arXiv subjects

Xian Wu

Publications and source records attributed to Xian Wu.

At least 181 records · Page 10Linked to original sources

arXiv2021

BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning

Recent research has confirmed the feasibility of backdoor attacks in deep reinforcement learning (RL) systems. However, the existing attacks require the ability to arbitrarily modify an agent's observation, constraining the application scope to simple RL systems such as Atari games. In this paper, we migrate backdoor attacks to more complex RL systems involving multiple agents and explore the possibility of triggering the backdoor without directly manipulating the agent's observation. As a proof of concept, we demonstrate that an adversary agent can trigger the backdoor of the victim agent with its own action in two-player competitive RL systems. We prototype and evaluate BACKDOORL in four competitive environments. The results show that when the backdoor is activated, the winning rate of the victim drops by 17% to 37% compared to when not activated.

cs.CR↗

arXiv2021

Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation

Medical report generation, which aims to automatically generate a long and coherent report of a given medical image, has been receiving growing research interests. Existing approaches mainly adopt a supervised manner and heavily rely on coupled image-report pairs. However, in the medical domain, building a large-scale image-report paired dataset is both time-consuming and expensive. To relax the dependency on paired data, we propose an unsupervised model Knowledge Graph Auto-Encoder (KGAE) which accepts independent sets of images and reports in training. KGAE consists of a pre-constructed knowledge graph, a knowledge-driven encoder and a knowledge-driven decoder. The knowledge graph works as the shared latent space to bridge the visual and textual domains; The knowledge-driven encoder projects medical images and reports to the corresponding coordinates in this latent space and the knowledge-driven decoder generates a medical report given a coordinate in this space. Since the knowledge-driven encoder and decoder can be trained with independent sets of images and reports, KGAE is unsupervised. The experiments show that the unsupervised KGAE generates desirable medical reports without using any image-report training pairs. Moreover, KGAE can also work in both semi-supervised and supervised settings, and accept paired images and reports in training. By further fine-tuning with image-report pairs, KGAE consistently outperforms the current state-of-the-art models on two datasets.

cs.LG↗

arXiv2021

Towards Joint Intent Detection and Slot Filling via Higher-order Attention

Intent detection (ID) and Slot filling (SF) are two major tasks in spoken language understanding (SLU). Recently, attention mechanism has been shown to be effective in jointly optimizing these two tasks in an interactive manner. However, latest attention-based works concentrated only on the first-order attention design, while ignoring the exploration of higher-order attention mechanisms. In this paper, we propose a BiLinear attention block, which leverages bilinear pooling to simultaneously exploit both the contextual and channel-wise bilinear attention distributions to capture the second-order interactions between the input intent or slot features. Higher and even infinity order interactions are built by stacking numerous blocks and assigning Exponential Linear Unit (ELU) to blocks. Before the decoding stage, we introduce the Dynamic Feature Fusion Layer to implicitly fuse intent and slot information in a more effective way. Technically, instead of simply concatenating intent and slot features, we first compute two correlation matrices to weight on two features. Furthermore, we present Higher-order Attention Network for the SLU tasks. Experiments on two benchmark datasets show that our approach yields improvements compared with the state-of-the-art approach. We also provide discussion to demonstrate the effectiveness of the proposed approach.

cs.CL↗

arXiv2021

Audio-Oriented Multimodal Machine Comprehension: Task, Dataset and Model

While Machine Comprehension (MC) has attracted extensive research interests in recent years, existing approaches mainly belong to the category of Machine Reading Comprehension task which mines textual inputs (paragraphs and questions) to predict the answers (choices or text spans). However, there are a lot of MC tasks that accept audio input in addition to the textual input, e.g. English listening comprehension test. In this paper, we target the problem of Audio-Oriented Multimodal Machine Comprehension, and its goal is to answer questions based on the given audio and textual information. To solve this problem, we propose a Dynamic Inter- and Intra-modality Attention (DIIA) model to effectively fuse the two modalities (audio and textual). DIIA can work as an independent component and thus be easily integrated into existing MC models. Moreover, we further develop a Multimodal Knowledge Distillation (MKD) module to enable our multimodal MC model to accurately predict the answers based only on either the text or the audio. As a result, the proposed approach can handle various tasks including: Audio-Oriented Multimodal Machine Comprehension, Machine Reading Comprehension and Machine Listening Comprehension, in a single model, making fair comparisons possible between our model and the existing unimodal MC models. Experimental results and analysis prove the effectiveness of the proposed approaches. First, the proposed DIIA boosts the baseline models by up to 21.08% in terms of accuracy; Second, under the unimodal scenarios, the MKD module allows our multimodal MC model to significantly outperform the unimodal models by up to 18.87%, which are trained and tested with only audio or textual data.

