arXiv subjects

Yiming Zhang

Publications and source records attributed to Yiming Zhang.

At least 181 records · Page 10Linked to original sources

arXiv2022

Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance

Recent advances in model-free deep reinforcement learning (DRL) show that simple model-free methods can be highly effective in challenging high-dimensional continuous control tasks. In particular, Truncated Quantile Critics (TQC) achieves state-of-the-art asymptotic training performance on the MuJoCo benchmark with a distributional representation of critics; and Randomized Ensemble Double Q-Learning (REDQ) achieves high sample efficiency that is competitive with state-of-the-art model-based methods using a high update-to-data ratio and target randomization. In this paper, we propose a novel model-free algorithm, Aggressive Q-Learning with Ensembles (AQE), which improves the sample-efficiency performance of REDQ and the asymptotic performance of TQC, thereby providing overall state-of-the-art performance during all stages of training. Moreover, AQE is very simple, requiring neither distributional representation of critics nor target randomization. The effectiveness of AQE is further supported by our extensive experiments, ablations, and theoretical results.

cs.LG↗

arXiv2022

Active Example Selection for In-Context Learning

With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance can be highly unstable across samples of examples, indicating the idiosyncrasies of how language models acquire information. We formulate example selection for in-context learning as a sequential decision problem, and propose a reinforcement learning algorithm for identifying generalizable policies to select demonstration examples. For GPT-2, our learned policies demonstrate strong abilities of generalizing to unseen tasks in training, with a $5.8\%$ improvement on average. Examples selected from our learned policies can even achieve a small improvement on GPT-3 Ada. However, the improvement diminishes on larger GPT-3 models, suggesting emerging capabilities of large language models.

cs.CL↗

arXiv2022

Aircraft Ground Taxiing Deduction and Conflict Early Warning Method Based on Control Command Information

Aircraft taxiing conflict is a threat to the safety of airport operations, mainly due to the human error in control command infor-mation. In order to solve the problem, The aircraft taxiing deduction and conflict early warning method based on control order information is proposed. This method does not need additional equipment and operating costs, and is completely based on his-torical data and control command information. When the aircraft taxiing command is given, the future route information will be deduced, and the probability of conflict with other taxiing aircraft will be calculated to achieve conflict detection and early warning of different levels. The method is validated by the aircraft taxi data from real airports. The results show that the method can effectively predict the aircraft taxiing process, and can provide early warning of possible conflicts. Due to the advantages of low cost and high accuracy, this method has the potential to be applied to airport operation decision support system.

eess.SY↗

arXiv2022

CW-ERM: Improving Autonomous Driving Planning with Closed-loop Weighted Empirical Risk Minimization

The imitation learning of self-driving vehicle policies through behavioral cloning is often carried out in an open-loop fashion, ignoring the effect of actions to future states. Training such policies purely with Empirical Risk Minimization (ERM) can be detrimental to real-world performance, as it biases policy networks towards matching only open-loop behavior, showing poor results when evaluated in closed-loop. In this work, we develop an efficient and simple-to-implement principle called Closed-loop Weighted Empirical Risk Minimization (CW-ERM), in which a closed-loop evaluation procedure is first used to identify training data samples that are important for practical driving performance and then we these samples to help debias the policy network. We evaluate CW-ERM in a challenging urban driving dataset and show that this procedure yields a significant reduction in collisions as well as other non-differentiable closed-loop metrics.

cs.LG↗

arXiv2022

Measuring the knot of non-Hermitian degeneracies and non-commuting braids

Any system of coupled oscillators may be characterized by its spectrum of resonance frequencies (or eigenfrequencies), which can be tuned by varying the system's parameters. The relationship between control parameters and the eigenfrequency spectrum is central to a range of applications. However, fundamental aspects of this relationship remain poorly understood. For example, if the controls are varied along a path that returns to its starting point (i.e., around a "loop"), the system's spectrum must return to itself. In systems that are Hermitian (i.e., lossless and reciprocal) this process is trivial, and each resonance frequency returns to its original value. However, in non-Hermitian systems, where the eigenfrequencies are complex, the spectrum may return to itself in a topologically non-trivial manner, a phenomenon known as spectral flow. The spectral flow is determined by how the control loop encircles degeneracies, and this relationship is well understood for $N=2$ (where $N$ is the number of oscillators in the system). Here we extend this description to arbitrary $N$. We show that control loops generically produce braids of eigenfrequencies, and for $N>2$ these braids form a non-Abelian group which reflects the non-trivial geometry of the space of degeneracies. We demonstrate these features experimentally for $N=3$ using a cavity optomechanical system.

physics.optics↗

arXiv2022

EmbRace: Accelerating Sparse Communication for Distributed Training of NLP Neural Networks

