in human, are generated and updated from calibration of movement errors in past experiences, and sent to the movement model to achieve high precision. The proposed framework mimics structures and functions of human recognition, visuomotor coordination and precise motor control. Experiments on object localization, recognition and movement control demonstrate that the new proposed model can not only accomplish visuomotor coordination tasks, but also achieve high precision movement with learning ability. Meanwhile, the results also prove the validity of the introduced mechanisms. Furthermore, the proposed model could be generalized and applied to other systems, such as mechanical and electrical systems in robotics, to achieve fast response, high precision movement with learning ability.

* 12 pages, 13 figures 

  Click for Model/Code and Paper
A Multimodal Alerting System for Online Class Quality Assurance

Sep 01, 2019
Jiahao Chen, Hang Li, Wenxin Wang, Wenbiao Ding, Gale Yan Huang, Zitao Liu

Online 1 on 1 class is created for more personalized learning experience. It demands a large number of teaching resources, which are scarce in China. To alleviate this problem, we build a platform (marketplace), i.e., \emph{Dahai} to allow college students from top Chinese universities to register as part-time instructors for the online 1 on 1 classes. To warn the unqualified instructors and ensure the overall education quality, we build a monitoring and alerting system by utilizing multimodal information from the online environment. Our system mainly consists of two key components: banned word detector and class quality predictor. The system performance is demonstrated both offline and online. By conducting experimental evaluation of real-world online courses, we are able to achieve 74.3\% alerting accuracy in our production environment.

* The 20th International Conference on Artificial Intelligence in Education(AIED), 2019 

  Click for Model/Code and Paper
Robust Tracking Using Region Proposal Networks

May 30, 2017
Jimmy Ren, Zhiyang Yu, Jianbo Liu, Rui Zhang, Wenxiu Sun, Jiahao Pang, Xiaohao Chen, Qiong Yan

Recent advances in visual tracking showed that deep Convolutional Neural Networks (CNN) trained for image classification can be strong feature extractors for discriminative trackers. However, due to the drastic difference between image classification and tracking, extra treatments such as model ensemble and feature engineering must be carried out to bridge the two domains. Such procedures are either time consuming or hard to generalize well across datasets. In this paper we discovered that the internal structure of Region Proposal Network (RPN)'s top layer feature can be utilized for robust visual tracking. We showed that such property has to be unleashed by a novel loss function which simultaneously considers classification accuracy and bounding box quality. Without ensemble and any extra treatment on feature maps, our proposed method achieved state-of-the-art results on several large scale benchmarks including OTB50, OTB100 and VOT2016. We will make our code publicly available.

  Click for Model/Code and Paper
Accurate Single Stage Detector Using Recurrent Rolling Convolution

Apr 19, 2017
Jimmy Ren, Xiaohao Chen, Jianbo Liu, Wenxiu Sun, Jiahao Pang, Qiong Yan, Yu-Wing Tai, Li Xu

Most of the recent successful methods in accurate object detection and localization used some variants of R-CNN style two stage Convolutional Neural Networks (CNN) where plausible regions were proposed in the first stage then followed by a second stage for decision refinement. Despite the simplicity of training and the efficiency in deployment, the single stage detection methods have not been as competitive when evaluated in benchmarks consider mAP for high IoU thresholds. In this paper, we proposed a novel single stage end-to-end trainable object detection network to overcome this limitation. We achieved this by introducing Recurrent Rolling Convolution (RRC) architecture over multi-scale feature maps to construct object classifiers and bounding box regressors which are "deep in context". We evaluated our method in the challenging KITTI dataset which measures methods under IoU threshold of 0.7. We showed that with RRC, a single reduced VGG-16 based model already significantly outperformed all the previously published results. At the time this paper was written our models ranked the first in KITTI car detection (the hard level), the first in cyclist detection and the second in pedestrian detection. These results were not reached by the previous single stage methods. The code is publicly available.

* CVPR 2017 

  Click for Model/Code and Paper
Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications

Feb 12, 2018
Haowen Xu, Wenxiao Chen, Nengwen Zhao, Zeyan Li, Jiahao Bu, Zhihan Li, Ying Liu, Youjian Zhao, Dan Pei, Yang Feng, Jie Chen, Zhaogang Wang, Honglin Qiao

To ensure undisrupted business, large Internet companies need to closely monitor various KPIs (e.g., Page Views, number of online users, and number of orders) of its Web applications, to accurately detect anomalies and trigger timely troubleshooting/mitigation. However, anomaly detection for these seasonal KPIs with various patterns and data quality has been a great challenge, especially without labels. In this paper, we proposed Donut, an unsupervised anomaly detection algorithm based on VAE. Thanks to a few of our key techniques, Donut greatly outperforms a state-of-arts supervised ensemble approach and a baseline VAE approach, and its best F-scores range from 0.75 to 0.9 for the studied KPIs from a top global Internet company. We come up with a novel KDE interpretation of reconstruction for Donut, making it the first VAE-based anomaly detection algorithm with solid theoretical explanation.

