arXiv subjects

Mingyu Yang

Publications and source records attributed to Mingyu Yang.

52 records · Page 3Linked to original sources

arXiv2023

Siamese Learning-based Monarch Butterfly Localization

A new GPS-less, daily localization method is proposed with deep learning sensor fusion that uses daylight intensity and temperature sensor data for Monarch butterfly tracking. Prior methods suffer from the location-independent day length during the equinox, resulting in high localization errors around that date. This work proposes a new Siamese learning-based localization model that improves the accuracy and reduces the bias of daily Monarch butterfly localization using light and temperature measurements. To train and test the proposed algorithm, we use $5658$ daily measurement records collected through a data measurement campaign involving 306 volunteers across the U.S., Canada, and Mexico from 2018 to 2020. This model achieves a mean absolute error of $1.416^\circ$ in latitude and $0.393^\circ$ in longitude coordinates outperforming the prior method.

eess.SP↗

arXiv2022

LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent Reinforcement Learning

Cooperative multi-agent reinforcement learning (MARL) has made prominent progress in recent years. For training efficiency and scalability, most of the MARL algorithms make all agents share the same policy or value network. However, in many complex multi-agent tasks, different agents are expected to possess specific abilities to handle different subtasks. In those scenarios, sharing parameters indiscriminately may lead to similar behavior across all agents, which will limit the exploration efficiency and degrade the final performance. To balance the training complexity and the diversity of agent behavior, we propose a novel framework to learn dynamic subtask assignment (LDSA) in cooperative MARL. Specifically, we first introduce a subtask encoder to construct a vector representation for each subtask according to its identity. To reasonably assign agents to different subtasks, we propose an ability-based subtask selection strategy, which can dynamically group agents with similar abilities into the same subtask. In this way, agents dealing with the same subtask share their learning of specific abilities and different subtasks correspond to different specific abilities. We further introduce two regularizers to increase the representation difference between subtasks and stabilize the training by discouraging agents from frequently changing subtasks, respectively. Empirical results show that LDSA learns reasonable and effective subtask assignment for better collaboration and significantly improves the learning performance on the challenging StarCraft II micromanagement benchmark and Google Research Football.

cs.LG↗

arXiv2022

Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection

In recent years, deep learning-based approaches for visual-inertial odometry (VIO) have shown remarkable performance outperforming traditional geometric methods. Yet, all existing methods use both the visual and inertial measurements for every pose estimation incurring potential computational redundancy. While visual data processing is much more expensive than that for the inertial measurement unit (IMU), it may not always contribute to improving the pose estimation accuracy. In this paper, we propose an adaptive deep-learning based VIO method that reduces computational redundancy by opportunistically disabling the visual modality. Specifically, we train a policy network that learns to deactivate the visual feature extractor on the fly based on the current motion state and IMU readings. A Gumbel-Softmax trick is adopted to train the policy network to make the decision process differentiable for end-to-end system training. The learned strategy is interpretable, and it shows scenario-dependent decision patterns for adaptive complexity reduction. Experiment results show that our method achieves a similar or even better performance than the full-modality baseline with up to 78.8% computational complexity reduction for KITTI dataset evaluation. The code is available at https://github.com/mingyuyng/Visual-Selective-VIO.

cs.CV↗

arXiv2022

NAFS: A Simple yet Tough-to-beat Baseline for Graph Representation Learning

Recently, graph neural networks (GNNs) have shown prominent performance in graph representation learning by leveraging knowledge from both graph structure and node features. However, most of them have two major limitations. First, GNNs can learn higher-order structural information by stacking more layers but can not deal with large depth due to the over-smoothing issue. Second, it is not easy to apply these methods on large graphs due to the expensive computation cost and high memory usage. In this paper, we present node-adaptive feature smoothing (NAFS), a simple non-parametric method that constructs node representations without parameter learning. NAFS first extracts the features of each node with its neighbors of different hops by feature smoothing, and then adaptively combines the smoothed features. Besides, the constructed node representation can further be enhanced by the ensemble of smoothed features extracted via different smoothing strategies. We conduct experiments on four benchmark datasets on two different application scenarios: node clustering and link prediction. Remarkably, NAFS with feature ensemble outperforms the state-of-the-art GNNs on these tasks and mitigates the aforementioned two limitations of most learning-based GNN counterparts.

cs.LG↗

arXiv2022

MCMARL: Parameterizing Value Function via Mixture of Categorical Distributions for Multi-Agent Reinforcement Learning

