arXiv subjects

Bo Chen

Publications and source records attributed to Bo Chen.

At least 343 records · Page 19Linked to original sources

arXiv2021

Privacy-Preserving Kickstarting Deep Reinforcement Learning with Privacy-Aware Learners

Kickstarting deep reinforcement learning algorithms facilitate a teacher-student relationship among the agents and allow for a well-performing teacher to share demonstrations with a student to expedite the student's training. However, despite the known benefits, the demonstrations may contain sensitive information about the teacher's training data and existing kickstarting methods do not take any measures to protect it. Therefore, we use the framework of differential privacy to develop a mechanism that securely shares the teacher's demonstrations with the student. The mechanism allows for the teacher to decide upon the accuracy of its demonstrations with respect to the privacy budget that it consumes, thereby granting the teacher full control over its data privacy. We then develop a kickstarted deep reinforcement learning algorithm for the student that is privacy-aware because we calibrate its objective with the parameters of the teacher's privacy mechanism. The privacy-aware design of the algorithm makes it possible to kickstart the student's learning despite the perturbations induced by the privacy mechanism. From numerical experiments, we highlight three empirical results: (i) the algorithm succeeds in expediting the student's learning, (ii) the student converges to a performance level that was not possible without the demonstrations, and (iii) the student maintains its enhanced performance even after the teacher stops sharing useful demonstrations due to its privacy budget constraints.

cs.LG↗

arXiv2021

An Embedding Learning Framework for Numerical Features in CTR Prediction

Click-Through Rate (CTR) prediction is critical for industrial recommender systems, where most deep CTR models follow an Embedding \& Feature Interaction paradigm. However, the majority of methods focus on designing network architectures to better capture feature interactions while the feature embedding, especially for numerical features, has been overlooked. Existing approaches for numerical features are difficult to capture informative knowledge because of the low capacity or hard discretization based on the offline expertise feature engineering. In this paper, we propose a novel embedding learning framework for numerical features in CTR prediction (AutoDis) with high model capacity, end-to-end training and unique representation properties preserved. AutoDis consists of three core components: meta-embeddings, automatic discretization and aggregation. Specifically, we propose meta-embeddings for each numerical field to learn global knowledge from the perspective of field with a manageable number of parameters. Then the differentiable automatic discretization performs soft discretization and captures the correlations between the numerical features and meta-embeddings. Finally, distinctive and informative embeddings are learned via an aggregation function. Comprehensive experiments on two public and one industrial datasets are conducted to validate the effectiveness of AutoDis. Moreover, AutoDis has been deployed onto a mainstream advertising platform, where online A/B test demonstrates the improvement over the base model by 2.1% and 2.7% in terms of CTR and eCPM, respectively. In addition, the code of our framework is publicly available in MindSpore(https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/recommend/autodis).

cs.IR↗

arXiv2021

The X Factor: A Robust and Powerful Approach to X-chromosome-Inclusive Whole-genome Association Studies

The X-chromosome is often excluded from genome-wide association studies because of analytical challenges. Some of the problems, such as the random, skewed or no X-inactivation model uncertainty, have been investigated. Other considerations have received little to no attention, such as the value in considering non-additive and gene-sex interaction effects, and the inferential consequence of choosing different baseline alleles (i.e.\ the reference vs.\ the alternative allele). Here we propose a unified and flexible regression-based association test for X-chromosomal variants. We provide theoretical justifications for its robustness in the presence of various model uncertainties, as well as for its improved power when compared with the existing approaches under certain scenarios. For completeness, we also revisit the autosomes and show that the proposed framework leads to a more robust approach than the standard method. Finally, we provide supporting evidence by revisiting several published association studies. Supplementary materials for this article are available online.

stat.AP↗

arXiv2021

Very regular solution to Landau-Lifshitz system with spin-polarized transport

In this paper, we provide a precise description of the compatibility conditions for the initial data so that one can show the existence and uniqueness of regular short-time solution to the Neumann initial-boundary problem of a class of Landau-Lifshitz-Gilbert system with spin-polarized transport, which is a strong nonlinear coupled parabolic system with non-local energy.

