Haichen Shen

Haichen Shen (沈海晨)

Ph.D student @ System Lab, CSE, UW
haichen at cs.washington.edu
CSE 391, Paul G. Allen Center

I'm a fifth year Ph.D. student in Computer Science at University of Washington, working with Prof. Arvind Krishnamurthy and Dr. Matthai Philipose. Previously I worked with Prof. David Wetherall and Prof. Aruna Balasumbramanian. I received my bachelor degree in Institute for Theoretical Computer Science (supervised by Prof. Andrew Yao) at Tsinghua University.

Research Projects

  • Sequential Model Specialization: aims to accelerate the speed of recognizing entities such as objects, people, scenes and activities in every frame of video footage of day-to-day life, by exploiting "specialized" convolutional neural networks (CNNs) under highly skewed distribution. When applied to recognizing faces in TV shows and movies we realized end-to-end classification speedups of 2.4-7.8x/2.6-11.2x (on GPU/CPU) relative to a state-of-the-art convolutional neural network, at competitive accuracy.
  • MCDNN: an approximation-based execution framework for applying computer vision to video on cloud-backed mobile devices using Deep Neural Networks(DNNs). The computational demands of DNNs are high enough that, without careful resource management, such applications strain device battery, and cloud cost budgets. MCDNN allows each request to be served approximately, by systematically trading off DNN classification accuracy for resource use.
  • Metasync: a secure and reliable file synchronization service that uses multiple cloud synchronization services as untrusted storage providers. We devised a novel variant of Paxos that provides efficient and consistent updates on top of the unmodified APIs exported by existing services.
  • Mobile Hub: leverages heterogeneous hardware, such as sensor hubs, to improve the power efficiency of always-on sensing applications on mobile phones. MobileHub rewrites the binary of a given application without programmer effort to make it more power efficient.

Publications

Fast Video Classification via Adaptive Cascading of Deep Models
Haichen Shen, Seungyeop Han, Matthai Philipose, Arvind Krishnamurthy
CVPR, July 2017 (spotlight)
abstract paper bibtex slides talk Project
Recent advances have enabled “oracle” classifiers that can classify across many classes and input distributions with high accuracy without retraining. However, these classifiers are relatively heavyweight, so that applying them to classify video is costly. We show that day-to-day video exhibits highly skewed class distributions over the short term, and that these distributions can be classified by much simpler models. We formulate the problem of detecting the short-term skews online and exploiting models based on it as a new sequential decision making problem dubbed the Online Bandit Problem, and present a new algorithm to solve it. When applied to recognizing faces in TV shows and movies, we realize end-toend classification speedups of 2.4-7.8×/2.6-11.2× (on GPU/CPU) relative to a state-of-the-art convolutional neural network, at competitive accuracy.
MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints
Seungyeop Han*, Haichen Shen*, Matthai Philipose, Sharad Agarwal, Alec Wolman, Arvind Krishnamurthy
MobiSys, Jun. 2016 (*equally contributed)
abstract paper bibtex slides 1-min video talk
We consider applying computer vision to video on cloud-backed mobile devices using Deep Neural Networks (DNNs). The computational demands of DNNs are high enough that, without careful resource management, such applications strain device battery, wireless data, and cloud cost budgets. We pose the corresponding resource management problem, which we call Approximate Model Scheduling, as one of serving a stream of heterogeneous (i.e., solving multiple classification problems) requests under resource constraints. We present the design and implementation of an optimizing compiler and runtime scheduler to address this problem. Going beyond traditional resource allocators, we allow each request to be served approximately, by systematically trading off DNN classification accuracy for resource use, and remotely, by reasoning about on-device/cloud execution trade-offs. To inform the resource allocator, we characterize how several common DNNs, when subjected to state-of-the art optimizations, trade off accuracy for resource use such as memory, computation, and energy. The heterogeneous streaming setting is a novel one for DNN execution, and we introduce two new and powerful DNN optimizations that exploit it. Using the challenging continuous mobile vision domain as a case study, we show that our techniques yield significant reductions in resource usage and perform effectively over a broad range of operating conditions.
Enhancing Mobile Apps To Use Sensor Hubs Without Programmer Effort
Haichen Shen, Aruna Balasubramanian, Anthony LaMarca, David Wetherall
Ubicomp, Sept. 2015 (Best paper award, Gaetano Borriello best student paper award)
abstract paper bibtex slides project
Always-on continuous sensing apps drain the battery quickly because they prevent the main processor from sleeping. Instead, sensor hub hardware, available in many smartphones today, can run continuous sensing at lower power while keeping the main processor idle. However, developers have to divide functionality between the main processor and the sensor hub. We implement MobileHub, a system that automatically rewrites applications to leverage the sensor hub without additional programming effort. MobileHub uses a combination of dynamic taint tracking and machine learning to learn when it is safe to leverage the sensor hub without affecting application semantics. We implement MobileHub in Android and prototype a sensor hub on a 8-bit AVR micro-controller. We experiment with 20 applications from Google Play. Our evaluation shows that MobileHub significantly reduces power consumption for continuous sensing apps.
MetaSync: File Synchronization Across Multiple Untrusted Storage Services
Seungyeop Han, Haichen Shen, Taesoo Kim, Arvind Krishnamurthy, Thomas Anderson, David Wetherall
USENIX ATC, July 2015
abstract paper bibtex project