cs.CL↗

arXiv2021

Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation

Automatically generating radiology reports can improve current clinical practice in diagnostic radiology. On one hand, it can relieve radiologists from the heavy burden of report writing; On the other hand, it can remind radiologists of abnormalities and avoid the misdiagnosis and missed diagnosis. Yet, this task remains a challenging job for data-driven neural networks, due to the serious visual and textual data biases. To this end, we propose a Posterior-and-Prior Knowledge Exploring-and-Distilling approach (PPKED) to imitate the working patterns of radiologists, who will first examine the abnormal regions and assign the disease topic tags to the abnormal regions, and then rely on the years of prior medical knowledge and prior working experience accumulations to write reports. Thus, the PPKED includes three modules: Posterior Knowledge Explorer (PoKE), Prior Knowledge Explorer (PrKE) and Multi-domain Knowledge Distiller (MKD). In detail, PoKE explores the posterior knowledge, which provides explicit abnormal visual regions to alleviate visual data bias; PrKE explores the prior knowledge from the prior medical knowledge graph (medical knowledge) and prior radiology reports (working experience) to alleviate textual data bias. The explored knowledge is distilled by the MKD to generate the final reports. Evaluated on MIMIC-CXR and IU-Xray datasets, our method is able to outperform previous state-of-the-art models on these two datasets.

cs.CV↗

arXiv2021

A universal quantum gate set for transmon qubits with strong ZZ interactions

High-fidelity single- and two-qubit gates are essential building blocks for a fault-tolerant quantum computer. While there has been much progress in suppressing single-qubit gate errors in superconducting qubit systems, two-qubit gates still suffer from error rates that are orders of magnitude higher. One limiting factor is the residual ZZ-interaction, which originates from a coupling between computational states and higher-energy states. While this interaction is usually viewed as a nuisance, here we experimentally demonstrate that it can be exploited to produce a universal set of fast single- and two-qubit entangling gates in a coupled transmon qubit system. To implement arbitrary single-qubit rotations, we design a new protocol called the two-axis gate that is based on a three-part composite pulse. It rotates a single qubit independently of the state of the other qubit despite the strong ZZ-coupling. We achieve single-qubit gate fidelities as high as 99.1% from randomized benchmarking measurements. We then demonstrate both a CZ gate and a CNOT gate. Because the system has a strong ZZ-interaction, a CZ gate can be achieved by letting the system freely evolve for a gate time $t_g=53.8$ ns. To design the CNOT gate, we utilize an analytical microwave pulse shape based on the SWIPHT protocol for realizing fast, low-leakage gates. We obtain fidelities of 94.6% and 97.8% for the CNOT and CZ gates respectively from quantum progress tomography.

quant-ph↗

arXiv2021

Simulating nonnative cubic interactions on noisy quantum machines

As a milestone for general-purpose computing machines, we demonstrate that quantum processors can be programmed to efficiently simulate dynamics that are not native to the hardware. Moreover, on noisy devices without error correction, we show that simulation results are significantly improved when the quantum program is compiled using modular gates instead of a restricted set of standard gates. We demonstrate the general methodology by solving a cubic interaction problem, which appears in nonlinear optics, gauge theories, as well as plasma and fluid dynamics. To encode the nonnative Hamiltonian evolution, we decompose the Hilbert space into a direct sum of invariant subspaces in which the nonlinear problem is mapped to a finite-dimensional Hamiltonian simulation problem. In a three-states example, the resultant unitary evolution is realized by a product of ~20 standard gates, using which ~10 simulation steps can be carried out on state-of-the-art quantum hardware before results are corrupted by decoherence. In comparison, the simulation depth is improved by more than an order of magnitude when the unitary evolution is realized as a single cubic gate, which is compiled directly using optimal control. Alternatively, parametric gates may also be compiled by interpolating control pulses. Modular gates thus obtained provide high-fidelity building blocks for quantum Hamiltonian simulations.