math.AP↗

arXiv2021

Wide-Beam Array Antenna Power Gain Maximization via ADMM Framework

This paper proposes two algorithms to maximize the minimum array power gain in a wide-beam mainlobe by solving the power gain pattern synthesis (PGPS) problem with and without sidelobe constraints. Firstly, the nonconvex PGPS problem is transformed into a nonconvex linear inequality optimization problem and then converted to an augmented Lagrangian problem by introducing auxiliary variables via the Alternating Direction Method of Multipliers (ADMM) framework. Next,the original intractable problem is converted into a series of nonconvex and convex subproblems. The nonconvex subproblems are solved by dividing their solution space into a finite set of smaller ones, in which the solution would be obtained pseudoanalytically. In such a way, the proposed algorithms are superior to the existing PGPS-based ones as their convergence can be theoretically guaranteed with a lower computational burden. Numerical examples with both isotropic element pattern (IEP) and active element pattern (AEP) arrays are simulated to show the effectiveness and superiority of the proposed algorithms by comparing with the related existing algorithms.

eess.SP↗

arXiv2021

Edge Differential Privacy for Algebraic Connectivity of Graphs

Graphs are the dominant formalism for modeling multi-agent systems. The algebraic connectivity of a graph is particularly important because it provides the convergence rates of consensus algorithms that underlie many multi-agent control and optimization techniques. However, sharing the value of algebraic connectivity can inadvertently reveal sensitive information about the topology of a graph, such as connections in social networks. Therefore, in this work we present a method to release a graph's algebraic connectivity under a graph-theoretic form of differential privacy, called edge differential privacy. Edge differential privacy obfuscates differences among graphs' edge sets and thus conceals the absence or presence of sensitive connections therein. We provide privacy with bounded Laplace noise, which improves accuracy relative to conventional unbounded noise. The private algebraic connectivity values are analytically shown to provide accurate estimates of consensus convergence rates, as well as accurate bounds on the diameter of a graph and the mean distance between its nodes. Simulation results confirm the utility of private algebraic connectivity in these contexts.

cs.CR↗

arXiv2021

MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

Inverted bottleneck layers, which are built upon depthwise convolutions, have been the predominant building blocks in state-of-the-art object detection models on mobile devices. In this work, we investigate the optimality of this design pattern over a broad range of mobile accelerators by revisiting the usefulness of regular convolutions. We discover that regular convolutions are a potent component to boost the latency-accuracy trade-off for object detection on accelerators, provided that they are placed strategically in the network via neural architecture search. By incorporating regular convolutions in the search space and directly optimizing the network architectures for object detection, we obtain a family of object detection models, MobileDets, that achieve state-of-the-art results across mobile accelerators. On the COCO object detection task, MobileDets outperform MobileNetV3+SSDLite by 1.7 mAP at comparable mobile CPU inference latencies. MobileDets also outperform MobileNetV2+SSDLite by 1.9 mAP on mobile CPUs, 3.7 mAP on Google EdgeTPU, 3.4 mAP on Qualcomm Hexagon DSP and 2.7 mAP on Nvidia Jetson GPU without increasing latency. Moreover, MobileDets are comparable with the state-of-the-art MnasFPN on mobile CPUs even without using the feature pyramid, and achieve better mAP scores on both EdgeTPUs and DSPs with up to 2x speedup. Code and models are available in the TensorFlow Object Detection API: https://github.com/tensorflow/models/tree/master/research/object_detection.

cs.CV↗

arXiv2021

Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs

Knowledge graph reasoning is the fundamental component to support machine learning applications such as information extraction, information retrieval, and recommendation. Since knowledge graphs can be viewed as the discrete symbolic representations of knowledge, reasoning on knowledge graphs can naturally leverage the symbolic techniques. However, symbolic reasoning is intolerant of the ambiguous and noisy data. On the contrary, the recent advances of deep learning promote neural reasoning on knowledge graphs, which is robust to the ambiguous and noisy data, but lacks interpretability compared to symbolic reasoning. Considering the advantages and disadvantages of both methodologies, recent efforts have been made on combining the two reasoning methods. In this survey, we take a thorough look at the development of the symbolic, neural and hybrid reasoning on knowledge graphs. We survey two specific reasoning tasks, knowledge graph completion and question answering on knowledge graphs, and explain them in a unified reasoning framework. We also briefly discuss the future directions for knowledge graph reasoning.

