arXiv subjects

Bo Yang

Publications and source records attributed to Bo Yang.

At least 343 records · Page 19Linked to original sources

arXiv2023

GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds

We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing methods which primarily rely on a large amount of human annotations for training neural networks, we propose the first purely unsupervised method, called GrowSP, to successfully identify complex semantic classes for every point in 3D scenes, without needing any type of human labels or pretrained models. The key to our approach is to discover 3D semantic elements via progressive growing of superpoints. Our method consists of three major components, 1) the feature extractor to learn per-point features from input point clouds, 2) the superpoint constructor to progressively grow the sizes of superpoints, and 3) the semantic primitive clustering module to group superpoints into semantic elements for the final semantic segmentation. We extensively evaluate our method on multiple datasets, demonstrating superior performance over all unsupervised baselines and approaching the classic fully-supervised PointNet. We hope our work could inspire more advanced methods for unsupervised 3D semantic learning.

cs.CV↗

arXiv2023

Geometric Fluctuation of Conformal Hilbert Spaces and Multiple Graviton Modes in Fractional Quantum Hall Effect

Neutral excitations in fractional quantum Hall (FQH) fluids define the incompressibility of topological phases, a species of which can show graviton-like behaviors and are thus called the graviton modes (GMs). Here, we develop the microscopic theory for multiple GMs in FQH fluids and show explicitly that they are associated with the geometric fluctuation of well-defined conformal Hilbert spaces (CHSs), which are hierarchical subspaces within a single Landau level, each with emergent conformal symmetry and continuously parameterized by a unimodular metric. This leads to several statements about the number and the merging/splitting of GMs, which are verified numerically with both model and realistic interactions. We also discuss how the microscopic theory can serve as the basis for the additional Haldane modes in the effective field theory description and their experimental relevance to realistic electron-electron interactions.

cond-mat.str-el↗

arXiv2023

Do We Need an Encoder-Decoder to Model Dynamical Systems on Networks?

As deep learning gains popularity in modelling dynamical systems, we expose an underappreciated misunderstanding relevant to modelling dynamics on networks. Strongly influenced by graph neural networks, latent vertex embeddings are naturally adopted in many neural dynamical network models. However, we show that embeddings tend to induce a model that fits observations well but simultaneously has incorrect dynamical behaviours. Recognising that previous studies narrowly focus on short-term predictions during the transient phase of a flow, we propose three tests for correct long-term behaviour, and illustrate how an embedding-based dynamical model fails these tests, and analyse the causes, particularly through the lens of topological conjugacy. In doing so, we show that the difficulties can be avoided by not using embedding. We propose a simple embedding-free alternative based on parametrising two additive vector-field components. Through extensive experiments, we verify that the proposed model can reliably recover a broad class of dynamics on different network topologies from time series data.

cs.LG↗

arXiv2023

Dual Personalization on Federated Recommendation

Federated recommendation is a new Internet service architecture that aims to provide privacy-preserving recommendation services in federated settings. Existing solutions are used to combine distributed recommendation algorithms and privacy-preserving mechanisms. Thus it inherently takes the form of heavyweight models at the server and hinders the deployment of on-device intelligent models to end-users. This paper proposes a novel Personalized Federated Recommendation (PFedRec) framework to learn many user-specific lightweight models to be deployed on smart devices rather than a heavyweight model on a server. Moreover, we propose a new dual personalization mechanism to effectively learn fine-grained personalization on both users and items. The overall learning process is formulated into a unified federated optimization framework. Specifically, unlike previous methods that share exactly the same item embeddings across users in a federated system, dual personalization allows mild finetuning of item embeddings for each user to generate user-specific views for item representations which can be integrated into existing federated recommendation methods to gain improvements immediately. Experiments on multiple benchmark datasets have demonstrated the effectiveness of PFedRec and the dual personalization mechanism. Moreover, we provide visualizations and in-depth analysis of the personalization techniques in item embedding, which shed novel insights on the design of recommender systems in federated settings. The code is available.

cs.IR↗

arXiv2023

Enhancing multilingual speech recognition in air traffic control by sentence-level language identification

Automatic speech recognition (ASR) technique is becoming increasingly popular to improve the efficiency and safety of air traffic control (ATC) operations. However, the conversation between ATC controllers and pilots using multilingual speech brings a great challenge to building high-accuracy ASR systems. In this work, we present a two-stage multilingual ASR framework. The first stage is to train a language identifier (LID), that based on a recurrent neural network (RNN) to obtain sentence language identification in the form of one-hot encoding. The second stage aims to train an RNN-based end-to-end multilingual recognition model that utilizes sentence language features generated by LID to enhance input features. In this work, We introduce Featurewise Linear Modulation (FiLM) to improve the performance of multilingual ASR by utilizing sentence language identification. Furthermore, we introduce a new sentence language identification learning module called SLIL, which consists of a FiLM layer and a Squeeze-and-Excitation Networks layer. Extensive experiments on the ATCSpeech dataset show that our proposed method outperforms the baseline model. Compared to the vanilla FiLMed backbone model, the proposed multilingual ASR model obtains about 7.50% character error rate relative performance improvement.