Cloud-based file synchronization services, such as Dropbox, are a worldwide resource for many millions of users. However, individual services often have tight resource limits, suffer from temporary outages or even shutdowns, and sometimes silently corrupt or leak user data.

We design, implement, and evaluate MetaSync, a secure and reliable file synchronization service that uses multiple cloud synchronization services as untrusted storage providers. To make MetaSync work correctly, we devise a novel variant of Paxos that provides efficient and consistent updates on top of the unmodified APIs exported by existing services. Our system automatically redistributes files upon reconfiguration of providers.

Our evaluation shows that MetaSync provides low update latency and high update throughput while being more trustworthy and available. MetaSync outperforms its underlying cloud services by 1.2-10× on three realistic workloads.

Enable Flexible Spectrum Access with Spectrum Virtualization
Kun Tan, Haichen Shen, Jiansong Zhang, Yongguang Zhang
DySPAN, Oct. 2012
abstract paper bibtex

Enabling flexible spectrum access (FSA) in existing wireless networks is challenging due to the limited spectrum programmability – the ability to change spectrum properties of a signal to match an arbitrary frequency allocation. This paper argues that spectrum programmability can be separated from general wireless physical layer (PHY) modulation. Therefore, we can support flexible spectrum programmability by inserting a new spectrum virtualization layer (SVL) directly below traditional wireless PHY, and enable FSA for wireless networks without changing their PHY designs.

SVL provides a virtual baseband abstraction to wireless PHY, which is static, contiguous, with a desirable width defined by the PHY. At the sender side, SVL reshapes the modulated baseband signals into waveform that matches the dynamically allocated physical frequency bands – which can be of different width, or non-contiguous – while keeping the modulated information unchanged. At the receiver side, SVL performs the inverse reshaping operation that collects the waveform from each physical band, and reconstructs the original modulated signals for PHY. All these reshaping operations are performed at the signal level and therefore SVL is agnostic and transparent to upper PHY. We have implemented a prototype of SVL on a software radio platform, and tested it with various wireless PHYs. Our experiments show SVL is flexible and effective to support FSA in existing wireless networks.

Frame Retransmissions Considered Harmful: Improving Spectrum Efficiency Using Micro-ACKs
Jiansong Zhang, Haichen Shen, Kun Tan, Ranveer Chandra, Yongguang Zhang, Qian Zhang
MobiCom, Aug. 2012
abstract paper bibtex
Retransmissions reduce the efficiency of data communication in wireless networks because of: (i) per-retransmission packet headers, (ii) contention overhead on every retransmission, and (iii) redundant bits in every retransmission. In fact, every retransmission nearly doubles the time to successfully deliver the packet. To improve spectrum efficiency in a lossy environment, we propose a new in-frame retransmission scheme using µACKs. Instead of waiting for the entire transmission to end before sending the ACK, the receiver sends smaller µACKs for every few symbols, on a separate narrow feedback channel. Based on these µACKs, the sender only retransmits the lost symbols after the last data symbol in the frame, thereby adaptively changing the frame size to ensure it is successfully delivered. We have implemented µACK on the Sora platform. Experiments with our prototype validate the feasibility of symbollevel µACK. By significantly reducing the retransmistion overhead, the sender is able to aggressively use higher data rate for a lossy link. Both improve the overall network efficiency. Our experimental results from a controlled environment and an 9-node software radio testbed show that µACK can have up to 140% throughput gain over 802.11g and up to 60% gain over the best known retransmission scheme.

Teaching Experience

  • Instructor for CSE 599G1: Deep Learning System, Spring 2017.
  • TA for CSEP 552: Distributed Systems, Winter 2016.
  • TA for CSEP 561: Network Systems, Fall 2013.

Last update: Aug. 2017