* 12 pages (including references), 17 figures, submitted to WWW 2018: The 2018 Web Conference, April 23--27, 2018, Lyon, France. The contents discarded from the conference version due to the 9-page limitation are also included in this version 

  Click for Model/Code and Paper
Deep End-to-End Alignment and Refinement for Time-of-Flight RGB-D Module

Sep 17, 2019
Di Qiu, Jiahao Pang, Wenxiu Sun, Chengxi Yang

Recently, it is increasingly popular to equip mobile RGB cameras with Time-of-Flight (ToF) sensors for active depth sensing. However, for off-the-shelf ToF sensors, one must tackle two problems in order to obtain high-quality depth with respect to the RGB camera, namely 1) online calibration and alignment; and 2) complicated error correction for ToF depth sensing. In this work, we propose a framework for jointly alignment and refinement via deep learning. First, a cross-modal optical flow between the RGB image and the ToF amplitude image is estimated for alignment. The aligned depth is then refined via an improved kernel predicting network that performs kernel normalization and applies the bias prior to the dynamic convolution. To enrich our data for end-to-end training, we have also synthesized a dataset using tools from computer graphics. Experimental results demonstrate the effectiveness of our approach, achieving state-of-the-art for ToF refinement.

* ICCV2019 

  Click for Model/Code and Paper
3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model

Mar 20, 2018
Jin Zeng, Gene Cheung, Michael Ng, Jiahao Pang, Cheng Yang

3D point cloud - a new signal representation of volumetric objects - is a discrete collection of triples marking exterior object surface locations in 3D space. Conventional imperfect acquisition processes of 3D point cloud - e.g., stereo-matching from multiple viewpoint images or depth data acquired directly from active light sensors - imply non-negligible noise in the data. In this paper, we adopt a previously proposed low-dimensional manifold model for the surface patches in the point cloud and seek self-similar patches to denoise them simultaneously using the patch manifold prior. Due to discrete observations of the patches on the manifold, we approximate the manifold dimension computation defined in the continuous domain with a patch-based graph Laplacian regularizer and propose a new discrete patch distance measure to quantify the similarity between two same-sized surface patches for graph construction that is robust to noise. We show that our graph Laplacian regularizer has a natural graph spectral interpretation, and has desirable numerical stability properties via eigenanalysis. Extensive simulation results show that our proposed denoising scheme can outperform state-of-the-art methods in objective metrics and can better preserve visually salient structural features like edges.

  Click for Model/Code and Paper
Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching

Jul 30, 2018
Jiahao Pang, Wenxiu Sun, Jimmy SJ. Ren, Chengxi Yang, Qiong Yan

Leveraging on the recent developments in convolutional neural networks (CNNs), matching dense correspondence from a stereo pair has been cast as a learning problem, with performance exceeding traditional approaches. However, it remains challenging to generate high-quality disparities for the inherently ill-posed regions. To tackle this problem, we propose a novel cascade CNN architecture composing of two stages. The first stage advances the recently proposed DispNet by equipping it with extra up-convolution modules, leading to disparity images with more details. The second stage explicitly rectifies the disparity initialized by the first stage; it couples with the first-stage and generates residual signals across multiple scales. The summation of the outputs from the two stages gives the final disparity. As opposed to directly learning the disparity at the second stage, we show that residual learning provides more effective refinement. Moreover, it also benefits the training of the overall cascade network. Experimentation shows that our cascade residual learning scheme provides state-of-the-art performance for matching stereo correspondence. By the time of the submission of this paper, our method ranks first in the KITTI 2015 stereo benchmark, surpassing the prior works by a noteworthy margin.

* Accepted at ICCVW 2017. The first two authors contributed equally to this paper 

  Click for Model/Code and Paper
Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains

Mar 18, 2018
Jiahao Pang, Wenxiu Sun, Chengxi Yang, Jimmy Ren, Ruichao Xiao, Jin Zeng, Liang Lin

Despite the recent success of stereo matching with convolutional neural networks (CNNs), it remains arduous to generalize a pre-trained deep stereo model to a novel domain. A major difficulty is to collect accurate ground-truth disparities for stereo pairs in the target domain. In this work, we propose a self-adaptation approach for CNN training, utilizing both synthetic training data (with ground-truth disparities) and stereo pairs in the new domain (without ground-truths). Our method is driven by two empirical observations. By feeding real stereo pairs of different domains to stereo models pre-trained with synthetic data, we see that: i) a pre-trained model does not generalize well to the new domain, producing artifacts at boundaries and ill-posed regions; however, ii) feeding an up-sampled stereo pair leads to a disparity map with extra details. To avoid i) while exploiting ii), we formulate an iterative optimization problem with graph Laplacian regularization. At each iteration, the CNN adapts itself better to the new domain: we let the CNN learn its own higher-resolution output; at the meanwhile, a graph Laplacian regularization is imposed to discriminatively keep the desired edges while smoothing out the artifacts. We demonstrate the effectiveness of our method in two domains: daily scenes collected by smartphone cameras, and street views captured in a driving car.

* Accepted at CVPR 2018 

  Click for Model/Code and Paper
Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization

Dec 04, 2019
Yuchen Guo, Nicholas Hanoian, Zhexiao Lin, Nicholas Liskij, Hanbaek Lyu, Deanna Needell, Jiahao Qu, Henry Sojico, Yuliang Wang, Zhe Xiong, Zhenhong Zou

We propose a novel model for a topic-aware chatbot by combining the traditional Recurrent Neural Network (RNN) encoder-decoder model with a topic attention layer based on Nonnegative Matrix Factorization (NMF). After learning topic vectors from an auxiliary text corpus via NMF, the decoder is trained so that it is more likely to sample response words from the most correlated topic vectors. One of the main advantages in our architecture is that the user can easily switch the NMF-learned topic vectors so that the chatbot obtains desired topic-awareness. We demonstrate our model by training on a single conversational data set which is then augmented with topic matrices learned from different auxiliary data sets. We show that our topic-aware chatbot not only outperforms the non-topic counterpart, but also that each topic-aware model qualitatively and contextually gives the most relevant answer depending on the topic of question.

* 14 pages, 1 figure, 2 tables 

  Click for Model/Code and Paper