cs.SD↗

arXiv2023

SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds

Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is even necessary, demonstrating that existing baselines designed under a fully annotated assumption only degrade slightly even when faced with 1% random point annotations. However, beyond this point, e.g., at 0.1% annotations, segmentation accuracy is unacceptably low. We observe that, as point clouds are samples of the 3D world, the distribution of points in a local neighborhood is relatively homogeneous, exhibiting strong semantic similarity. Motivated by this, we propose a new weak supervision method to implicitly augment highly sparse supervision signals. Extensive experiments demonstrate the proposed Semantic Query Network (SQN) achieves promising performance on seven large-scale open datasets under weak supervision schemes, while requiring only 0.1% randomly annotated points for training, greatly reducing annotation cost and effort. The code is available at https://github.com/QingyongHu/SQN.

cs.CV↗

arXiv2023

SSBM: A Signed Stochastic Block Model for Multiple Structure Discovery in Large-Scale Exploratory Signed Networks

Signed network structure discovery has received extensive attention and has become a research focus in the field of network science. However, most of the existing studies are focused on the networks with a single structure, e.g., community or bipartite, while ignoring multiple structures, e.g., the coexistence of community and bipartite structures. Furthermore, existing studies were faced with challenge regarding large-scale signed networks due to their high time complexity, especially when determining the number of clusters in the observed network without any prior knowledge. In view of this, we propose a mathematically principled method for signed network multiple structure discovery named the Signed Stochastic Block Model (SSBM). The SSBM can capture the multiple structures contained in signed networks, e.g., community, bipartite, and coexistence of them, by adopting a probabilistic model. Moreover, by integrating the minimum message length (MML) criterion and component-wise EM (CEM) algorithm, a scalable learning algorithm that has the ability of model selection is proposed to handle large-scale signed networks. By comparing state-of-the-art methods on synthetic and real-world signed networks, extensive experimental results demonstrate the effectiveness and efficiency of SSBM in discovering large-scale exploratory signed networks with multiple structures.

cs.SI↗

arXiv2023

NeUDF: Leaning Neural Unsigned Distance Fields with Volume Rendering

Multi-view shape reconstruction has achieved impressive progresses thanks to the latest advances in neural implicit surface rendering. However, existing methods based on signed distance function (SDF) are limited to closed surfaces, failing to reconstruct a wide range of real-world objects that contain open-surface structures. In this work, we introduce a new neural rendering framework, coded NeUDF, that can reconstruct surfaces with arbitrary topologies solely from multi-view supervision. To gain the flexibility of representing arbitrary surfaces, NeUDF leverages the unsigned distance function (UDF) as surface representation. While a naive extension of an SDF-based neural renderer cannot scale to UDF, we propose two new formulations of weight function specially tailored for UDF-based volume rendering. Furthermore, to cope with open surface rendering, where the in/out test is no longer valid, we present a dedicated normal regularization strategy to resolve the surface orientation ambiguity. We extensively evaluate our method over a number of challenging datasets, including DTU}, MGN, and Deep Fashion 3D. Experimental results demonstrate that nEudf can significantly outperform the state-of-the-art method in the task of multi-view surface reconstruction, especially for complex shapes with open boundaries.

cs.CV↗

arXiv2023

Linear Model Predictive Control under Continuous Path Constraints via Parallelized Primal-Dual Hybrid Gradient Algorithm

In this paper, we consider a Model Predictive Control (MPC) problem of a continuous-time linear time-invariant system subject to continuous-time path constraints on the states and the inputs. By leveraging the concept of differential flatness, we can replace the differential equations governing the system with linear mapping between the states, inputs, and flat outputs (including their derivatives). The flat outputs are then parameterized by piecewise polynomials, and the model predictive control problem can be equivalently transformed into a Semi-Definite Programming (SDP) problem via Sum-of-Squares (SOS), ensuring constraint satisfaction at every continuous-time interval. We further note that the SDP problem contains a large number of small-size semi-definite matrices as optimization variables. To address this, we develop a Primal-Dual Hybrid Gradient (PDHG) algorithm that can be efficiently parallelized to speed up the optimization procedure. Simulation results on a quadruple-tank process demonstrate that our formulation can guarantee strict constraint satisfaction, while the standard MPC controller based on the discretized system may violate the constraint inside a sampling period. Moreover, the computational speed superiority of our proposed algorithm is collaborated by numerical simulation.

math.OC↗

arXiv2023

Pretrained Embeddings for E-commerce Machine Learning: When it Fails and Why?