Distributed data-parallel training has been widely adopted for deep neural network (DNN) models. Although current deep learning (DL) frameworks scale well for dense models like image classification models, we find that these DL frameworks have relatively low scalability for sparse models like natural language processing (NLP) models that have highly sparse embedding tables. Most existing works overlook the sparsity of model parameters thus suffering from significant but unnecessary communication overhead. In this paper, we propose EmbRace, an efficient communication framework to accelerate communications of distributed training for sparse models. EmbRace introduces Sparsity-aware Hybrid Communication, which integrates AlltoAll and model parallelism into data-parallel training, so as to reduce the communication overhead of highly sparse parameters. To effectively overlap sparse communication with both backward and forward computation, EmbRace further designs a 2D Communication Scheduling approach which optimizes the model computation procedure, relaxes the dependency of embeddings, and schedules the sparse communications of each embedding row with a priority queue. We have implemented a prototype of EmbRace based on PyTorch and Horovod, and conducted comprehensive evaluations with four representative NLP models. Experimental results show that EmbRace achieves up to 2.41X speedup compared to the state-of-the-art distributed training baselines.

cs.LG↗

arXiv2022

Nonholonomic dynamics and control of road vehicles: moving toward automation

Nonholonomic models of automobiles are developed by utilizing tools of analytical mechanics, in particular the Appellian approach that allows one to describe the vehicle dynamics with minimum number of time-dependent state variables. The models are categorized based on how they represent the wheel-ground contact, whether they incorporate the longitudinal dynamics, and whether they consider the steering dynamics. It is demonstrated that the developed models can be used to design low-complexity controllers that enable automated vehicles to execute a large variety of maneuvers with high precision.

eess.SY↗

arXiv2022

High thermoelectric performances in PbP monolayers considering full electron-phonon coupling and four-phonon scattering processes

The band convergence strategy, which improves Seebeck coefficient by inducing multi-valley in bandstructures, has been widely used in thermoelectric performance (TE) enhancing. However, the phonon-assisted intervalley scattering effect is neglected and the mode-selection rules remain unclear. In this work, TE properties for $α$-, $β$- and $γ$-PbP are intestigated under the consideration of full mode-, energy- and momentum-resolved electron-phonon interactions (EPI). The group theory is used to analyze the selection rules for EPI matrix elements. Our calculations reveal that, the intervalley scattering contributes non-trivially to the total carrier relaxation time, and the intervalley scattering can be modulated through crystal symmetry. In addition, the investigation on the thermal properties reveals that four-phonon scattering effect dominates the phonon relaxation processes, since the three-phonon scattering is suppressed due to the significantly large acoustic-optical phonon bandgap in $α$-, $β$- and $γ$-PbP. By considering full EPI effect and high-order phonon scattering processes, the calculated ZT values reach 0.90, 0.24 and 1.25 for $α$-, $β$- and $γ$-PbP, repectively, indicating their promising applications in thermoelectric devices.

cond-mat.mtrl-sci↗

arXiv2022

Caption Feature Space Regularization for Audio Captioning

Audio captioning aims at describing the content of audio clips with human language. Due to the ambiguity of audio, different people may perceive the same audio differently, resulting in caption disparities (i.e., one audio may correlate to several captions with diverse semantics). For that, general audio captioning models achieve the one-to-many training by randomly selecting a correlated caption as the ground truth for each audio. However, it leads to a significant variation in the optimization directions and weakens the model stability. To eliminate this negative effect, in this paper, we propose a two-stage framework for audio captioning: (i) in the first stage, via the contrastive learning, we construct a proxy feature space to reduce the distances between captions correlated to the same audio, and (ii) in the second stage, the proxy feature space is utilized as additional supervision to encourage the model to be optimized in the direction that benefits all the correlated captions. We conducted extensive experiments on two datasets using four commonly used encoder and decoder architectures. Experimental results demonstrate the effectiveness of the proposed method. The code is available at https://github.com/PRIS-CV/Caption-Feature-Space-Regularization.

cs.SD↗

arXiv2022

Intention Adaptive Graph Neural Network for Category-aware Session-based Recommendation

Session-based recommendation (SBR) is proposed to recommend items within short sessions given that user profiles are invisible in various scenarios nowadays, such as e-commerce and short video recommendation. There is a common scenario that user specifies a target category of items as a global filter, however previous SBR settings mainly consider the item sequence and overlook the rich target category information. Therefore, we define a new task called Category-aware Session-Based Recommendation (CSBR), focusing on the above scenario, in which the user-specified category can be efficiently utilized by the recommendation system. To address the challenges of the proposed task, we develop a novel method called Intention Adaptive Graph Neural Network (IAGNN), which takes advantage of relationship between items and their categories to achieve an accurate recommendation result. Specifically, we construct a category-aware graph with both item and category nodes to represent the complex transition information in the session. An intention-adaptive graph neural network on the category-aware graph is utilized to capture user intention by transferring the historical interaction information to the user-specified category domain. Extensive experiments on three real-world datasets are conducted to show our IAGNN outperforms the state-of-the-art baselines in the new task.

