arXiv subjects

Tao Chen

Publications and source records attributed to Tao Chen.

At least 415 records · Page 23Linked to original sources

arXiv2022

Planning Landscape Analysis for Self-Adaptive Systems

To assure performance on the fly, planning is arguably one of the most important steps for self-adaptive systems (SASs), especially when they are highly configurable with a daunting number of adaptation options. However, there has been little understanding of the planning landscape or ways by which it can be analyzed. This inevitably creates barriers to the design of better and tailored planners for SASs. In this paper, we showcase how the planning landscapes of SASs can be quantified and reasoned, particularly with respect to the different environments. By studying four diverse real-world SASs and 14 environments, we found that (1) the SAS planning landscapes often provide strong guidance to the planner, but their ruggedness and multi-modality can be the major obstacle; (2) the extents of guidance and number of global/local optima are sensitive to the changing environment, but not the ruggedness of the surface; (3) the local optima are often closer to the global optimum than other random points; and (4) there are considerable (and useful) overlaps on the global/local optima between landscapes under different environments. We then discuss the potential implications to the future work of planner designs for SASs.

cs.SE↗

arXiv2022

Nonparametric Adaptive Robust Control Under Model Uncertainty

We consider a discrete time stochastic Markovian control problem under model uncertainty. Such uncertainty not only comes from the fact that the true probability law of the underlying stochastic process is unknown, but the parametric family of probability distributions which the true law belongs to is also unknown. We propose a nonparametric adaptive robust control methodology to deal with such problem. Our approach hinges on the following building concepts: first, using the adaptive robust paradigm to incorporate online learning and uncertainty reduction into the robust control problem; second, learning the unknown probability law through the empirical distribution, and representing uncertainty reduction in terms of a sequence of Wasserstein balls around the empirical distribution; third, using Lagrangian duality to convert the optimization over Wasserstein balls to a scalar optimization problem, and adopting a machine learning technique to achieve efficient computation of the optimal control. We illustrate our methodology by considering a utility maximization problem. Numerical comparisons show that the nonparametric adaptive robust control approach is preferable to the traditional robust frameworks.

math.OC↗

arXiv2022

Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection

Unsupervised domain adaptive object detection aims to adapt a well-trained detector from its original source domain with rich labeled data to a new target domain with unlabeled data. Recently, mainstream approaches perform this task through adversarial learning, yet still suffer from two limitations. First, they mainly align marginal distribution by unsupervised cross-domain feature matching, and ignore each feature's categorical and positional information that can be exploited for conditional alignment; Second, they treat all classes as equally important for transferring cross-domain knowledge and ignore that different classes usually have different transferability. In this paper, we propose a joint adaptive detection framework (JADF) to address the above challenges. First, an end-to-end joint adversarial adaptation framework for object detection is proposed, which aligns both marginal and conditional distributions between domains without introducing any extra hyperparameter. Next, to consider the transferability of each object class, a metric for class-wise transferability assessment is proposed, which is incorporated into the JADF objective for domain adaptation. Further, an extended study from unsupervised domain adaptation (UDA) to unsupervised few-shot domain adaptation (UFDA) is conducted, where only a few unlabeled training images are available in unlabeled target domain. Extensive experiments validate that JADF is effective in both the UDA and UFDA settings, achieving significant performance gains over existing state-of-the-art cross-domain detection methods.

cs.CV↗

arXiv2022

$β$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search

Neural Architecture Search~(NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural networks automatically. Among them, differential NAS approaches such as DARTS, have gained popularity for the search efficiency. However, they suffer from two main issues, the weak robustness to the performance collapse and the poor generalization ability of the searched architectures. To solve these two problems, a simple-but-efficient regularization method, termed as Beta-Decay, is proposed to regularize the DARTS-based NAS searching process. Specifically, Beta-Decay regularization can impose constraints to keep the value and variance of activated architecture parameters from too large. Furthermore, we provide in-depth theoretical analysis on how it works and why it works. Experimental results on NAS-Bench-201 show that our proposed method can help to stabilize the searching process and makes the searched network more transferable across different datasets. In addition, our search scheme shows an outstanding property of being less dependent on training time and data. Comprehensive experiments on a variety of search spaces and datasets validate the effectiveness of the proposed method.