In cooperative multi-agent tasks, a team of agents jointly interact with an environment by taking actions, receiving a team reward and observing the next state. During the interactions, the uncertainty of environment and reward will inevitably induce stochasticity in the long-term returns and the randomness can be exacerbated with the increasing number of agents. However, such randomness is ignored by most of the existing value-based multi-agent reinforcement learning (MARL) methods, which only model the expectation of Q-value for both individual agents and the team. Compared to using the expectations of the long-term returns, it is preferable to directly model the stochasticity by estimating the returns through distributions. With this motivation, this work proposes a novel value-based MARL framework from a distributional perspective, \emph{i.e.}, parameterizing value function via \underline{M}ixture of \underline{C}ategorical distributions for MARL. Specifically, we model both individual Q-values and global Q-value with categorical distribution. To integrate categorical distributions, we define five basic operations on the distribution, which allow the generalization of expected value function factorization methods (\emph{e.g.}, VDN and QMIX) to their MCMARL variants. We further prove that our MCMARL framework satisfies \emph{Distributional-Individual-Global-Max} (DIGM) principle with respect to the expectation of distribution, which guarantees the consistency between joint and individual greedy action selections in the global Q-value and individual Q-values. Empirically, we evaluate MCMARL on both a stochastic matrix game and a challenging set of StarCraft II micromanagement tasks, showing the efficacy of our framework.

cs.LG↗

arXiv2022

Multi-Target Active Object Tracking with Monte Carlo Tree Search and Target Motion Modeling

In this work, we are dedicated to multi-target active object tracking (AOT), where there are multiple targets as well as multiple cameras in the environment. The goal is maximize the overall target coverage of all cameras. Previous work makes a strong assumption that each camera is fixed in a location and only allowed to rotate, which limits its application. In this work, we relax the setting by allowing all cameras to both move along the boundary lines and rotate. In our setting, the action space becomes much larger, which leads to much higher computational complexity to identify the optimal action. To this end, we propose to leverage the action selection from multi-agent reinforcement learning (MARL) network to prune the search tree of Monte Carlo Tree Search (MCTS) method, so as to find the optimal action more efficiently. Besides, we model the motion of the targets to predict the future position of the targets, which makes a better estimation of the future environment state in the MCTS process. We establish a multi-target 2D environment to simulate the sports games, and experimental results demonstrate that our method can effectively improve the target coverage.

cs.CV↗

arXiv2022

CTDS: Centralized Teacher with Decentralized Student for Multi-Agent Reinforcement Learning

Due to the partial observability and communication constraints in many multi-agent reinforcement learning (MARL) tasks, centralized training with decentralized execution (CTDE) has become one of the most widely used MARL paradigms. In CTDE, centralized information is dedicated to learning the allocation of the team reward with a mixing network, while the learning of individual Q-values is usually based on local observations. The insufficient utility of global observation will degrade performance in challenging environments. To this end, this work proposes a novel Centralized Teacher with Decentralized Student (CTDS) framework, which consists of a teacher model and a student model. Specifically, the teacher model allocates the team reward by learning individual Q-values conditioned on global observation, while the student model utilizes the partial observations to approximate the Q-values estimated by the teacher model. In this way, CTDS balances the full utilization of global observation during training and the feasibility of decentralized execution for online inference. Our CTDS framework is generic which is ready to be applied upon existing CTDE methods to boost their performance. We conduct experiments on a challenging set of StarCraft II micromanagement tasks to test the effectiveness of our method and the results show that CTDS outperforms the existing value-based MARL methods.

cs.MA↗

arXiv2022

Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agents

Multi-agent reinforcement learning is difficult to be applied in practice, which is partially due to the gap between the simulated and real-world scenarios. One reason for the gap is that the simulated systems always assume that the agents can work normally all the time, while in practice, one or more agents may unexpectedly "crash" during the coordination process due to inevitable hardware or software failures. Such crashes will destroy the cooperation among agents, leading to performance degradation. In this work, we present a formal formulation of a cooperative multi-agent reinforcement learning system with unexpected crashes. To enhance the robustness of the system to crashes, we propose a coach-assisted multi-agent reinforcement learning framework, which introduces a virtual coach agent to adjust the crash rate during training. We design three coaching strategies and the re-sampling strategy for our coach agent. To the best of our knowledge, this work is the first to study the unexpected crashes in the multi-agent system. Extensive experiments on grid-world and StarCraft II micromanagement tasks demonstrate the efficacy of adaptive strategy compared with the fixed crash rate strategy and curriculum learning strategy. The ablation study further illustrates the effectiveness of our re-sampling strategy.