cs.IR↗

arXiv2022

Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis

The aspect-based sentiment analysis (ABSA) is a fine-grained task that aims to determine the sentiment polarity towards targeted aspect terms occurring in the sentence. The development of the ABSA task is very much hindered by the lack of annotated data. To tackle this, the prior works have studied the possibility of utilizing the sentiment analysis (SA) datasets to assist in training the ABSA model, primarily via pretraining or multi-task learning. In this article, we follow this line, and for the first time, we manage to apply the Pseudo-Label (PL) method to merge the two homogeneous tasks. While it seems straightforward to use generated pseudo labels to handle this case of label granularity unification for two highly related tasks, we identify its major challenge in this paper and propose a novel framework, dubbed as Dual-granularity Pseudo Labeling (DPL). Further, similar to PL, we regard the DPL as a general framework capable of combining other prior methods in the literature. Through extensive experiments, DPL has achieved state-of-the-art performance on standard benchmarks surpassing the prior work significantly.

cs.CL↗

arXiv2022

Virtual Displacement based Discontinuity Layout Optimization

Discontinuity layout optimization (DLO) is a relatively new upper bound limit analysis method. Compared to classic topology optimization methods, aimed at obtaining the optimum design of a structure by considering its self-weight, building cost or bearing capacity, DLO optimizes the failure pattern of the structure under specific loading conditions and constraints by minimizing the dissipation energy. In this work, we present a modified DLO algorithm that contains all of the advantages of DLO. It is referred to virtual displacement-based discontinuity layout optimization (VDLO). VDLO takes the stress state of a loaded structure as a snapshot and correspondingly provides the optimum failure pattern, which greatly extends the application potential of DLO. Numerical examples indicate the effectiveness and flexibility of VDLO. It is regarded as a highly promising supplemental tool for other numerical methods in element-/node-based frameworks.

cs.CE↗

arXiv2022

Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendation

Predicting the next interaction of a short-term interaction session is a challenging task in session-based recommendation. Almost all existing works rely on item transition patterns, and neglect the impact of user historical sessions while modeling user preference, which often leads to non-personalized recommendation. Additionally, existing personalized session-based recommenders capture user preference only based on the sessions of the current user, but ignore the useful item-transition patterns from other user's historical sessions. To address these issues, we propose a novel Heterogeneous Global Graph Neural Networks (HG-GNN) to exploit the item transitions over all sessions in a subtle manner for better inferring user preference from the current and historical sessions. To effectively exploit the item transitions over all sessions from users, we propose a novel heterogeneous global graph that contains item transitions of sessions, user-item interactions and global co-occurrence items. Moreover, to capture user preference from sessions comprehensively, we propose to learn two levels of user representations from the global graph via two graph augmented preference encoders. Specifically, we design a novel heterogeneous graph neural network (HGNN) on the heterogeneous global graph to learn the long-term user preference and item representations with rich semantics. Based on the HGNN, we propose the Current Preference Encoder and the Historical Preference Encoder to capture the different levels of user preference from the current and historical sessions, respectively. To achieve personalized recommendation, we integrate the representations of the user current preference and historical interests to generate the final user preference representation. Extensive experimental results on three real-world datasets show that our model outperforms other state-of-the-art methods.

cs.IR↗

arXiv2022

Multiple Choice Questions based Multi-Interest Policy Learning for Conversational Recommendation

Conversational recommendation system (CRS) is able to obtain fine-grained and dynamic user preferences based on interactive dialogue. Previous CRS assumes that the user has a clear target item. However, for many users who resort to CRS, they might not have a clear idea about what they really like. Specifically, the user may have a clear single preference for some attribute types (e.g. color) of items, while for other attribute types, the user may have multiple preferences or even no clear preferences, which leads to multiple acceptable attribute instances (e.g. black and red) of one attribute type. Therefore, the users could show their preferences over items under multiple combinations of attribute instances rather than a single item with unique combination of all attribute instances. As a result, we first propose a more realistic CRS learning setting, namely Multi-Interest Multi-round Conversational Recommendation, where users may have multiple interests in attribute instance combinations and accept multiple items with partially overlapped combinations of attribute instances. To effectively cope with the new CRS learning setting, in this paper, we propose a novel learning framework namely, Multi-Choice questions based Multi-Interest Policy Learning . In order to obtain user preferences more efficiently, the agent generates multi-choice questions rather than binary yes/no ones on specific attribute instance. Besides, we propose a union set strategy to select candidate items instead of existing intersection set strategy in order to overcome over-filtering items during the conversation. Finally, we design a Multi-Interest Policy Learning module, which utilizes captured multiple interests of the user to decide next action, either asking attribute instances or recommending items. Extensive experimental results on four datasets verify the superiority of our method for the proposed setting.

