arXiv subjects

Ao Liu

Publications and source records attributed to Ao Liu.

At least 55 records · Page 3Linked to original sources

arXiv2023

Trading Off Voting Axioms for Privacy

In this paper, we investigate tradeoffs among differential privacy (DP) and several important voting axioms: Pareto efficiency, SD-efficiency, PC-efficiency, Condorcet consistency, and Condorcet loser criterion. We provide upper and lower bounds on the two-way tradeoffs between DP and each axiom. We also provide upper and lower bounds on three-way tradeoffs among DP and every pairwise combination of all the axioms, showing that, while the axioms are compatible without DP, their upper bounds cannot be achieved simultaneously under DP. Our results illustrate the effect of DP on the satisfaction and compatibility of voting axioms.

cs.GT↗

arXiv2023

Accelerating Voting by Quantum Computation

Studying the computational complexity and designing fast algorithms for determining winners under voting rules are classical and fundamental questions in computational social choice. In this paper, we accelerate voting by leveraging quantum computation: we propose a quantum-accelerated voting algorithm that can be applied to any anonymous voting rule. We show that our algorithm can be quadratically faster than any classical algorithm (based on sampling with replacement) under a wide range of common voting rules, including positional scoring rules, Copeland, and single transferable voting (STV). Precisely, our quantum-accelerated voting algorithm outputs the correct winner with high probability in $Θ\left(\frac{n}{\text{MOV}}\right)$ time, where $n$ is the number of votes and $\text{MOV}$ is {\em margin of victory}, the smallest number of voters to change the winner. In contrast, any classical voting algorithm based on sampling with replacement requires $Ω\left(\frac{n^2}{\text{MOV}^2}\right)$ time under a large class of voting rules. Our theoretical results are supported by experiments under plurality, Borda, Copeland, and STV.

cs.CY↗

arXiv2023

Task Containerization and Container Placement Optimization for MEC: A Joint Communication and Computing Perspective

Containers are used by an increasing number of Internet service providers to deploy their applications in multi-access edge computing (MEC) systems. Although container-based virtualization technologies significantly increase application availability, they may suffer expensive communication overhead and resource use imbalances. However, so far there has been a scarcity of studies to conquer these difficulties. In this paper, we design a workflow-based mathematical model for applications built upon interdependent multitasking composition, formulate a multi-objective combinatorial optimization problem composed of two subproblems -- graph partitioning and multi-choice vector bin packing, and propose several joint task-containerization-and-container-placement methods to reduce communication overhead and balance multi-type computing resource utilization. The performance superiority of the proposed algorithms is demonstrated by comparison with the state-of-the-art task and container scheduling schemes.

cs.DC↗

arXiv2023

FedCliP: Federated Learning with Client Pruning

The prevalent communication efficient federated learning (FL) frameworks usually take advantages of model gradient compression or model distillation. However, the unbalanced local data distributions (either in quantity or quality) of participating clients, contributing non-equivalently to the global model training, still pose a big challenge to these works. In this paper, we propose FedCliP, a novel communication efficient FL framework that allows faster model training, by adaptively learning which clients should remain active for further model training and pruning those who should be inactive with less potential contributions. We also introduce an alternative optimization method with a newly defined contribution score measure to facilitate active and inactive client determination. We empirically evaluate the communication efficiency of FL frameworks with extensive experiments on three benchmark datasets under both IID and non-IID settings. Numerical results demonstrate the outperformance of the porposed FedCliP framework over state-of-the-art FL frameworks, i.e., FedCliP can save 70% of communication overhead with only 0.2% accuracy loss on MNIST datasets, and save 50% and 15% of communication overheads with less than 1% accuracy loss on FMNIST and CIFAR-10 datasets, respectively.

cs.LG↗

arXiv2022

THMA: Tencent HD Map AI System for Creating HD Map Annotations

Nowadays, autonomous vehicle technology is becoming more and more mature. Critical to progress and safety, high-definition (HD) maps, a type of centimeter-level map collected using a laser sensor, provide accurate descriptions of the surrounding environment. The key challenge of HD map production is efficient, high-quality collection and annotation of large-volume datasets. Due to the demand for high quality, HD map production requires significant manual human effort to create annotations, a very time-consuming and costly process for the map industry. In order to reduce manual annotation burdens, many artificial intelligence (AI) algorithms have been developed to pre-label the HD maps. However, there still exists a large gap between AI algorithms and the traditional manual HD map production pipelines in accuracy and robustness. Furthermore, it is also very resource-costly to build large-scale annotated datasets and advanced machine learning algorithms for AI-based HD map automatic labeling systems. In this paper, we introduce the Tencent HD Map AI (THMA) system, an innovative end-to-end, AI-based, active learning HD map labeling system capable of producing and labeling HD maps with a scale of hundreds of thousands of kilometers. In THMA, we train AI models directly from massive HD map datasets via supervised, self-supervised, and weakly supervised learning to achieve high accuracy and efficiency required by downstream users. THMA has been deployed by the Tencent Map team to provide services to downstream companies and users, serving over 1,000 labeling workers and producing more than 30,000 kilometers of HD map data per day at most. More than 90 percent of the HD map data in Tencent Map is labeled automatically by THMA, accelerating the traditional HD map labeling process by more than ten times.

