arXiv subjects

Bo Liu

Publications and source records attributed to Bo Liu.

At least 541 records · Page 30Linked to original sources

arXiv2021

Discrete Knowledge Graph Embedding based on Discrete Optimization

This paper proposes a discrete knowledge graph (KG) embedding (DKGE) method, which projects KG entities and relations into the Hamming space based on a computationally tractable discrete optimization algorithm, to solve the formidable storage and computation cost challenges in traditional continuous graph embedding methods. The convergence of DKGE can be guaranteed theoretically. Extensive experiments demonstrate that DKGE achieves superior accuracy than classical hashing functions that map the effective continuous embeddings into discrete codes. Besides, DKGE reaches comparable accuracy with much lower computational complexity and storage compared to many continuous graph embedding methods.

cs.IR↗

arXiv2021

Topological semimetal and superfluid of s-wave interacting fermionic atoms in an orbital optical lattice

Recent advanced experimental implementations of optical lattices with highly tunable geometry open up new regimes for quantum many-body states of matter that previously had not been accessible. Here we introduce a symmetry-based method of utilizing the geometry of optical lattice to systematically control topologically non-trivial orbital hybridization. Such an orbital mixing leads to an unexpected and yet robust topological semimetal at single-particle level for a gas of fermionic atoms. When considering s-wave attractive interaction between atoms as for instance tuned by Feshbach resonance, topological superfluid state with high Chern number is unveiled in the presence of on-site rotation. This state supports chiral edge excitations, manifesting its topological nature. An experimental realization scheme is designed, which introduces a systematic way of achieving a new universality class (such as Chern number of 2) of orbital-hybridized topological phases beyond geometrically standard optical lattices.

cond-mat.quant-gas↗

arXiv2020

Towards Playing Full MOBA Games with Deep Reinforcement Learning

MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose grand challenges to AI systems such as multi-agent, enormous state-action space, complex action control, etc. Developing AI for playing MOBA games has raised much attention accordingly. However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i.e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes. As a result, full MOBA games without restrictions are far from being mastered by any existing AI system. In this paper, we propose a MOBA AI learning paradigm that methodologically enables playing full MOBA games with deep reinforcement learning. Specifically, we develop a combination of novel and existing learning techniques, including curriculum self-play learning, policy distillation, off-policy adaption, multi-head value estimation, and Monte-Carlo tree-search, in training and playing a large pool of heroes, meanwhile addressing the scalability issue skillfully. Tested on Honor of Kings, a popular MOBA game, we show how to build superhuman AI agents that can defeat top esports players. The superiority of our AI is demonstrated by the first large-scale performance test of MOBA AI agent in the literature.

cs.AI↗

arXiv2020

A temperature-modulated dilatometer by using a piezobender-based device

We report a new design of temperature-modulated dilatometer, which obtains the linear thermal expansion coefficient by measuring the oscillating changes of the sample's length and temperature by a piezobender and a thermocouple, respectively. Using an iron-based superconductor KFe$_2$As$_2$ as an example, we show that this device is able to measure thin samples with high resolutions at low temperatures and high magnetic fields. Despite its incapability of giving absolute values, the new dilatometer provides a high-resolution method to study many important physical properties in condensed matter physics, such as thermal and quantum phase transitions, and vortex dynamics in the superconducting state. The prototype design of this device can be further improved in many aspects to meet particular requirements.

physics.ins-det↗

arXiv2020

GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values

We present GradientDICE for estimating the density ratio between the state distribution of the target policy and the sampling distribution in off-policy reinforcement learning. GradientDICE fixes several problems of GenDICE (Zhang et al., 2020), the state-of-the-art for estimating such density ratios. Namely, the optimization problem in GenDICE is not a convex-concave saddle-point problem once nonlinearity in optimization variable parameterization is introduced to ensure positivity, so any primal-dual algorithm is not guaranteed to converge or find the desired solution. However, such nonlinearity is essential to ensure the consistency of GenDICE even with a tabular representation. This is a fundamental contradiction, resulting from GenDICE's original formulation of the optimization problem. In GradientDICE, we optimize a different objective from GenDICE by using the Perron-Frobenius theorem and eliminating GenDICE's use of divergence. Consequently, nonlinearity in parameterization is not necessary for GradientDICE, which is provably convergent under linear function approximation.