cs.AI↗

arXiv2021

Memory-Efficient Network for Large-scale Video Compressive Sensing

Video snapshot compressive imaging (SCI) captures a sequence of video frames in a single shot using a 2D detector. The underlying principle is that during one exposure time, different masks are imposed on the high-speed scene to form a compressed measurement. With the knowledge of masks, optimization algorithms or deep learning methods are employed to reconstruct the desired high-speed video frames from this snapshot measurement. Unfortunately, though these methods can achieve decent results, the long running time of optimization algorithms or huge training memory occupation of deep networks still preclude them in practical applications. In this paper, we develop a memory-efficient network for large-scale video SCI based on multi-group reversible 3D convolutional neural networks. In addition to the basic model for the grayscale SCI system, we take one step further to combine demosaicing and SCI reconstruction to directly recover color video from Bayer measurements. Extensive results on both simulation and real data captured by SCI cameras demonstrate that our proposed model outperforms previous state-of-the-art with less memory and thus can be used in large-scale problems. The code is at https://github.com/BoChenGroup/RevSCI-net.

eess.IV↗

arXiv2021

MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing

To capture high-speed videos using a two-dimensional detector, video snapshot compressive imaging (SCI) is a promising system, where the video frames are coded by different masks and then compressed to a snapshot measurement. Following this, efficient algorithms are desired to reconstruct the high-speed frames, where the state-of-the-art results are achieved by deep learning networks. However, these networks are usually trained for specific small-scale masks and often have high demands of training time and GPU memory, which are hence {\bf \em not flexible} to $i$) a new mask with the same size and $ii$) a larger-scale mask. We address these challenges by developing a Meta Modulated Convolutional Network for SCI reconstruction, dubbed MetaSCI. MetaSCI is composed of a shared backbone for different masks, and light-weight meta-modulation parameters to evolve to different modulation parameters for each mask, thus having the properties of {\bf \em fast adaptation} to new masks (or systems) and ready to {\bf \em scale to large data}. Extensive simulation and real data results demonstrate the superior performance of our proposed approach. Our code is available at {\small\url{https://github.com/xyvirtualgroup/MetaSCI-CVPR2021}}.

eess.IV↗

arXiv2021

Robust Trajectory-Constrained Frequency Control for Microgrids Considering Model Linearization Error

The capability to switch between grid-connected and islanded modes has promoted adoption of microgrid technology for powering remote locations. Stabilizing frequency during the islanding event, however, is a challenging control task, particularly under high penetration of converter-interfaced sources. In this paper, a numerical optimal control (NOC)-based control synthesis methodology is proposed for preparedness of microgrid islanding that ensure guaranteed performance. The key feature of the proposed paradigm is near real-time centralized scheduling for real-time decentralized executing. For tractable computation, linearized models are used in the problem formulation. To accommodate the linearization errors, interval analysis is employed to compute linearization-induced uncertainty as numerical intervals so that the NOC problem can be formulated into a robust mixed-integer linear program. The proposed control is verified on the full nonlinear model in Simulink. The simulation results shown effectiveness of the proposed control paradigm and the necessity of considering linearization-induced uncertainty.

eess.SY↗

arXiv2021

Experimental evidence on the dissipationless transport of chiral edge state of the high-field Chern insulator in MnBi2Te4 nanodevices

We demonstrate the dissipationless transport of the chiral edge state (CES) in the nanodevices of quantum anomalous Hall insulator candidate MnBi2Te4. The device presents a near-zero longitudinal resistance together with a quantized Hall plateau in excess of 0.97 h/e2 over a range of temperatures from very low up to the Neel temperature of 22 K. Each of four-probe nonlocal measurements gives near-zero resistance and two-probe measurements exhibit a plateau of +1 h/e2, while the results of three-probe nonlocal measurements depend on the magnetic field. This indicates non-dissipation as well as the chirality of the edge state. The CES shows three regimes of temperature dependence, i.e., well-preserved dissipationless transport below 6 K, variable range hopping while increasing the temperature and thermal activation at higher than 22 K. Even at the lowest temperature, a current of over 1.4 μA breaks the dissipationless transport. These form a complete set of evidences of the Chern insulator state in the MnBi2Te4 systems.

cond-mat.mes-hall↗

arXiv2021

Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation

A fundamental ability of humans is to utilize commonsense knowledge in language understanding and question answering. In recent years, many knowledge-enhanced Commonsense Question Answering (CQA) approaches have been proposed. However, it remains unclear: (1) How far can we get by exploiting external knowledge for CQA? (2) How much potential of knowledge has been exploited in current CQA models? (3) Which are the most promising directions for future CQA? To answer these questions, we benchmark knowledge-enhanced CQA by conducting extensive experiments on multiple standard CQA datasets using a simple and effective knowledge-to-text transformation framework. Experiments show that: (1) Our knowledge-to-text framework is effective and achieves state-of-the-art performance on CommonsenseQA dataset, providing a simple and strong knowledge-enhanced baseline for CQA; (2) The potential of knowledge is still far from being fully exploited in CQA -- there is a significant performance gap from current models to our models with golden knowledge; and (3) Context-sensitive knowledge selection, heterogeneous knowledge exploitation, and commonsense-rich language models are promising CQA directions.

