Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation

Zero-shot NL2SQL is crucial in achieving natural language to SQL that is adaptive to new environments (e.g., new databases, new linguistic phenomena or SQL structures) with zero annotated NL2SQL samples from such environments. Existing approaches either fine-tune pre-trained language models (PLMs) based on annotated data or use prompts to guide fixed large language models (LLMs) such as ChatGPT. PLMs can perform well in schema alignment but struggle to achieve complex reasoning, while LLMs is superior in complex reasoning tasks but cannot achieve precise schema alignment. In this paper, we propose a ZeroNL2SQL framework that combines the complementary advantages of PLMs and LLMs for supporting zero-shot NL2SQL. ZeroNL2SQL first uses PLMs to generate an SQL sketch via schema alignment, then uses LLMs to fill the missing information via complex reasoning. Moreover, in order to better align the generated SQL queries with values in the given database instances, we design a predicate calibration method to guide the LLM in completing the SQL sketches based on the database instances and select the optimal SQL query via an execution-based strategy. Comprehensive experiments show that ZeroNL2SQL can achieve the best zero-shot NL2SQL performance on real-world benchmarks. Specifically, ZeroNL2SQL outperforms the state-of-the-art PLM-based methods by 3.2% to 13% and exceeds LLM-based methods by 10% to 20% on execution accuracy.

RITA: Group Attention is All You Need for Timeseries Analytics

Timeseries analytics is of great importance in many real-world applications. Recently, the Transformer model, popular in natural language processing, has been leveraged to learn high quality feature embeddings from timeseries, core to the performance of various timeseries analytics tasks. However, the quadratic time and space complexities limit Transformers' scalability, especially for long timeseries. To address these issues, we develop a timeseries analytics tool, RITA, which uses a novel attention mechanism, named group attention, to address this scalability issue. Group attention dynamically clusters the objects based on their similarity into a small number of groups and approximately computes the attention at the coarse group granularity. It thus significantly reduces the time and space complexity, yet provides a theoretical guarantee on the quality of the computed attention. The dynamic scheduler of RITA continuously adapts the number of groups and the batch size in the training process, ensuring group attention always uses the fewest groups needed to meet the approximation quality requirement. Extensive experiments on various timeseries datasets and analytics tasks demonstrate that RITA outperforms the state-of-the-art in accuracy and is significantly faster -- with speedups of up to 63X.

iCOIL: Scenario Aware Autonomous Parking Via Integrated Constrained Optimization and Imitation Learning

Autonomous parking (AP) is an emering technique to navigate an intelligent vehicle to a parking space without any human intervention. Existing AP methods based on mathematical optimization or machine learning may lead to potential failures due to either excessive execution time or lack of generalization. To fill this gap, this paper proposes an integrated constrained optimization and imitation learning (iCOIL) approach to achieve efficient and reliable AP. The iCOIL method has two candidate working modes, i.e., CO and IL, and adopts a hybrid scenario analysis (HSA) model to determine the better mode under various scenarios. We implement and verify iCOIL on the Macao Car Racing Metaverse (MoCAM) platform. Results show that iCOIL properly adapts to different scenarios during the entire AP procedure, and achieves significantly larger success rates than other benchmarks.

Multi-Point Integrated Sensing and Communication: Fusion Model and Functionality Selection

Integrated sensing and communication (ISAC) represents a paradigm shift, where previously competing wireless transmissions are jointly designed to operate in harmony via the shared use of the hardware platform for improving the spectral, energy, and hardware efficiencies. However, due to adversarial factors such as fading and blockages, ISAC without fusion may suffer from high sensing uncertainties. This paper presents a multi-point ISAC (MPISAC) system that fuses the outputs from multiple ISAC devices for achieving higher sensing performance by exploiting multi-radar data redundancy. Furthermore, we propose to effectively explore the performance trade-off between sensing and communication via a functionality selection module that adaptively determines the working state (i.e., sensing or communication) of an ISAC device. The crux of our approach is to adopt a fusion model that predicts the fusion accuracy via hypothesis testing and optimal voting analysis. Simulation results demonstrate the superiority of MPISAC over various benchmark schemes and show that the proposed approach can effectively span the trade-off region in ISAC systems.