cs.CV↗

arXiv2022

PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation

Logical table-to-text generation is a task that involves generating logically faithful sentences from tables, which requires models to derive logical level facts from table records via logical inference. It raises a new challenge on the logical-level content planning of table-to-text models. However, directly learning the logical inference knowledge from table-text pairs is very difficult for neural models because of the ambiguity of natural language and the scarcity of parallel data. Hence even large-scale pre-trained language models present low logical fidelity on logical table-to-text. In this work, we propose a PLOG (Pretrained Logical Form Generator) framework to improve the generation fidelity. Specifically, PLOG is first pretrained on a table-to-logic-form generation (table-to-logic) task, then finetuned on downstream table-to-text tasks. The formal definition of logical forms enables us to collect large amount of accurate logical forms from tables without human annotation. In addition, PLOG can learn logical inference from table-logic pairs much more definitely than from table-text pairs. To evaluate our model, we further collect a controlled logical table-to-text dataset CONTLOG based on an existing dataset. On two benchmarks, LOGICNLG and CONTLOG, PLOG outperforms strong baselines by a large margin on the logical fidelity, demonstrating the effectiveness of table-to-logic pretraining.

cs.CL↗

arXiv2022

Differentially Private Condorcet Voting

Designing private voting rules is an important and pressing problem for trustworthy democracy. In this paper, under the framework of differential privacy, we propose a novel famliy of randomized voting rules based on the well-known Condorcet method, and focus on three classes of voting rules in this family: Laplacian Condorcet method ($\CMLAP_λ$), exponential Condorcet method ($\CMEXP_λ$), and randomized response Condorcet method ($\CMRR_λ$), where $λ$ represents the level of noise. We prove that all of our rules satisfy absolute monotonicity, lexi-participation, probabilistic Pareto efficiency, approximate probabilistic Condorcet criterion, and approximate SD-strategyproofness. In addition, $\CMRR_λ$ satisfies (non-approximate) probabilistic Condorcet criterion, while $\CMLAP_λ$ and $\CMEXP_λ$ satisfy strong lexi-participation. Finally, we regard differential privacy as a voting axiom, and discuss its relations to other axioms.

cs.GT↗

arXiv2022

Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction

Target-oriented Opinion Words Extraction (TOWE) is a fine-grained sentiment analysis task that aims to extract the corresponding opinion words of a given opinion target from the sentence. Recently, deep learning approaches have made remarkable progress on this task. Nevertheless, the TOWE task still suffers from the scarcity of training data due to the expensive data annotation process. Limited labeled data increase the risk of distribution shift between test data and training data. In this paper, we propose exploiting massive unlabeled data to reduce the risk by increasing the exposure of the model to varying distribution shifts. Specifically, we propose a novel Multi-Grained Consistency Regularization (MGCR) method to make use of unlabeled data and design two filters specifically for TOWE to filter noisy data at different granularity. Extensive experimental results on four TOWE benchmark datasets indicate the superiority of MGCR compared with current state-of-the-art methods. The in-depth analysis also demonstrates the effectiveness of the different-granularity filters. Our codes are available at https://github.com/TOWESSL/TOWESSL.

cs.CL↗

arXiv2022

A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks

Tensorial Convolutional Neural Networks (TCNNs) have attracted much research attention for their power in reducing model parameters or enhancing the generalization ability. However, exploration of TCNNs is hindered even from weight initialization methods. To be specific, general initialization methods, such as Xavier or Kaiming initialization, usually fail to generate appropriate weights for TCNNs. Meanwhile, although there are ad-hoc approaches for specific architectures (e.g., Tensor Ring Nets), they are not applicable to TCNNs with other tensor decomposition methods (e.g., CP or Tucker decomposition). To address this problem, we propose a universal weight initialization paradigm, which generalizes Xavier and Kaiming methods and can be widely applicable to arbitrary TCNNs. Specifically, we first present the Reproducing Transformation to convert the backward process in TCNNs to an equivalent convolution process. Then, based on the convolution operators in the forward and backward processes, we build a unified paradigm to control the variance of features and gradients in TCNNs. Thus, we can derive fan-in and fan-out initialization for various TCNNs. We demonstrate that our paradigm can stabilize the training of TCNNs, leading to faster convergence and better results.

cs.LG↗

arXiv2022

Safe, efficient and socially-compatible decision of automated vehicles: a case study of unsignalized intersection driving

