arXiv subjects

Lihao Zhang

Publications and source records attributed to Lihao Zhang.

23 records · Page 2Linked to original sources

arXiv2022

Share the Tensor Tea: How Databases can Leverage the Machine Learning Ecosystem

We demonstrate Tensor Query Processor (TQP): a query processor that automatically compiles relational operators into tensor programs. By leveraging tensor runtimes such as PyTorch, TQP is able to: (1) integrate with ML tools (e.g., Pandas for data ingestion, Tensorboard for visualization); (2) target different hardware (e.g., CPU, GPU) and software (e.g., browser) backends; and (3) end-to-end accelerate queries containing both relational and ML operators. TQP is generic enough to support the TPC-H benchmark, and it provides performance that is comparable to, and often better than, that of specialized CPU and GPU query processors.

cs.DB↗

arXiv2022

Reliable Wireless Networking via Soft-Source Information Combining

This paper puts forth a multi-stream networking paradigm, referred to as soft-source-information-combining (SSIC), to support wireless Internet of Things (IoT) applications with ultra-reliability requirements. For SSIC networking, an SSIC dispatcher at the source dispatches duplicates of packets over multiple streams, which may be established over different physical wireless networks. If a packet on a stream cannot be decoded due to wireless interference or noise, the decoder makes available the packet's soft information. An aggregator then combines the soft information of the duplicates to boost reliability. Of importance are two challenges: i) how to descramble the scrambled soft information from different streams to enable correct SSIC; ii) the construct of an SSIC dispatching and aggregation framework compatible with commercial network interface cards (NICs) and TCP/IP networks. To address the challenges, we put forth: i) a soft descrambling (SD) method to minimize the bit-error rate (BER) and packet-error rate (PER) at the SSIC's output; ii) an SSIC networking architecture readily deployable over today's TCP/IP networks without specialized NICs. For concept proving and experimentation, we realized an SSIC system over two Wi-Fi's physical paths in such a way that all legacy TCP/IP applications can enjoy the reliability brought forth by SSIC without modification. Experiments over our testbed corroborate the effectiveness of SSIC in lowering the packet delivery failure rate and the possibility of SSIC in providing 99.99% reliable packet delivery for short-range communication.

cs.NI↗

arXiv2021

Independent Ethical Assessment of Text Classification Models: A Hate Speech Detection Case Study

An independent ethical assessment of an artificial intelligence system is an impartial examination of the system's development, deployment, and use in alignment with ethical values. System-level qualitative frameworks that describe high-level requirements and component-level quantitative metrics that measure individual ethical dimensions have been developed over the past few years. However, there exists a gap between the two, which hinders the execution of independent ethical assessments in practice. This study bridges this gap and designs a holistic independent ethical assessment process for a text classification model with a special focus on the task of hate speech detection. The assessment is further augmented with protected attributes mining and counterfactual-based analysis to enhance bias assessment. It covers assessments of technical performance, data bias, embedding bias, classification bias, and interpretability. The proposed process is demonstrated through an assessment of a deep hate speech detection model.

cs.CY↗

arXiv2021

Speeding up Block Propagation in Blockchain Network: Uncoded and Coded Designs

We design and validate new block propagation protocols for the peer-to-peer (P2P) network of the Bitcoin blockchain. Despite its strong protection for security and privacy, the current Bitcoin blockchain can only support a low number of transactions per second (TPS). In this work, we redesign the current Bitcoin's networking protocol to increase TPS without changing vital components in its consensus-building protocol. In particular, we improve the compact-block relaying protocol to enable the propagation of blocks containing a massive number of transactions without inducing extra propagation latencies. Our improvements consist of (i) replacing the existing store-and-forward compact-block relaying scheme with a cut-through compact-block relaying scheme; (ii) exploiting rateless erasure codes for P2P networks to increase block-propagation efficiency. Since our protocols only need to rework the current Bitcoin's networking protocol and does not modify the data structures and crypto-functional components, they can be seamlessly incorporated into the existing Bitcoin blockchain. To validate our designs, we perform analysis on our protocols and implement a Bitcoin network simulator on NS3 to run different block propagation protocols. The analysis and experimental results confirm that our new block propagation protocols could increase the TPS of the Bitcoin blockchain by 100x without compromising security and consensus-building.

cs.NI↗

arXiv2019

Deep Learning for Joint MIMO Detection and Channel Decoding

We propose a deep-learning approach for the joint MIMO detection and channel decoding problem. Conventional MIMO receivers adopt a model-based approach for MIMO detection and channel decoding in linear or iterative manners. However, due to the complex MIMO signal model, the optimal solution to the joint MIMO detection and channel decoding problem (i.e., the maximum likelihood decoding of the transmitted codewords from the received MIMO signals) is computationally infeasible. As a practical measure, the current model-based MIMO receivers all use suboptimal MIMO decoding methods with affordable computational complexities. This work applies the latest advances in deep learning for the design of MIMO receivers. In particular, we leverage deep neural networks (DNN) with supervised training to solve the joint MIMO detection and channel decoding problem. We show that DNN can be trained to give much better decoding performance than conventional MIMO receivers do. Our simulations show that a DNN implementation consisting of seven hidden layers can outperform conventional model-based linear or iterative receivers. This performance improvement points to a new direction for future MIMO receiver design.

cs.IT↗