Stochastic Gradient Descent without Full Data Shuffle

Stochastic gradient descent (SGD) is the cornerstone of modern machine learning (ML) systems. Despite its computational efficiency, SGD requires random data access that is inherently inefficient when implemented in systems that rely on block-addressable secondary storage such as HDD and SSD, e.g., TensorFlow/PyTorch and in-DB ML systems over large files. To address this impedance mismatch, various data shuffling strategies have been proposed to balance the convergence rate of SGD (which favors randomness) and its I/O performance (which favors sequential access). In this paper, we first conduct a systematic empirical study on existing data shuffling strategies, which reveals that all existing strategies have room for improvement -- they all suffer in terms of I/O performance or convergence rate. With this in mind, we propose a simple but novel hierarchical data shuffling strategy, CorgiPile. Compared with existing strategies, CorgiPile avoids a full data shuffle while maintaining comparable convergence rate of SGD as if a full shuffle were performed. We provide a non-trivial theoretical analysis of CorgiPile on its convergence behavior. We further integrate CorgiPile into PyTorch by designing new parallel/distributed shuffle operators inside a new CorgiPileDataSet API. We also integrate CorgiPile into PostgreSQL by introducing three new physical operators with optimizations. Our experimental results show that CorgiPile can achieve comparable convergence rate with the full shuffle based SGD for both deep learning and generalized linear models. For deep learning models on ImageNet dataset, CorgiPile is 1.5X faster than PyTorch with full data shuffle. For in-DB ML with linear models, CorgiPile is 1.6X-12.8X faster than two state-of-the-art in-DB ML systems, Apache MADlib and Bismarck, on both HDD and SSD.

nvBench: A Large-Scale Synthesized Dataset for Cross-Domain Natural Language to Visualization Task

NL2VIS - which translates natural language (NL) queries to corresponding visualizations (VIS) - has attracted more and more attention both in commercial visualization vendors and academic researchers. In the last few years, the advanced deep learning-based models have achieved human-like abilities in many natural language processing (NLP) tasks, which clearly tells us that the deep learning-based technique is a good choice to push the field of NL2VIS. However, a big balk is the lack of benchmarks with lots of (NL, VIS) pairs. We present nvBench, the first large-scale NL2VIS benchmark, containing 25,750 (NL, VIS) pairs from 750 tables over 105 domains, synthesized from (NL, SQL) benchmarks to support cross-domain NL2VIS task. The quality of nvBench has been extensively validated by 23 experts and 300+ crowd workers. Deep learning-based models training using nvBench demonstrate that nvBench can push the field of NL2VIS.

Rethinking the Tradeoff in Integrated Sensing and Communication: Recognition Accuracy versus Communication Rate

Integrated sensing and communication (ISAC) is a promising technology to improve the band-utilization efficiency via spectrum sharing or hardware sharing between radar and communication systems. Since a common radio resource budget is shared by both functionalities, there exists a tradeoff between the sensing and communication performance. However, this tradeoff curve is currently unknown in ISAC systems with human motion recognition tasks based on deep learning. To fill this gap, this paper formulates and solves a multi-objective optimization problem which simultaneously maximizes the recognition accuracy and the communication data rate. The key ingredient of this new formulation is a nonlinear recognition accuracy model with respect to the wireless resources, where the model is derived from power function regression of the system performance of the deep spectrogram network. To avoid cost-expensive data collection procedures, a primitive-based autoregressive hybrid (PBAH) channel model is developed, which facilitates efficient training and testing dataset generation for human motion recognition in a virtual environment. Extensive results demonstrate that the proposed wireless recognition accuracy and PBAH channel models match the actual experimental data very well. Moreover, it is found that the accuracy-rate region consists of a communication saturation zone, a sensing saturation zone, and a communication-sensing adversarial zone, of which the third zone achieves the desirable balanced performance for ISAC systems.