Safe and smooth interacting with other vehicles is one of the ultimate goals of driving automation. However, recent reports of demonstrative deployments of automated vehicles (AVs) indicate that AVs are still difficult to meet the expectation of other interacting drivers, which leads to several AV accidents involving human-driven vehicles (HVs). This is most likely due to the lack of understanding about the dynamic interaction process, especially about the human drivers. By investigating the causes of 4,300 video clips of traffic accidents, we find that the limited dynamic visual field of drivers is one leading factor in inter-vehicle interaction accidents, especially in those involving trucks. A game-theoretic decision algorithm considering social compatibility is proposed to handle the interaction with a human-driven truck at an unsignalized intersection. Starting from a probabilistic model for the visual field characteristics of truck drivers, social fitness and reciprocal altruism in the decision are incorporated in the game payoff design. Human-in-the-loop experiments are carried out, in which 24 subjects are invited to drive and interact with AVs deployed with the proposed algorithm and two comparison algorithms. Totally 207 cases of intersection interactions are obtained and analyzed, which shows that the proposed decision-making algorithm can not only improve both safety and time efficiency, but also make AV decisions more in line with the expectation of interacting human drivers. These findings can help inform the design of automated driving decision algorithms, to ensure that AVs can be safely and efficiently integrated into the human-dominated traffic.

eess.SY↗

arXiv2022

Learning Mixtures of Random Utility Models with Features from Incomplete Preferences

Random Utility Models (RUMs), which subsume Plackett-Luce model (PL) as a special case, are among the most popular models for preference learning. In this paper, we consider RUMs with features and their mixtures, where each alternative has a vector of features, possibly different across agents. Such models significantly generalize the standard PL and RUMs, but are not as well investigated in the literature. We extend mixtures of RUMs with features to models that generate incomplete preferences and characterize their identifiability. For PL, we prove that when PL with features is identifiable, its MLE is consistent with a strictly concave objective function under mild assumptions, by characterizing a bound on root-mean-square-error (RMSE), which naturally leads to a sample complexity bound. We also characterize identifiability of more general RUMs with features and propose a generalized RBCML to learn them. Our experiments on synthetic data demonstrate the effectiveness of MLE on PL with features with tradeoffs between statistical efficiency and computational efficiency. Our experiments on real-world data show the prediction power of PL with features and its mixtures.

cs.LG↗

arXiv2022

Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks

Since a vast number of tables can be easily collected from web pages, spreadsheets, PDFs, and various other document types, a flurry of table pre-training frameworks have been proposed following the success of text and images, and they have achieved new state-of-the-arts on various tasks such as table question answering, table type recognition, column relation classification, table search, formula prediction, etc. To fully use the supervision signals in unlabeled tables, a variety of pre-training objectives have been designed and evaluated, for example, denoising cell values, predicting numerical relationships, and implicitly executing SQLs. And to best leverage the characteristics of (semi-)structured tables, various tabular language models, particularly with specially-designed attention mechanisms, have been explored. Since tables usually appear and interact with free-form text, table pre-training usually takes the form of table-text joint pre-training, which attracts significant research interests from multiple domains. This survey aims to provide a comprehensive review of different model designs, pre-training objectives, and downstream tasks for table pre-training, and we further share our thoughts and vision on existing challenges and future opportunities.

cs.CL↗

arXiv2022

Semi-Supervised Formality Style Transfer with Consistency Training

Formality style transfer (FST) is a task that involves paraphrasing an informal sentence into a formal one without altering its meaning. To address the data-scarcity problem of existing parallel datasets, previous studies tend to adopt a cycle-reconstruction scheme to utilize additional unlabeled data, where the FST model mainly benefits from target-side unlabeled sentences. In this work, we propose a simple yet effective semi-supervised framework to better utilize source-side unlabeled sentences based on consistency training. Specifically, our approach augments pseudo-parallel data obtained from a source-side informal sentence by enforcing the model to generate similar outputs for its perturbed version. Moreover, we empirically examined the effects of various data perturbation methods and propose effective data filtering strategies to improve our framework. Experimental results on the GYAFC benchmark demonstrate that our approach can achieve state-of-the-art results, even with less than 40% of the parallel data.

cs.CL↗

arXiv2022

Deterministic relation between optical polarization and lattice symmetry revealed in ion-doped single microcrystals

Rare-earth ions doped crystals are of great significance for micro-sensing and quantum information, whilst the ions in the crystals emit light with spontaneous partial polarization, which is, though believed to be originated from the crystal lattice structure, still lacking a deterministic explanation that can be tested with quantitative accuracy. We report the experimental evidence showing the profound physical relation between the polarization degree of light emitted by the doped ion and the lattice symmetry, by demonstrating, with unprecedented precision, that the lattice constant ratio c/a directly quantifies the macroscopic effective polar angle of the electric and magnetic dipoles, which essentially determines the linear polarization degree of the emission. Based on this discovery, we further propose a pure optical technology to identify the three-dimensional orientation of a rod-shaped single microcrystal using the polarization-resolved micro-spectroscopy. Our results, revealing the physical origin of light polarization in ion-doped crystals, open the way towards on-demand polarization control with crystallography, and provide a versatile platform for polarization-based microscale sensing in dynamical systems.