The use of pretrained embeddings has become widespread in modern e-commerce machine learning (ML) systems. In practice, however, we have encountered several key issues when using pretrained embedding in a real-world production system, many of which cannot be fully explained by current knowledge. Unfortunately, we find that there is a lack of a thorough understanding of how pre-trained embeddings work, especially their intrinsic properties and interactions with downstream tasks. Consequently, it becomes challenging to make interactive and scalable decisions regarding the use of pre-trained embeddings in practice. Our investigation leads to two significant discoveries about using pretrained embeddings in e-commerce applications. Firstly, we find that the design of the pretraining and downstream models, particularly how they encode and decode information via embedding vectors, can have a profound impact. Secondly, we establish a principled perspective of pre-trained embeddings via the lens of kernel analysis, which can be used to evaluate their predictability, interactively and scalably. These findings help to address the practical challenges we faced and offer valuable guidance for successful adoption of pretrained embeddings in real-world production. Our conclusions are backed by solid theoretical reasoning, benchmark experiments, as well as online testings.

cs.LG↗

arXiv2023

Interacting topological Dirac magnons

In this work, we study the magnon-magnon interaction effect in typical honeycomb ferromagnets consisting of van der Waals-bonded stacks of honeycomb layers, e.g., chromium trihalides CrX3 (X = F, Cl, Br, and I), that display two spin-wave modes (Dirac magnon). Using Green's function formalism with the presence of the Dzyaloshinskii-Moriya interaction, we obtain a spinor Dyson equation up to the second-order approximation by the cluster expansion method. Numerical calculations show prominent renormalizations of the single-particle spectrum. Furthermore, we propose a tunable renormalization effect using a parametric magnon amplification scheme. By amplifying the magnon population at different k points, the enabled renormalization effect not only reshapes the band structure but also modifies the Berry curvature distribution. Our work demonstrates the interplay between band geometry, interactions, and the external light field in the bosonic system and can potentially lead to new insights into the properties of magnon-based spintronic devices.

cond-mat.mes-hall↗

arXiv2023

Volume preserving Gauss curvature flow of convex hypersurfaces in the hyperbolic space

We consider the volume preserving flow of smooth, closed and convex hypersurfaces in the hyperbolic space $\mathbb{H}^{n+1} (n\geq 2)$ with the speed given by arbitrary positive power $α$ of the Gauss curvature. We prove that if the initial hypersurface is convex, then the smooth solution of the flow remains convex and exists for all positive time $t\in [0,\infty)$. Moreover, we apply a result of Kohlmann which characterises the geodesic ball using the hyperbolic curvature measures and an argument of Alexandrov reflection to prove that the flow converges to a geodesic sphere exponentially in the smooth topology. This can be viewed as the first result for non-local type volume preserving curvature flows for hypersurfaces in the hyperbolic space with only convexity required on the initial data.

math.DG↗

arXiv2023

NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Images

Recent progress in neural implicit functions has set new state-of-the-art in reconstructing high-fidelity 3D shapes from a collection of images. However, these approaches are limited to closed surfaces as they require the surface to be represented by a signed distance field. In this paper, we propose NeAT, a new neural rendering framework that can learn implicit surfaces with arbitrary topologies from multi-view images. In particular, NeAT represents the 3D surface as a level set of a signed distance function (SDF) with a validity branch for estimating the surface existence probability at the query positions. We also develop a novel neural volume rendering method, which uses SDF and validity to calculate the volume opacity and avoids rendering points with low validity. NeAT supports easy field-to-mesh conversion using the classic Marching Cubes algorithm. Extensive experiments on DTU, MGN, and Deep Fashion 3D datasets indicate that our approach is able to faithfully reconstruct both watertight and non-watertight surfaces. In particular, NeAT significantly outperforms the state-of-the-art methods in the task of open surface reconstruction both quantitatively and qualitatively.

cs.CV↗

arXiv2023

DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images

In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views. By leveraging the recent implicit neural representation techniques, particularly the appealing neural radiance fields, we introduce an object field component to learn unique codes for all individual objects in 3D space only from 2D supervision. The key to this component is a series of carefully designed loss functions to enable every 3D point, especially in non-occupied space, to be effectively optimized even without 3D labels. In addition, we introduce an inverse query algorithm to freely manipulate any specified 3D object shape in the learned scene representation. Notably, our manipulation algorithm can explicitly tackle key issues such as object collisions and visual occlusions. Our method, called DM-NeRF, is among the first to simultaneously reconstruct, decompose, manipulate and render complex 3D scenes in a single pipeline. Extensive experiments on three datasets clearly show that our method can accurately decompose all 3D objects from 2D views, allowing any interested object to be freely manipulated in 3D space such as translation, rotation, size adjustment, and deformation.