cs.LG↗

arXiv2022

Composite Short-path Nonadiabatic Holonomic Quantum Gates

Nonadiabatic holonomic quantum computation (NHQC) has attracted significant attention due to its fast evolution and the geometric nature induced resilience to local noises. However, its long operation time and complex physical implementation make it hard to surpass the dynamical scheme, and thus hindering its wide application. Here, we present to implement NHQC with the shortest path under some conditions, through the inverse Hamiltonian engineering technique, which posseses higher fidelity and stronger robustness than previous NHQC schemes. Meanwhile, the gate performance in our scheme can be further improved by using the proposed composite dynamical decoupling pulses, which can efficiently improve both the gate fidelity and robustness, making our scheme outperform the optimal dynamical scheme in certain parameters range. Remarkably, our scheme can be readily implemented with Rydberg atoms, and a simplified implementation of the controlled-not gate in the Rydberg blockade regime can be achieved. Therefore, our scheme represents a promising progress towards future fault-tolerant quantum computation in atomic systems.

quant-ph↗

arXiv2022

Curriculum-style Local-to-global Adaptation for Cross-domain Remote Sensing Image Segmentation

Although domain adaptation has been extensively studied in natural image-based segmentation task, the research on cross-domain segmentation for very high resolution (VHR) remote sensing images (RSIs) still remains underexplored. The VHR RSIs-based cross-domain segmentation mainly faces two critical challenges: 1) Large area land covers with many diverse object categories bring severe local patch-level data distribution deviations, thus yielding different adaptation difficulties for different local patches; 2) Different VHR sensor types or dynamically changing modes cause the VHR images to go through intensive data distribution differences even for the same geographical location, resulting in different global feature-level domain gap. To address these challenges, we propose a curriculum-style local-to-global cross-domain adaptation framework for the segmentation of VHR RSIs. The proposed curriculum-style adaptation performs the adaptation process in an easy-to-hard way according to the adaptation difficulties that can be obtained using an entropy-based score for each patch of the target domain, and thus well aligns the local patches in a domain image. The proposed local-to-global adaptation performs the feature alignment process from the locally semantic to globally structural feature discrepancies, and consists of a semantic-level domain classifier and an entropy-level domain classifier that can reduce the above cross-domain feature discrepancies. Extensive experiments have been conducted in various cross-domain scenarios, including geographic location variations and imaging mode variations, and the experimental results demonstrate that the proposed method can significantly boost the domain adaptability of segmentation networks for VHR RSIs. Our code is available at: https://github.com/BOBrown/CCDA_LGFA.

cs.CV↗

arXiv2022

The Weights can be Harmful: Pareto Search versus Weighted Search in Multi-Objective Search-Based Software Engineering

In presence of multiple objectives to be optimized in Search-Based Software Engineering (SBSE), Pareto search has been commonly adopted. It searches for a good approximation of the problem's Pareto optimal solutions, from which the stakeholders choose the most preferred solution according to their preferences. However, when clear preferences of the stakeholders (e.g., a set of weights which reflect relative importance between objectives) are available prior to the search, weighted search is believed to be the first choice since it simplifies the search via converting the original multi-objective problem into a single-objective one and enable the search to focus on what only the stakeholders are interested in. This paper questions such a "weighted search first" belief. We show that the weights can, in fact, be harmful to the search process even in the presence of clear preferences. Specifically, we conduct a large scale empirical study which consists of 38 systems/projects from three representative SBSE problems, together with two types of search budget and nine sets of weights, leading to 604 cases of comparisons. Our key finding is that weighted search reaches a certain level of solution quality by consuming relatively less resources at the early stage of the search; however, Pareto search is at the majority of the time (up to 77% of the cases) significantly better than its weighted counterpart, as long as we allow a sufficient, but not unrealistic search budget. This, together with other findings and actionable suggestions in the paper, allows us to codify pragmatic and comprehensive guidance on choosing weighted and Pareto search for SBSE under the circumstance that clear preferences are available. All code and data can be accessed at: https://github.com/ideas-labo/pareto-vs-weight-for-sbse.