cs.LG↗

arXiv2022

Coordinate-Aligned Multi-Camera Collaboration for Active Multi-Object Tracking

Active Multi-Object Tracking (AMOT) is a task where cameras are controlled by a centralized system to adjust their poses automatically and collaboratively so as to maximize the coverage of targets in their shared visual field. In AMOT, each camera only receives partial information from its observation, which may mislead cameras to take locally optimal action. Besides, the global goal, i.e., maximum coverage of objects, is hard to be directly optimized. To address the above issues, we propose a coordinate-aligned multi-camera collaboration system for AMOT. In our approach, we regard each camera as an agent and address AMOT with a multi-agent reinforcement learning solution. To represent the observation of each agent, we first identify the targets in the camera view with an image detector, and then align the coordinates of the targets in 3D environment. We define the reward of each agent based on both global coverage as well as four individual reward terms. The action policy of the agents is derived with a value-based Q-network. To the best of our knowledge, we are the first to study the AMOT task. To train and evaluate the efficacy of our system, we build a virtual yet credible 3D environment, named "Soccer Court", to mimic the real-world AMOT scenario. The experimental results show that our system achieves a coverage of 71.88%, outperforming the baseline method by 8.9%.

cs.CV↗

arXiv2021

Deep Learning Based Near-Orthogonal Superposition Code for Short Message Transmission

Massive machine type communication (mMTC) has attracted new coding schemes optimized for reliable short message transmission. In this paper, a novel deep learning based near-orthogonal superposition (NOS) coding scheme is proposed for reliable transmission of short messages in the additive white Gaussian noise (AWGN) channel for mMTC applications. Similar to recent hyper-dimensional modulation (HDM), the NOS encoder spreads the information bits to multiple near-orthogonal high dimensional vectors to be combined (superimposed) into a single vector for transmission. The NOS decoder first estimates the information vectors and then performs a cyclic redundancy check (CRC)-assisted K-best tree-search algorithm to further reduce the packet error rate. The proposed NOS encoder and decoder are deep neural networks (DNNs) jointly trained as an auto encoder and decoder pair to learn a new NOS coding scheme with near-orthogonal codewords. Simulation results show the proposed deep learning-based NOS scheme outperforms HDM and Polar code with CRC-aided list decoding for short(32-bit) message transmission.

cs.IT↗

arXiv2021

Node Dependent Local Smoothing for Scalable Graph Learning

Recent works reveal that feature or label smoothing lies at the core of Graph Neural Networks (GNNs). Concretely, they show feature smoothing combined with simple linear regression achieves comparable performance with the carefully designed GNNs, and a simple MLP model with label smoothing of its prediction can outperform the vanilla GCN. Though an interesting finding, smoothing has not been well understood, especially regarding how to control the extent of smoothness. Intuitively, too small or too large smoothing iterations may cause under-smoothing or over-smoothing and can lead to sub-optimal performance. Moreover, the extent of smoothness is node-specific, depending on its degree and local structure. To this end, we propose a novel algorithm called node-dependent local smoothing (NDLS), which aims to control the smoothness of every node by setting a node-specific smoothing iteration. Specifically, NDLS computes influence scores based on the adjacency matrix and selects the iteration number by setting a threshold on the scores. Once selected, the iteration number can be applied to both feature smoothing and label smoothing. Experimental results demonstrate that NDLS enjoys high accuracy -- state-of-the-art performance on node classifications tasks, flexibility -- can be incorporated with any models, scalability and efficiency -- can support large scale graphs with fast training.

cs.LG↗

arXiv2021

Deep Joint Source-Channel Coding for Wireless Image Transmission with Adaptive Rate Control

We present a novel adaptive deep joint source-channel coding (JSCC) scheme for wireless image transmission. The proposed scheme supports multiple rates using a single deep neural network (DNN) model and learns to dynamically control the rate based on the channel condition and image contents. Specifically, a policy network is introduced to exploit the tradeoff space between the rate and signal quality. To train the policy network, the Gumbel-Softmax trick is adopted to make the policy network differentiable and hence the whole JSCC scheme can be trained end-to-end. To the best of our knowledge, this is the first deep JSCC scheme that can automatically adjust its rate using a single network model. Experiments show that our scheme successfully learns a reasonable policy that decreases channel bandwidth utilization for high SNR scenarios or simple image contents. For an arbitrary target rate, our rate-adaptive scheme using a single model achieves similar performance compared to an optimized model specifically trained for that fixed target rate. To reproduce our results, we make the source code publicly available at https://github.com/mingyuyng/Dynamic_JSCC.