cs.LG↗

arXiv2020

When Machine Learning Meets Privacy: A Survey and Outlook

The newly emerged machine learning (e.g. deep learning) methods have become a strong driving force to revolutionize a wide range of industries, such as smart healthcare, financial technology, and surveillance systems. Meanwhile, privacy has emerged as a big concern in this machine learning-based artificial intelligence era. It is important to note that the problem of privacy preservation in the context of machine learning is quite different from that in traditional data privacy protection, as machine learning can act as both friend and foe. Currently, the work on the preservation of privacy and machine learning (ML) is still in an infancy stage, as most existing solutions only focus on privacy problems during the machine learning process. Therefore, a comprehensive study on the privacy preservation problems and machine learning is required. This paper surveys the state of the art in privacy issues and solutions for machine learning. The survey covers three categories of interactions between privacy and machine learning: (i) private machine learning, (ii) machine learning aided privacy protection, and (iii) machine learning-based privacy attack and corresponding protection schemes. The current research progress in each category is reviewed and the key challenges are identified. Finally, based on our in-depth analysis of the area of privacy and machine learning, we point out future research directions in this field.

cs.LG↗

arXiv2020

Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation

We present the first provably convergent two-timescale off-policy actor-critic algorithm (COF-PAC) with function approximation. Key to COF-PAC is the introduction of a new critic, the emphasis critic, which is trained via Gradient Emphasis Learning (GEM), a novel combination of the key ideas of Gradient Temporal Difference Learning and Emphatic Temporal Difference Learning. With the help of the emphasis critic and the canonical value function critic, we show convergence for COF-PAC, where the critics are linear and the actor can be nonlinear.

cs.LG↗

arXiv2020

Experimental implementation of secure anonymous protocols on an eight-user quantum network

Anonymity in networked communication is vital for many privacy-preserving tasks. Secure key distribution alone is insufficient for high-security communications, often knowing who transmits a message to whom and when must also be kept hidden from an adversary. Here we experimentally demonstrate 5 information-theoretically secure anonymity protocols on an 8 user city-wide quantum network using polarisation-entangled photon pairs. At the heart of these protocols is anonymous broadcasting, which is a cryptographic primitive that allows one user to reveal one bit of information while keeping her identity anonymous. For a network of $n$ users, the protocols retain anonymity for the sender, given less than $n-2$ users are dishonest. This is one of the earliest implementations of genuine multi-user cryptographic protocols beyond standard QKD. Our anonymous protocols enhance the functionality of any fully-connected Quantum Key Distribution network without trusted nodes.

quant-ph↗

arXiv2020

The SLT 2021 children speech recognition challenge: Open datasets, rules and baselines

Automatic speech recognition (ASR) has been significantly advanced with the use of deep learning and big data. However improving robustness, including achieving equally good performance on diverse speakers and accents, is still a challenging problem. In particular, the performance of children speech recognition (CSR) still lags behind due to 1) the speech and language characteristics of children's voice are substantially different from those of adults and 2) sizable open dataset for children speech is still not available in the research community. To address these problems, we launch the Children Speech Recognition Challenge (CSRC), as a flagship satellite event of IEEE SLT 2021 workshop. The challenge will release about 400 hours of Mandarin speech data for registered teams and set up two challenge tracks and provide a common testbed to benchmark the CSR performance. In this paper, we introduce the datasets, rules, evaluation method as well as baselines.

cs.SD↗

arXiv2020

Heterogeneous Deep Graph Infomax

Graph representation learning is to learn universal node representations that preserve both node attributes and structural information. The derived node representations can be used to serve various downstream tasks, such as node classification and node clustering. When a graph is heterogeneous, the problem becomes more challenging than the homogeneous graph node learning problem. Inspired by the emerging information theoretic-based learning algorithm, in this paper we propose an unsupervised graph neural network Heterogeneous Deep Graph Infomax (HDGI) for heterogeneous graph representation learning. We use the meta-path structure to analyze the connections involving semantics in heterogeneous graphs and utilize graph convolution module and semantic-level attention mechanism to capture local representations. By maximizing local-global mutual information, HDGI effectively learns high-level node representations that can be utilized in downstream graph-related tasks. Experiment results show that HDGI remarkably outperforms state-of-the-art unsupervised graph representation learning methods on both classification and clustering tasks. By feeding the learned representations into a parametric model, such as logistic regression, we even achieve comparable performance in node classification tasks when comparing with state-of-the-art supervised end-to-end GNN models.