cs.SE↗

arXiv2022

Out-of-Domain Semantics to the Rescue! Zero-Shot Hybrid Retrieval Models

The pre-trained language model (eg, BERT) based deep retrieval models achieved superior performance over lexical retrieval models (eg, BM25) in many passage retrieval tasks. However, limited work has been done to generalize a deep retrieval model to other tasks and domains. In this work, we carefully select five datasets, including two in-domain datasets and three out-of-domain datasets with different levels of domain shift, and study the generalization of a deep model in a zero-shot setting. Our findings show that the performance of a deep retrieval model is significantly deteriorated when the target domain is very different from the source domain that the model was trained on. On the contrary, lexical models are more robust across domains. We thus propose a simple yet effective framework to integrate lexical and deep retrieval models. Our experiments demonstrate that these two models are complementary, even when the deep model is weaker in the out-of-domain setting. The hybrid model obtains an average of 20.4% relative gain over the deep retrieval model, and an average of 9.54% over the lexical model in three out-of-domain datasets.

cs.IR↗

arXiv2022

Lifelong Dynamic Optimization for Self-Adaptive Systems: Fact or Fiction?

When faced with changing environment, highly configurable software systems need to dynamically search for promising adaptation plan that keeps the best possible performance, e.g., higher throughput or smaller latency -- a typical planning problem for self-adaptive systems (SASs). However, given the rugged and complex search landscape with multiple local optima, such a SAS planning is challenging especially in dynamic environments. In this paper, we propose LiDOS, a lifelong dynamic optimization framework for SAS planning. What makes LiDOS unique is that to handle the "dynamic", we formulate the SAS planning as a multi-modal optimization problem, aiming to preserve the useful information for better dealing with the local optima issue under dynamic environment changes. This differs from existing planners in that the "dynamic" is not explicitly handled during the search process in planning. As such, the search and planning in LiDOS run continuously over the lifetime of SAS, terminating only when it is taken offline or the search space has been covered under an environment. Experimental results on three real-world SASs show that the concept of explicitly handling dynamic as part of the search in the SAS planning is effective, as LiDOS outperforms its stationary counterpart overall with up to 10x improvement. It also achieves better results in general over state-of-the-art planners and with 1.4x to 10x speedup on generating promising adaptation plans.

cs.SE↗

arXiv2022

Asymmetric topological pumping in nonparaxial photonics

Topological photonics was initially inspired by the quantum-optical analogy between the Schrödinger equation for an electron wavefunction and the paraxial equation for a light beam. Here, we reveal an unexpected phenomenon in topological pumping observed in arrays of nonparaxial optical waveguides where the quantum-optical analogy becomes invalid. We predict theoretically and demonstrate experimentally an asymmetric topological pumping when the injected field transfers from one side of the waveguide array to the other side whereas the reverse process is unexpectedly forbidden. Our finding could open an avenue for exploring topological photonics that enables nontrivial topological phenomena and designs in photonics driven by nonparaxiality.