eess.SP↗

arXiv2021

OFDM-guided Deep Joint Source Channel Coding for Wireless Multipath Fading Channels

We investigate joint source channel coding (JSCC) for wireless image transmission over multipath fading channels. Inspired by recent works on deep learning based JSCC and model-based learning methods, we combine an autoencoder with orthogonal frequency division multiplexing (OFDM) to cope with multipath fading. The proposed encoder and decoder use convolutional neural networks (CNNs) and directly map the source images to complex-valued baseband samples for OFDM transmission. The multipath channel and OFDM are represented by non-trainable (deterministic) but differentiable layers so that the system can be trained end-to-end. Furthermore, our JSCC decoder further incorporates explicit channel estimation, equalization, and additional subnets to enhance the performance. The proposed method exhibits 2.5 -- 4 dB SNR gain for the equivalent image quality compared to conventional schemes that employ state-of-the-art but separate source and channel coding such as BPG and LDPC. The performance further improves when the system incorporates the channel state information (CSI) feedback. The proposed scheme is robust against OFDM signal clipping and parameter mismatch for the channel model used in training and evaluation.

eess.SP↗

arXiv2021

Hybrid algorithms to solve linear systems of equations with limited qubit resources

The solution of linear systems of equations is a very frequent operation and thus important in many fields. The complexity using classical methods increases linearly with the size of equations. The HHL algorithm proposed by Harrow et al. achieves exponential acceleration compared with the best classical algorithm. However, it has a relatively high demand for qubit resources and the solution $\left| x \right\rangle $ is in a normalized form. Assuming that the eigenvalues of the coefficient matrix of the linear systems of equations can be represented perfectly by finite binary number strings, three hybrid iterative phase estimation algorithms (HIPEA) are designed based on the iterative phase estimation algorithm in this paper. The complexity is transferred to the measurement operation in an iterative way, and thus the demand of qubit resources is reduced in our hybrid algorithms. Moreover, the solution is stored in a classical register instead of a quantum register, so the exact unnormalized solution can be obtained. The required qubit resources in the three HIPEA algorithms are different. HIPEA-1 only needs one single ancillary qubit. The number of ancillary qubits in HIPEA-2 is equal to the number of nondegenerate eigenvalues of the coefficient matrix of linear systems of equations. HIPEA-3 is designed with a flexible number of ancillary qubits. The HIPEA algorithms proposed in this paper broadens the application range of quantum computation in solving linear systems of equations by avoiding the problem that quantum programs may not be used to solve linear systems of equations due to the lack of qubit resources.

quant-ph↗

arXiv2021

Deep Joint Source Channel Coding for WirelessImage Transmission with OFDM

We present a deep learning based joint source channel coding (JSCC) scheme for wireless image transmission over multipath fading channels with non-linear signal clipping. The proposed encoder and decoder use convolutional neural networks (CNN) and directly map the source images to complex-valued baseband samples for orthogonal frequency division multiplexing (OFDM) transmission. The proposed model-driven machine learning approach eliminates the need for separate source and channel coding while integrating an OFDM datapath to cope with multipath fading channels. The end-to-end JSCC communication system combines trainable CNN layers with non-trainable but differentiable layers representing the multipath channel model and OFDM signal processing blocks. Our results show that injecting domain expert knowledge by incorporating OFDM baseband processing blocks into the machine learning framework significantly enhances the overall performance compared to an unstructured CNN. Our method outperforms conventional schemes that employ state-of-the-art but separate source and channel coding such as BPG and LDPC with OFDM. Moreover, our method is shown to be robust against non-linear signal clipping in OFDM for various channel conditions that do not match the model parameter used during the training.

eess.SP↗

arXiv2019

Migrating Monarch Butterfly Localization Using Multi-Sensor Fusion Neural Networks

Details of Monarch butterfly migration from the U.S. to Mexico remain a mystery due to lack of a proper localization technology to accurately localize and track butterfly migration. In this paper, we propose a deep learning based butterfly localization algorithm that can estimate a butterfly's daily location by analyzing a light and temperature sensor data log continuously obtained from an ultra-low power, mm-scale sensor attached to the butterfly. To train and test the proposed neural network based multi-sensor fusion localization algorithm, we collected over 1500 days of real world sensor measurement data with 82 volunteers all over the U.S. The proposed algorithm exhibits a mean absolute error of <1.5 degree in latitude and <0.5 degree in longitude Earth coordinate, satisfying our target goal for the Monarch butterfly migration study.

eess.SP↗