quant-ph↗

arXiv2021

Relation-aware Meta-learning for Market Segment Demand Prediction with Limited Records

E-commerce business is revolutionizing our shopping experiences by providing convenient and straightforward services. One of the most fundamental problems is how to balance the demand and supply in market segments to build an efficient platform. While conventional machine learning models have achieved great success on data-sufficient segments, it may fail in a large-portion of segments in E-commerce platforms, where there are not sufficient records to learn well-trained models. In this paper, we tackle this problem in the context of market segment demand prediction. The goal is to facilitate the learning process in the target segments by leveraging the learned knowledge from data-sufficient source segments. Specifically, we propose a novel algorithm, RMLDP, to incorporate a multi-pattern fusion network (MPFN) with a meta-learning paradigm. The multi-pattern fusion network considers both local and seasonal temporal patterns for segment demand prediction. In the meta-learning paradigm, transferable knowledge is regarded as the model parameter initialization of MPFN, which are learned from diverse source segments. Furthermore, we capture the segment relations by combining data-driven segment representation and segment knowledge graph representation and tailor the segment-specific relations to customize transferable model parameter initialization. Thus, even with limited data, the target segment can quickly find the most relevant transferred knowledge and adapt to the optimal parameters. We conduct extensive experiments on two large-scale industrial datasets. The results justify that our RMLDP outperforms a set of state-of-the-art baselines. Besides, RMLDP has been deployed in Taobao, a real-world E-commerce platform. The online A/B testing results further demonstrate the practicality of RMLDP.

cs.LG↗

arXiv2020

Variance Reduced Value Iteration and Faster Algorithms for Solving Markov Decision Processes

In this paper we provide faster algorithms for approximately solving discounted Markov Decision Processes in multiple parameter regimes. Given a discounted Markov Decision Process (DMDP) with $|S|$ states, $|A|$ actions, discount factor $γ\in(0,1)$, and rewards in the range $[-M, M]$, we show how to compute an $ε$-optimal policy, with probability $1 - δ$ in time \[ \tilde{O}\left( \left(|S|^2 |A| + \frac{|S| |A|}{(1 - γ)^3} \right) \log\left( \frac{M}ε \right) \log\left( \frac{1}δ \right) \right) ~ . \] This contribution reflects the first nearly linear time, nearly linearly convergent algorithm for solving DMDPs for intermediate values of $γ$. We also show how to obtain improved sublinear time algorithms provided we can sample from the transition function in $O(1)$ time. Under this assumption we provide an algorithm which computes an $ε$-optimal policy with probability $1 - δ$ in time \[ \tilde{O} \left(\frac{|S| |A| M^2}{(1 - γ)^4 ε^2} \log \left(\frac{1}δ\right) \right) ~. \] Lastly, we extend both these algorithms to solve finite horizon MDPs. Our algorithms improve upon the previous best for approximately computing optimal policies for fixed-horizon MDPs in multiple parameter regimes. Interestingly, we obtain our results by a careful modification of approximate value iteration. We show how to combine classic approximate value iteration analysis with new techniques in variance reduction. Our fastest algorithms leverage further insights to ensure that our algorithms make monotonic progress towards the optimal value. This paper is one of few instances in using sampling to obtain a linearly convergent linear programming algorithm and we hope that the analysis may be useful more broadly.

cs.DS↗

arXiv2020

Wireless power transfer via topological modes in dimer chains

The topological characteristics, including invariant topological orders, band inversion, and the topological edge mode (TEM) in the photonic insulators, have been widely studied. Whether people can take advantage of intriguing topological modes in simple one-dimensional systems to implement some practical applications is an issue which people are increasingly concerned about. In this work, based on a photonic dimer chain composed of ultra-subwavelength resonators, we verify experimentally that the TEM in the effective second-order parity-time (PT) system is immune to the inner disorder perturbation, and can be used to realize the long-range wireless power transfer (WPT) with high transmission efficiency. To intuitively show the TEM can be used for WPT, a power signal source is used to excite the TEM. It can be clearly seen that two LED lamps with 0.5-W at both ends of the structure are lighted up with the aid of TEMs. In addition, in order to solve the special technical problems of standby power loss and frequency tracking, we further propose that a WPT system with effective third-order PT symmetry can be constructed by using one topological interface mode and two TEMs. Inspired by the long-range WPT with TEMs in this work, it is expected to use more complex topological structures to achieve energy transmission with more functions, such as the WPT devices whose direction can be selected flexibly in the quasiperiodic or trimer topological chains.