physics.optics↗

arXiv2022

CO2Sum:Contrastive Learning for Factual-Consistent Abstractive Summarization

Generating factual-consistent summaries is a challenging task for abstractive summarization. Previous works mainly encode factual information or perform post-correct/rank after decoding. In this paper, we provide a factual-consistent solution from the perspective of contrastive learning, which is a natural extension of previous works. We propose CO2Sum (Contrastive for Consistency), a contrastive learning scheme that can be easily applied on sequence-to-sequence models for factual-consistent abstractive summarization, proving that the model can be fact-aware without modifying the architecture. CO2Sum applies contrastive learning on the encoder, which can help the model be aware of the factual information contained in the input article, or performs contrastive learning on the decoder, which makes the model to generate factual-correct output summary. What's more, these two schemes are orthogonal and can be combined to further improve faithfulness. Comprehensive experiments on public benchmarks demonstrate that CO2Sum improves the faithfulness on large pre-trained language models and reaches competitive results compared to other strong factual-consistent summarization baselines.

cs.CL↗

arXiv2021

A new class of differential quasivariational inequalities with an application to a quasistatic viscoelastic frictional contact problem

The overarching goal of this paper is to introduce and investigate a new nonlinear system driven by a nonlinear differential equation, a history-dependent quasivariational inequality, and a parabolic variational inequality in Banach spaces. Such a system can be used to model quasistatic frictional contact problems for viscoelastic materials with long memory, damage and wear. By using the Banach fixed point theorem, we prove an existence and uniqueness theorem of solution for such a system under some mild conditions. As a novel application, we obtain a unique solvability of a quasistatic viscoelastic frictional contact problem with long memory, damage and wear.

math.OC↗

arXiv2021

Neural Hierarchical Factorization Machines for User's Event Sequence Analysis

Many prediction tasks of real-world applications need to model multi-order feature interactions in user's event sequence for better detection performance. However, existing popular solutions usually suffer two key issues: 1) only focusing on feature interactions and failing to capture the sequence influence; 2) only focusing on sequence information, but ignoring internal feature relations of each event, thus failing to extract a better event representation. In this paper, we consider a two-level structure for capturing the hierarchical information over user's event sequence: 1) learning effective feature interactions based event representation; 2) modeling the sequence representation of user's historical events. Experimental results on both industrial and public datasets clearly demonstrate that our model achieves significantly better performance compared with state-of-the-art baselines.

cs.LG↗

arXiv2021

Feature-context driven Federated Meta-Learning for Rare Disease Prediction

Millions of patients suffer from rare diseases around the world. However, the samples of rare diseases are much smaller than those of common diseases. In addition, due to the sensitivity of medical data, hospitals are usually reluctant to share patient information for data fusion citing privacy concerns. These challenges make it difficult for traditional AI models to extract rare disease features for the purpose of disease prediction. In this paper, we overcome this limitation by proposing a novel approach for rare disease prediction based on federated meta-learning. To improve the prediction accuracy of rare diseases, we design an attention-based meta-learning (ATML) approach which dynamically adjusts the attention to different tasks according to the measured training effect of base learners. Additionally, a dynamic-weight based fusion strategy is proposed to further improve the accuracy of federated learning, which dynamically selects clients based on the accuracy of each local model. Experiments show that with as few as five shots, our approach out-performs the original federated meta-learning algorithm in accuracy and speed. Compared with each hospital's local model, the proposed model's average prediction accuracy increased by 13.28%.

cs.LG↗

arXiv2021

Error-Tolerant Geometric Quantum Control for Logical Qubits with Minimal Resource

Geometric quantum computation offers a practical strategy toward robust quantum computation due to its inherently error tolerance. However, the rigorous geometric conditions lead to complex and/or error-disturbed quantum controls, especially for logical qubits that involve more physical qubits, whose error tolerance is effective in principle though, their experimental demonstration is still demanding. Thus, how to best simplify the needed control and manifest its full advantage has become the key to widespread applications of geometric quantum computation. Here we propose a new fast and robust geometric scheme, with the decoherence-free-subspace encoding, and present its physical implementation on superconducting quantum circuits, where we only utilize the experimentally demonstrated parametrically tunable coupling to achieve high-fidelity geometric control over logical qubits. Numerical simulation verifies that it can efficiently combine the error tolerance from both the geometric phase and logical-qubit encoding, displaying our gate-performance superiority over the conventional dynamical one without encoding, in terms of both gate fidelity and robustness. Therefore, our scheme can consolidate both error suppression methods for logical-qubit control, which sheds light on the future large-scale quantum computation.