physics.optics↗

arXiv2022

Towards Effective Multi-Task Interaction for Entity-Relation Extraction: A Unified Framework with Selection Recurrent Network

Entity-relation extraction aims to jointly solve named entity recognition (NER) and relation extraction (RE). Recent approaches use either one-way sequential information propagation in a pipeline manner or two-way implicit interaction with a shared encoder. However, they still suffer from poor information interaction due to the gap between the different task forms of NER and RE, raising a controversial question whether RE is really beneficial to NER. Motivated by this, we propose a novel and unified cascade framework that combines the advantages of both sequential information propagation and implicit interaction. Meanwhile, it eliminates the gap between the two tasks by reformulating entity-relation extraction as unified span-extraction tasks. Specifically, we propose a selection recurrent network as a shared encoder to encode task-specific independent and shared representations and design two sequential information propagation strategies to realize the sequential information flow between NER and RE. Extensive experiments demonstrate that our approaches can achieve state-of-the-art results on two common benchmarks, ACE05 and SciERC, and effectively model the multi-task interaction, which realizes significant mutual benefits of NER and RE.

cs.CL↗

arXiv2021

Personalized Lane Change Decision Algorithm Using Deep Reinforcement Learning Approach

To develop driving automation technologies for human, a human-centered methodology should be adopted for ensured safety and satisfactory user experience. Automated lane change decision in dense highway traffic is challenging, especially when considering the personalized preferences of different drivers. To fulfill human driver centered decision algorithm development, we carry out driver-in-the-loop experiments on a 6-Degree-of-Freedom driving simulator. Based on the analysis of the lane change data by drivers of three specific styles,personalization indicators are selected to describe the driver preferences in lane change decision. Then a deep reinforcement learning (RL) approach is applied to design human-like agents for automated lane change decision, with refined reward and loss functions to capture the driver preferences.The trained RL agents and benchmark agents are tested in a two-lane highway driving scenario, and by comparing the agents with the specific drivers at the same initial states of lane change, the statistics show that the proposed algorithm can guarantee higher consistency of lane change decision preferences. The driver personalization indicators and the proposed RL-based lane change decision algorithm are promising to contribute in automated lane change system developing.

cs.RO↗

arXiv2021

Improving Logical-Level Natural Language Generation with Topic-Conditioned Data Augmentation and Logical Form Generation

Logical Natural Language Generation, i.e., generating textual descriptions that can be logically entailed by a structured table, has been a challenge due to the low fidelity of the generation. \citet{chen2020logic2text} have addressed this problem by annotating interim logical programs to control the generation contents and semantics, and presented the task of table-aware logical form to text (Logic2text) generation. However, although table instances are abundant in the real world, logical forms paired with textual descriptions require costly human annotation work, which limits the performance of neural models. To mitigate this, we propose topic-conditioned data augmentation (TopicDA), which utilizes GPT-2 to generate unpaired logical forms and textual descriptions directly from tables. We further introduce logical form generation (LG), a dual task of Logic2text that requires generating a valid logical form based on a text description of a table. We also propose a semi-supervised learning approach to jointly train a Logic2text and an LG model with both labeled and augmented data. The two models benefit from each other by providing extra supervision signals through back-translation. Experimental results on the Logic2text dataset and the LG task demonstrate that our approach can effectively utilize the augmented data and outperform supervised baselines by a substantial margin.

cs.CL↗

arXiv2021

Personalized Highway Pilot Assist Considering Leading Vehicle's Lateral Behaviours

Highway pilot assist has become the front line of competition in advanced driver assistance systems. The increasing requirements on safety and user acceptance are calling for personalization in the development process of such systems. Inspired by a finding on drivers' car-following preferences on lateral direction, a personalized highway pilot assist algorithm is proposed, which consists of an Intelligent Driver Model (IDM) based speed control model and a novel lane-keeping model considering the leading vehicle's lateral movement. A simulated driving experiment is conducted to analyse driver gaze and lane-keeping Behaviours in free-driving and following driving scenario. Drivers are clustered into two driving style groups referring to their driving Behaviours affected by the leading vehicle, and then the personalization parameters for every specific subject driver are optimized. The proposed algorithm is validated through driver-in-the-loop experiment based on a moving-base simulator. Results show that, compared with the un-personalized algorithms, the personalized highway pilot algorithm can significantly reduce the mental workload and improve user acceptance of the assist functions.

eess.SY↗