physics.app-ph↗

arXiv2020

Significant enhancement of magnetic shielding effect by using the composite metamaterial composed of mu-near-zero media and ferrite

The magnetic shield plays an important role in magnetic near-field control. However, the requirements of efficient, ultrathin, lightweight and cheap are still the challenges. Here, we firstly propose a composite metamaterial in which the mu-near-zero media is covered with a ferrite slab. We verify that this structure can enhance the shielding effectiveness in a small area. Furthermore, we optimize the magnetic path by changing the bulk ferrite slab into a patterned slab. In this way, significant shielding effectiveness enhancement can be achieved in a large area. Experimental results show that the maximum shielding effectiveness (SE) of the composite metamaterial with a patterned ferrite is 20.56 dB, which is nearly 19 dB higher than that of a single ferrite slab with the same thickness of the composite metamaterial. The results on the composite metamaterial would be very useful in the applications involving magnetic shielding.

physics.app-ph↗

arXiv2020

Automatic Distractor Generation for Multiple Choice Questions in Standard Tests

To assess the knowledge proficiency of a learner, multiple choice question is an efficient and widespread form in standard tests. However, the composition of the multiple choice question, especially the construction of distractors is quite challenging. The distractors are required to both incorrect and plausible enough to confuse the learners who did not master the knowledge. Currently, the distractors are generated by domain experts which are both expensive and time-consuming. This urges the emergence of automatic distractor generation, which can benefit various standard tests in a wide range of domains. In this paper, we propose a question and answer guided distractor generation (EDGE) framework to automate distractor generation. EDGE consists of three major modules: (1) the Reforming Question Module and the Reforming Passage Module apply gate layers to guarantee the inherent incorrectness of the generated distractors; (2) the Distractor Generator Module applies attention mechanism to control the level of plausibility. Experimental results on a large-scale public dataset demonstrate that our model significantly outperforms existing models and achieves a new state-of-the-art.

cs.CL↗

arXiv2020

Nonlinear Signal Distortion Corrections Through Quantum Sensing

Having accurate gate generation is essential for precise control of a quantum system. The generated gate usually suffers from linear and nonlinear distortion. Previous works have demonstrated how to use a qubit to correct linear frequency distortions but have not commented on how to handle nonlinear distortions. This is an important issue as we show that nonlinear amplitude distortions from the RF electronics can affect Rabi pulses by as much as 10%. We present work that demonstrates how a transmon qubit can be used as a highly sensitive cryogenic detector to characterize these nonlinear amplitude distortions. We show that a correction can drive these errors down to <1% over a 700 MHz range. This correction technique provides a method to minimize the effects of signal distortions and can be easily applied to broadband control pulses to produce higher fidelity arbitrary quantum gates.

quant-ph↗

arXiv2020

High-fidelity software-defined quantum logic on a superconducting qudit

Nearly all modern solid-state quantum processors approach quantum computation with a set of discrete qubit operations (gates) that can achieve universal quantum control with only a handful of primitive gates. In principle, this approach is highly flexible, allowing full control over the qubits' Hilbert space without necessitating the development of specific control protocols for each application. However, current error rates on quantum hardware place harsh limits on the number of primitive gates that can be concatenated together (with compounding error rates) and remain viable. Here, we report our efforts at implementing a software-defined $0\leftrightarrow2$ SWAP gate that does not rely on a primitive gate set and achieves an average gate fidelity of $99.4\%$. Our work represents an alternative, fully generalizable route towards achieving nontrivial quantum control through the use of optimal control techniques. We describe our procedure for computing optimal control solutions, calibrating the quantum and classical hardware chain, and characterizing the fidelity of the optimal control gate.