cs.CV↗

arXiv2023

Decoupling Skill Learning from Robotic Control for Generalizable Object Manipulation

Recent works in robotic manipulation through reinforcement learning (RL) or imitation learning (IL) have shown potential for tackling a range of tasks e.g., opening a drawer or a cupboard. However, these techniques generalize poorly to unseen objects. We conjecture that this is due to the high-dimensional action space for joint control. In this paper, we take an alternative approach and separate the task of learning 'what to do' from 'how to do it' i.e., whole-body control. We pose the RL problem as one of determining the skill dynamics for a disembodied virtual manipulator interacting with articulated objects. The whole-body robotic kinematic control is optimized to execute the high-dimensional joint motion to reach the goals in the workspace. It does so by solving a quadratic programming (QP) model with robotic singularity and kinematic constraints. Our experiments on manipulating complex articulated objects show that the proposed approach is more generalizable to unseen objects with large intra-class variations, outperforming previous approaches. The evaluation results indicate that our approach generates more compliant robotic motion and outperforms the pure RL and IL baselines in task success rates. Additional information and videos are available at https://kl-research.github.io/decoupskill

cs.RO↗

arXiv2023

High-fidelity realization of the AKLT state on a NISQ-era quantum processor

The AKLT state is the ground state of an isotropic quantum Heisenberg spin-$1$ model. It exhibits an excitation gap and an exponentially decaying correlation function, with fractionalized excitations at its boundaries. So far, the one-dimensional AKLT model has only been experimentally realized with trapped-ions as well as photonic systems. In this work, we successfully prepared the AKLT state on a noisy intermediate-scale quantum (NISQ) era quantum device for the first time. In particular, we developed a non-deterministic algorithm on the IBM quantum processor, where the non-unitary operator necessary for the AKLT state preparation is embedded in a unitary operator with an additional ancilla qubit for each pair of auxiliary spin-1/2's. Such a unitary operator is effectively represented by a parametrized circuit composed of single-qubit and nearest-neighbor $CX$ gates. Compared with the conventional operator decomposition method from Qiskit, our approach results in a much shallower circuit depth with only nearest-neighbor gates, while maintaining a fidelity in excess of $99.99\%$ with the original operator. By simultaneously post-selecting each ancilla qubit such that it belongs to the subspace of spin-up $|\uparrow \rangle$, an AKLT state can be systematically obtained by evolving from an initial trivial product state of singlets plus ancilla qubits in spin-up on a quantum computer, and it is subsequently recorded by performing measurements on all the other physical qubits. We show how the accuracy of our implementation can be further improved on the IBM quantum processor with readout error mitigation.

quant-ph↗

arXiv2023

Two-timescale Mechanism-and-Data-Driven Control for Aggressive Driving of Autonomous Cars

The control for aggressive driving of autonomous cars is challenging due to the presence of significant tyre slip. Data-driven and mechanism-based methods for the modeling and control of autonomous cars under aggressive driving conditions are limited in data efficiency and adaptability respectively. This paper is an attempt toward the fusion of the two classes of methods. By means of a modular design that is consisted of mechanism-based and data-driven components, and aware of the two-timescale phenomenon in the car model, our approach effectively improves over previous methods in terms of data efficiency, ability of transfer and final performance. The hybrid mechanism-and-data-driven approach is verified on TORCS (The Open Racing Car Simulator). Experiment results demonstrate the benefit of our approach over purely mechanism-based and purely data-driven methods.

cs.RO↗

arXiv2023

OPT-GAN: A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution

Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details. Most classical methods for such problems are based on strong and fixed a priori assumptions, such as Gaussianity. However, the complex real-world problems, especially when the global optimum is desired, could be very far from the a priori assumptions because of their diversities, causing unexpected obstacles. In this study, we propose a generative adversarial net-based broad-spectrum global optimizer (OPT-GAN) which estimates the distribution of optimum gradually, with strategies to balance exploration-exploitation trade-off. It has potential to better adapt to the regularity and structure of diversified landscapes than other methods with fixed prior, e.g., Gaussian assumption or separability. Experiments on diverse BBO benchmarks and high dimensional real world applications exhibit that OPT-GAN outperforms other traditional and neural net-based BBO algorithms.

cs.LG↗