cs.LG↗

arXiv2020

Discovery of the Superconductivity in 3d Element Ni doped IrTe$_2$

IrTe$_2$ with large spin-orbital coupling (SOC) shows a CDW-like first order structural phase transition from high-temperature trigonal phase to low-temperature monoclinic phase at 270 K, accompanying with a large jump in transport and magnetic measurement as well as in heat capacity. Here, the 3d element Ni has been doped into IrTe$_2$ by growing Ir$_{1-x}$Ni$_x$Te$_2$ single crystals. Both XRD and XPS results reveal that the Ni atoms have substituted for Ir, which is consistent with the calculation result. Like the CDW behaviour, the structural phase transition shows competition and coexistence with the superconductivity. The monoclinic phase transition has been suppressed gradually with the increase of the doping amount of Ni, at last giving rise to the stabilization of the trigonal phase with superconductivity. Within 0.1$\leq$x$\leq$0.2, Ir$_{1-x}$Ni$_x$Te$_2$ shows the superconductive behaviour with T$_c$ around 2.6K. The superconductivity shows anisotropy with dimensionless anisotropy parameter $γ$=$ξ_{//}$$/$$ξ_{\perp}$$\sim$ 2. Even Ni element shows ferromagnetic behaviour, Ir$_{1-x}$Ni$_x$Te$_2$ only shows weak paramagnetism, no ferromagnetic order is observed in it, which is coincident with the calculation result that their up and down spin density of states compensate each other well. In addition, for other 3d elements Fe, Co and Mn doped IrTe$_2$, only Ir$_{1-x}$Mn$_x$Te$_2$ owns magnetism with magnetic moment of 3.0$μ$$_B$ to the supercell, theoretically.

cond-mat.supr-con↗

arXiv2020

An Industry Evaluation of Embedding-based Entity Alignment

Embedding-based entity alignment has been widely investigated in recent years, but most proposed methods still rely on an ideal supervised learning setting with a large number of unbiased seed mappings for training and validation, which significantly limits their usage. In this study, we evaluate those state-of-the-art methods in an industrial context, where the impact of seed mappings with different sizes and different biases is explored. Besides the popular benchmarks from DBpedia and Wikidata, we contribute and evaluate a new industrial benchmark that is extracted from two heterogeneous knowledge graphs (KGs) under deployment for medical applications. The experimental results enable the analysis of the advantages and disadvantages of these alignment methods and the further discussion of suitable strategies for their industrial deployment.

cs.CL↗

arXiv2020

Strategies for achieving high key rates in satellite-based QKD

Quantum key distribution (QKD) is a pioneering quantum technology on the brink of widespread deployment. Nevertheless, the distribution of secret keys beyond a few 100 kilometers at practical rates remains a major challenge. One approach to circumvent lossy terrestrial transmission of entangled photon pairs is the deployment of optical satellite links. Optimizing these non-static quantum links to yield the highest possible key rate is essential for their successful operation. We therefore developed a high-brightness polarization-entangled photon pair source and a receiver module with a fast steering mirror capable of satellite tracking. We employed this state-of-the-art hardware to distribute photons over a terrestrial free-space link with a distance of 143 km, and extracted secure key rates up to 300 bits per second. Contrary to fiber-based links, the channel loss in satellite downlinks is time-varying and the link time is limited to a few minutes. We therefore propose a model-based optimization of link parameters based on current channel and receiver conditions. This model and our field test will prove helpful in the design and operation of future satellite missions and advance the distribution of secret keys at high rates on a global scale.

quant-ph↗

arXiv2020

The Layer-inserting Growth of Antiferromagnetic Topological Insulator MnBi$_2$Te$_4$ Based on Symmetry and Its X-ray Photoelectron Spectroscopy