cs.CL↗

arXiv2020

Simulations of stray light from the surface scattering of the Solar Corona Imager primary mirror

The Solar Corona Imager is an internally occulted coronagraph on board the ASO-S mission, which has the advantage of imaging the inner corona in H I {Lyman-\textalpha} (Ly-alpha) and white-light (WL) wavebands. However, scattering of solar disk light by the primary mirror (M1) becomes the main source of stray light. To study the methods of stray light suppression, three scattering models are used to model M1 scattering in Zemax OpticStudio. The ratio of coronal emission to predicted stray light decrease along field of view in both channels. The stray light in Ly-alpha channel is generally lower than coronal emission, but the stray light in WL channel tends to be one order of magnitude higher than coronal signal at 2.5 Rsun. Optimized parameter combinations that suppress the stray light to required level are obtained, which put some limitations on the M1 manufacture. Besides, K-correlation model is recommended to simulate surface scattering.

astro-ph.SR↗

arXiv2020

Bayesian Attention Modules

Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpretability. Most current models use deterministic attention modules due to their simplicity and ease of optimization. Stochastic counterparts, on the other hand, are less popular despite their potential benefits. The main reason is that stochastic attention often introduces optimization issues or requires significant model changes. In this paper, we propose a scalable stochastic version of attention that is easy to implement and optimize. We construct simplex-constrained attention distributions by normalizing reparameterizable distributions, making the training process differentiable. We learn their parameters in a Bayesian framework where a data-dependent prior is introduced for regularization. We apply the proposed stochastic attention modules to various attention-based models, with applications to graph node classification, visual question answering, image captioning, machine translation, and language understanding. Our experiments show the proposed method brings consistent improvements over the corresponding baselines.

stat.ML↗

arXiv2020

Variational Temporal Deep Generative Model for Radar HRRP Target Recognition

We develop a recurrent gamma belief network (rGBN) for radar automatic target recognition (RATR) based on high-resolution range profile (HRRP), which characterizes the temporal dependence across the range cells of HRRP. The proposed rGBN adopts a hierarchy of gamma distributions to build its temporal deep generative model. For scalable training and fast out-of-sample prediction, we propose the hybrid of a stochastic-gradient Markov chain Monte Carlo (MCMC) and a recurrent variational inference model to perform posterior inference. To utilize the label information to extract more discriminative latent representations, we further propose supervised rGBN to jointly model the HRRP samples and their corresponding labels. Experimental results on synthetic and measured HRRP data show that the proposed models are efficient in computation, have good classification accuracy and generalization ability, and provide highly interpretable multi-stochastic-layer latent structure.

stat.ML↗

arXiv2020

CONNA: Addressing Name Disambiguation on The Fly

Name disambiguation is a key and also a very tough problem in many online systems such as social search and academic search. Despite considerable research, a critical issue that has not been systematically studied is disambiguation on the fly -- to complete the disambiguation in the real-time. This is very challenging, as the disambiguation algorithm must be accurate, efficient, and error tolerance. In this paper, we propose a novel framework -- CONNA -- to train a matching component and a decision component jointly via reinforcement learning. The matching component is responsible for finding the top matched candidate for the given paper, and the decision component is responsible for deciding on assigning the top matched person or creating a new person. The two components are intertwined and can be bootstrapped via jointly training. Empirically, we evaluate CONNA on two name disambiguation datasets. Experimental results show that the proposed framework can achieve a 1.21%-19.84% improvement on F1-score using joint training of the matching and the decision components. The proposed CONNA has been successfully deployed on AMiner -- a large online academic search system.

cs.SI↗

arXiv2020

Large Magnetoresistance in Topological Insulator Candidate TaSe3

Large unsaturated magnetoresistance (XMR) with magnitude about 1000% is observed in topological insulator candidate TaSe3 from our high field (up to 38 T) measurements. Two oscillation modes, associated with one hole pocket and two electron pockets in the bulk, respectively, are detected from our Shubnikov-de Hass (SdH) measurements, consistent with our first-principles calculations. With the detailed Hall measurements performed, our two-band model analysis exhibits an imperfect density ratio n_h/n_e closing 0.9 at T< 20 K , which suggests that the carrier compensations account for the XMR in TaSe3.

cond-mat.mtrl-sci↗