cs.IR↗

arXiv2022

Realization of an Error-Correcting Surface Code with Superconducting Qubits

Quantum error correction is a critical technique for transitioning from noisy intermediate-scale quantum (NISQ) devices to fully fledged quantum computers. The surface code, which has a high threshold error rate, is the leading quantum error correction code for two-dimensional grid architecture. So far, the repeated error correction capability of the surface code has not been realized experimentally. Here, we experimentally implement an error-correcting surface code, the distance-3 surface code which consists of 17 qubits, on the \textit{Zuchongzhi} 2.1 superconducting quantum processor. By executing several consecutive error correction cycles, the logical error can be significantly reduced after applying corrections, achieving the repeated error correction of surface code for the first time. This experiment represents a fully functional instance of an error-correcting surface code, providing a key step on the path towards scalable fault-tolerant quantum computing.

quant-ph↗

arXiv2021

Temporal aware Multi-Interest Graph Neural Network For Session-based Recommendation

Session-based recommendation (SBR) is a challenging task, which aims at recommending next items based on anonymous interaction sequences. Despite the superior performance of existing methods for SBR, there are still several limitations: (i) Almost all existing works concentrate on single interest extraction and fail to disentangle multiple interests of user, which easily results in suboptimal representations for SBR. (ii) Furthermore, previous methods also ignore the multi-form temporal information, which is significant signal to obtain current intention for SBR. To address the limitations mentioned above, we propose a novel method, called \emph{Temporal aware Multi-Interest Graph Neural Network} (TMI-GNN) to disentangle multi-interest and yield refined intention representations with the injection of two level temporal information. Specifically, by appending multiple interest nodes, we construct a multi-interest graph for current session, and adopt the GNNs to model the item-item relation to capture adjacent item transitions, item-interest relation to disentangle the multi-interests, and interest-item relation to refine the item representation. Meanwhile, we incorporate item-level time interval signals to guide the item information propagation, and interest-level time distribution information to assist the scattering of interest information. Experiments on three benchmark datasets demonstrate that TMI-GNN outperforms other state-of-the-art methods consistently.

cs.IR↗

arXiv2021

Automatic Configuration for Optimal Communication Scheduling in DNN Training

ByteScheduler partitions and rearranges tensor transmissions to improve the communication efficiency of distributed Deep Neural Network (DNN) training. The configuration of hyper-parameters (i.e., the partition size and the credit size) is critical to the effectiveness of partitioning and rearrangement. Currently, ByteScheduler adopts Bayesian Optimization (BO) to find the optimal configuration for the hyper-parameters beforehand. In practice, however, various runtime factors (e.g., worker node status and network conditions) change over time, making the statically-determined one-shot configuration result suboptimal for real-world DNN training. To address this problem, we present a real-time configuration method (called AutoByte) that automatically and timely searches the optimal hyper-parameters as the training systems dynamically change. AutoByte extends the ByteScheduler framework with a meta-network, which takes the system's runtime statistics as its input and outputs predictions for speedups under specific configurations. Evaluation results on various DNN models show that AutoByte can dynamically tune the hyper-parameters with low resource usage, and deliver up to 33.2\% higher performance than the best static configuration in ByteScheduler.

cs.DC↗

arXiv2021

The Rendering from the Periodic System of the Elements on the stability, elastic, and electronic properties of M2AC phases

MAX phases are nanolaminated ternary materials that combine metallic and ceramic properties. Currently, the A-site elements replacement in traditional ones by later transition-metals opens a door to explore new types of MAX phases. In this work, we performed a systematic first-principle study to explore trends in stability, electronic structure and mechanical properties of 288 compositions of M2AX phases (M=Ti, V, Cr, Zr, Nb, Mo, Hf, Ta, W; A=Al, Si, P, S, Ga, Ge, As, Se, In, Sn, Sb, Te, Tl, Pb, Bi, Mn, Fe, Co, Ni, Cu, Zn, Tc, Ru, Rh, Pd, Ag, Cd, Os, Ir, Pt, Au, Hg; X=C). Such a dataset, combined with the rigid-band model been applied to most transition metal carbides, shows us the fundamental trends in bonding mechanisms and mechanical properties of MAX phases endowed with the periodic arrangements of M/A-site elements. It worth noting, in particular, the M-A d-d interactions of MAX phases uniquely contribute to the elastic constant C33.

cond-mat.mtrl-sci↗