The antiferromagnetic topological insulator has attracted lots of attention recently, as its intrinsic magnetism and topological property makes it a potential material to realize the quantum anomalous Hall effect (QAHE) at relative high temperature. Until now, only MnBi$_2$Te$_4$ is predicted and grown successfully. The other MB$_2$T$_4$-family materials predicted (MB$_2$T$_4$:M=transition-metal or rare-earth element, B=Bi or Sb, T=Te, Se, or S) with not only antiferromagnetic topological property but also rich and exotic topological quantum states and dynamically stable (or metastable) structure have not been realized on experiment completely. Here, MnBi$_2$Te$_4$ single crystals have been grown successfully and tested. It shows typical antiferromagnetic character, with Neel temperature of 24.5K and a spin-flop transition at H$\thickapprox$35000 Oe, 1.8K. After obtaining MnBi$_2$Te$_4$ single crystals, we have tried to synthesize the other members of MB$_2$T$_4$-family materials, but things are not going so well. Then it inspires us to discuss the growth mechanism of MnBi$_2$Te$_4$. The growth mode may be the layer-inserting growth mode based on symmetry, which is supported by our X-ray photoelectron spectroscopy (XPS) measurement. The XPS measurement combing with the $Ar^+$ ion sputtering is done to investigate the chemical state of MnBi$_2$Te$_4$. Binding energies (BE) of the MnBi$_2$Te$_4$-related contributions to Mn2p and Te3d spectra agree well with those of inserting material $α$-MnTe. Rising intensity of the Mn2p satellite for divalent Mn (bound to chalcogen) with atomic number of ligand (from MnO to MnBi$_2$Te$_4$) has been observed, thus suggesting classification of MnBi$_2$Te$_4$ as the charge-transfer compound. Understanding the growth mode of MnBi$_2$Te$_4$ can help us to grow the other members of MB$_2$T$_4$-family materials.

cond-mat.str-el↗

arXiv2020

APPLR: Adaptive Planner Parameter Learning from Reinforcement

Classical navigation systems typically operate using a fixed set of hand-picked parameters (e.g. maximum speed, sampling rate, inflation radius, etc.) and require heavy expert re-tuning in order to work in new environments. To mitigate this requirement, it has been proposed to learn parameters for different contexts in a new environment using human demonstrations collected via teleoperation. However, learning from human demonstration limits deployment to the training environment, and limits overall performance to that of a potentially-suboptimal demonstrator. In this paper, we introduce APPLR, Adaptive Planner Parameter Learning from Reinforcement, which allows existing navigation systems to adapt to new scenarios by using a parameter selection scheme discovered via reinforcement learning (RL) in a wide variety of simulation environments. We evaluate APPLR on a robot in both simulated and physical experiments, and show that it can outperform both a fixed set of hand-tuned parameters and also a dynamic parameter tuning scheme learned from human demonstration.

cs.RO↗

arXiv2020

Extended Abstract: Motion Planners Learned from Geometric Hallucination

Learning motion planners to move robot from one point to another within an obstacle-occupied space in a collision-free manner requires either an extensive amount of data or high-quality demonstrations. This requirement is caused by the fact that among the variety of maneuvers the robot can perform, it is difficult to find the single optimal plan without many trial-and-error or an expert who is already capable of doing so. However, given a plan performed in obstacle-free space, it is relatively easy to find an obstacle geometry, where this plan is optimal. We consider this "dual" problem of classical motion planning and name this process of finding appropriate obstacle geometry as hallucination. In this work, we present two different approaches to hallucinate (1) the most constrained and (2) a minimal obstacle space where a given plan executed during an exploration phase in a completely safe obstacle-free environment remains optimal. We then train an end-to-end motion planner that can produce motions to move through realistic obstacles during deployment. Both methods are tested on a physical mobile robot in real-world cluttered environments.

cs.RO↗

arXiv2020

The NVIDIA PilotNet Experiments

Four years ago, an experimental system known as PilotNet became the first NVIDIA system to steer an autonomous car along a roadway. This system represents a departure from the classical approach for self-driving in which the process is manually decomposed into a series of modules, each performing a different task. In PilotNet, on the other hand, a single deep neural network (DNN) takes pixels as input and produces a desired vehicle trajectory as output; there are no distinct internal modules connected by human-designed interfaces. We believe that handcrafted interfaces ultimately limit performance by restricting information flow through the system and that a learned approach, in combination with other artificial intelligence systems that add redundancy, will lead to better overall performing systems. We continue to conduct research toward that goal. This document describes the PilotNet lane-keeping effort, carried out over the past five years by our NVIDIA PilotNet group in Holmdel, New Jersey. Here we present a snapshot of system status in mid-2020 and highlight some of the work done by the PilotNet group.

cs.CV↗

arXiv2020

Google Landmark Recognition 2020 Competition Third Place Solution

We present our third place solution to the Google Landmark Recognition 2020 competition. It is an ensemble of global features only Sub-center ArcFace models. We introduce dynamic margins for ArcFace loss, a family of tune-able margin functions of class size, designed to deal with the extreme imbalance in GLDv2 dataset. Progressive finetuning and careful postprocessing are also key to the solution. Our two submissions scored 0.6344 and 0.6289 on private leaderboard, both ranking third place out of 736 teams.

cs.CV↗