quant-ph↗

arXiv2021

Deep Feature Mining via Attention-based BiLSTM-GCN for Human Motor Imagery Recognition

Recognition accuracy and response time are both critically essential ahead of building practical electroencephalography (EEG) based brain-computer interface (BCI). Recent approaches, however, have either compromised in the classification accuracy or responding time. This paper presents a novel deep learning approach designed towards remarkably accurate and responsive motor imagery (MI) recognition based on scalp EEG. Bidirectional Long Short-term Memory (BiLSTM) with the Attention mechanism manages to derive relevant features from raw EEG signals. The connected graph convolutional neural network (GCN) promotes the decoding performance by cooperating with the topological structure of features, which are estimated from the overall data. The 0.4-second detection framework has shown effective and efficient prediction based on individual and group-wise training, with 98.81% and 94.64% accuracy, respectively, which outperformed all the state-of-the-art studies. The introduced deep feature mining approach can precisely recognize human motion intents from raw EEG signals, which paves the road to translate the EEG based MI recognition to practical BCI systems.

eess.SP↗

arXiv2021

A Gross-Pitaevskii-equation description of the momentum-state lattice: roles of the trap and many-body interactions

We report a theoretical description of the synthetic momentum-state lattices with a 3D Gross-Pitaevskii equation (GPE), where both the external trap potential and the mean-field spatial-density-dependent many-body interactions are naturally included and exactly treated. The GPE models exhibit better performance than the tight-binding model to depict the experimental observations. Since the trap modifies the dispersion relation for free particles and shapes the spatial density distribution that leads to inhomogeneous interactions, decoherences (damping oscillation) appear even for a short-time evolution. Our parametric calculations for the two-state oscillation suggest that we should work with a relatively shallow trap in the weakly interacting regime, especially when the long-term dynamics are concerned. The impact of the mean-field interaction, i.e., the self-trapping behavior, on the transport dynamics and the topological phase transition in a finite multiple-state lattice chain is also specifically investigated. Such an accurate treatment of the inhomogeneous interactions allows for further investigations on the interplay with disorder, the pair correlation dynamics, and the thermalization process in momentum space.

cond-mat.quant-gas↗

arXiv2021

Where have all the interstellar silicon carbides gone?

The detection of the 11.3-micron emission feature characteristic of the Si--C stretch in carbon-rich evolved stars reveals that silicon carbide (SiC) dust grains are condensed in the outflows of carbon stars. SiC dust could be a significant constituent of interstellar dust since it is generally believed that carbon stars inject a considerable amount of dust into the interstellar medium (ISM). The presence of SiC dust in the ISM is also supported by the identification of presolar SiC grains of stellar origin in primitive meteorites. However, the 11.3-micron absorption feature of SiC has never been seen in the ISM and oxidative destruction of SiC is often invoked. In this work we quantitatively explore the destruction of interstellar SiC dust through oxidation based on molecular dynamics simulations and density functional theory calculations. We find that the reaction of an oxygen atom with SiC molecules and clusters is exothermic and could cause CO-loss. Nevertheless, even if this is extrapolable to bulk SiC dust, the destruction rate of SiC dust through oxidation could still be considerably smaller than the (currently believed) injection rate from carbon stars. Therefore, the lack of the 11.3-micron absorption feature of SiC dust in the ISM remains a mystery. A possible solution may lie in the currently believed stellar injection rate of SiC (which may have been overestimated) and/or the size of SiC dust (which may actually be considerably smaller than submicron in size).

astro-ph.GA↗