Accelerating Edge Intelligence via Integrated Sensing and Communication

Realizing edge intelligence consists of sensing, communication, training, and inference stages. Conventionally, the sensing and communication stages are executed sequentially, which results in excessive amount of dataset generation and uploading time. This paper proposes to accelerate edge intelligence via integrated sensing and communication (ISAC). As such, the sensing and communication stages are merged so as to make the best use of the wireless signals for the dual purpose of dataset generation and uploading. However, ISAC also introduces additional interference between sensing and communication functionalities. To address this challenge, this paper proposes a classification error minimization formulation to design the ISAC beamforming and time allocation. Globally optimal solution is derived via the rank-1 guaranteed semidefinite relaxation, and performance analysis is performed to quantify the ISAC gain. Simulation results are provided to verify the effectiveness of the proposed ISAC scheme. Interestingly, it is found that when the sensing time dominates the communication time, ISAC is always beneficial. However, when the communication time dominates, the edge intelligence with ISAC scheme may not be better than that with the conventional scheme, since ISAC introduces harmful interference between the sensing and communication signals.

Hierarchical Temperature Imaging Using Pseudo-Inversed Convolutional Neural Network Aided TDLAS Tomography

As an in situ combustion diagnostic tool, Tunable Diode Laser Absorption Spectroscopy (TDLAS) tomography has been widely used for imaging of two-dimensional temperature distributions in reactive flows. Compared with the computational tomographic algorithms, Convolutional Neural Networks (CNNs) have been proofed to be more robust and accurate for image reconstruction, particularly in case of limited access of laser beams in the Region of Interest (RoI). In practice, flame in the RoI that requires to be reconstructed with good spatial resolution is commonly surrounded by low-temperature background. Although the background is not of high interest, spectroscopic absorption still exists due to heat dissipation and gas convection. Therefore, we propose a Pseudo-Inversed CNN (PI-CNN) for hierarchical temperature imaging that (a) uses efficiently the training and learning resources for temperature imaging in the RoI with good spatial resolution, and (b) reconstructs the less spatially resolved background temperature by adequately addressing the integrity of the spectroscopic absorption model. In comparison with the traditional CNN, the newly introduced pseudo inversion of the RoI sensitivity matrix is more penetrating for revealing the inherent correlation between the projection data and the RoI to be reconstructed, thus prioritising the temperature imaging in the RoI with high accuracy and high computational efficiency. In this paper, the proposed algorithm was validated by both numerical simulation and lab-scale experiment, indicating good agreement between the phantoms and the high-fidelity reconstructions.

Wireless Sensing With Deep Spectrogram Network and Primitive Based Autoregressive Hybrid Channel Model

Human motion recognition (HMR) based on wireless sensing is a low-cost technique for scene understanding. Current HMR systems adopt support vector machines (SVMs) and convolutional neural networks (CNNs) to classify radar signals. However, whether a deeper learning model could improve the system performance is currently not known. On the other hand, training a machine learning model requires a large dataset, but data gathering from experiment is cost-expensive and time-consuming. Although wireless channel models can be adopted for dataset generation, current channel models are mostly designed for communication rather than sensing. To address the above problems, this paper proposes a deep spectrogram network (DSN) by leveraging the residual mapping technique to enhance the HMR performance. Furthermore, a primitive based autoregressive hybrid (PBAH) channel model is developed, which facilitates efficient training and testing dataset generation for HMR in a virtual environment. Experimental results demonstrate that the proposed PBAH channel model matches the actual experimental data very well and the proposed DSN achieves significantly smaller recognition error than that of CNN.