quant-ph↗

arXiv2020

Nearest Neighbor Search for Hyperbolic Embeddings

Embedding into hyperbolic space is emerging as an effective representation technique for datasets that exhibit hierarchical structure. This development motivates the need for algorithms that are able to effectively extract knowledge and insights from datapoints embedded in negatively curved spaces. We focus on the problem of nearest neighbor search, a fundamental problem in data analysis. We present efficient algorithmic solutions that build upon established methods for nearest neighbor search in Euclidean space, allowing for easy adoption and integration with existing systems. We prove theoretical guarantees for our techniques and our experiments demonstrate the effectiveness of our approach on real datasets over competing algorithms.

cs.DS↗

arXiv2020

Least Squares Regression with Markovian Data: Fundamental Limits and Algorithms

We study the problem of least squares linear regression where the data-points are dependent and are sampled from a Markov chain. We establish sharp information theoretic minimax lower bounds for this problem in terms of $τ_{\mathsf{mix}}$, the mixing time of the underlying Markov chain, under different noise settings. Our results establish that in general, optimization with Markovian data is strictly harder than optimization with independent data and a trivial algorithm (SGD-DD) that works with only one in every $\tildeΘ(τ_{\mathsf{mix}})$ samples, which are approximately independent, is minimax optimal. In fact, it is strictly better than the popular Stochastic Gradient Descent (SGD) method with constant step-size which is otherwise minimax optimal in the regression with independent data setting. Beyond a worst case analysis, we investigate whether structured datasets seen in practice such as Gaussian auto-regressive dynamics can admit more efficient optimization schemes. Surprisingly, even in this specific and natural setting, Stochastic Gradient Descent (SGD) with constant step-size is still no better than SGD-DD. Instead, we propose an algorithm based on experience replay--a popular reinforcement learning technique--that achieves a significantly better error rate. Our improved rate serves as one of the first results where an algorithm outperforms SGD-DD on an interesting Markov chain and also provides one of the first theoretical analyses to support the use of experience replay in practice.

cs.LG↗

arXiv2020

Jointly Predicting Job Performance, Personality, Cognitive Ability, Affect, and Well-Being

Assessment of job performance, personalized health and psychometric measures are domains where data-driven and ubiquitous computing exhibits the potential of a profound impact in the future. Existing techniques use data extracted from questionnaires, sensors (wearable, computer, etc.), or other traits, to assess well-being and cognitive attributes of individuals. However, these techniques can neither predict individual's well-being and psychological traits in a global manner nor consider the challenges associated to processing the data available, that is incomplete and noisy. In this paper, we create a benchmark for predictive analysis of individuals from a perspective that integrates: physical and physiological behavior, psychological states and traits, and job performance. We design data mining techniques as benchmark and uses real noisy and incomplete data derived from wearable sensors to predict 19 constructs based on 12 standardized well-validated tests. The study included 757 participants who were knowledge workers in organizations across the USA with varied work roles. We developed a data mining framework to extract the meaningful predictors for each of the 19 variables under consideration. Our model is the first benchmark that combines these various instrument-derived variables in a single framework to understand people's behavior by leveraging real uncurated data from wearable, mobile, and social media sources. We verify our approach experimentally using the data obtained from our longitudinal study. The results show that our framework is consistently reliable and capable of predicting the variables under study better than the baselines when prediction is restricted to the noisy, incomplete data.

cs.CY↗

arXiv2020

Representation Learning on Variable Length and Incomplete Wearable-Sensory Time Series

The prevalence of wearable sensors (e.g., smart wristband) is creating unprecedented opportunities to not only inform health and wellness states of individuals, but also assess and infer personal attributes, including demographic and personality attributes. However, the data captured from wearables, such as heart rate or number of steps, present two key challenges: 1) the time series is often of variable-length and incomplete due to different data collection periods (e.g., wearing behavior varies by person); and 2) inter-individual variability to external factors like stress and environment. This paper addresses these challenges and brings us closer to the potential of personalized insights about an individual, taking the leap from quantified self to qualified self. Specifically, HeartSpace proposed in this paper encodes time series data with variable-length and missing values via the integration of a time series encoding module and a pattern aggregation network. Additionally, HeartSpace implements a Siamese-triplet network to optimize representations by jointly capturing intra- and inter-series correlations during the embedding learning process. The empirical evaluation over two different real-world data presents significant performance gains overstate-of-the-art baselines in a variety of applications, including personality prediction, demographics inference, and user identification.

eess.SP↗