arXiv subjects

Gong Cheng

Publications and source records attributed to Gong Cheng.

At least 73 records · Page 4Linked to original sources

arXiv2022

Large $N$ Matrix Quantum Mechanics as a Quantum Memory

In this paper, we explore the possibility of building a quantum memory that is robust to thermal noise using large $N$ matrix quantum mechanics models. First, we investigate the gauged $SU(N)$ matrix harmonic oscillator and different ways to encode quantum information in it. By calculating the mutual information between the system and a reference which purifies the encoded information, we identify a transition temperature, $T_c$, below which the encoded quantum information is protected from thermal noise for a memory time scaling as $N^2$. Conversely, for temperatures higher than $T_c$, the information is quickly destroyed by thermal noise. Second, we relax the requirement of gauge invariance and study a matrix harmonic oscillator model with only global symmetry. Finally, we further relax even the symmetry requirement and propose a model that consists of a large number $N^2$ of qubits, with interactions derived from an approximate $SU(N)$ symmetry. In both ungauged models, we find that the effects of gauging can be mimicked using an energy penalty to give a similar result for the memory time. The final qubit model also has the potential to be realized in the laboratory.

quant-ph↗

arXiv2022

Knowledge Base Question Answering: A Semantic Parsing Perspective

Recent advances in deep learning have greatly propelled the research on semantic parsing. Improvement has since been made in many downstream tasks, including natural language interface to web APIs, text-to-SQL generation, among others. However, despite the close connection shared with these tasks, research on question answering over knowledge bases (KBQA) has comparatively been progressing slowly. We identify and attribute this to two unique challenges of KBQA, schema-level complexity and fact-level complexity. In this survey, we situate KBQA in the broader literature of semantic parsing and give a comprehensive account of how existing KBQA approaches attempt to address the unique challenges. Regardless of the unique challenges, we argue that we can still take much inspiration from the literature of semantic parsing, which has been overlooked by existing research on KBQA. Based on our discussion, we can better understand the bottleneck of current KBQA research and shed light on promising directions for KBQA to keep up with the literature of semantic parsing, particularly in the era of pre-trained language models.

cs.CL↗

arXiv2022

Query-based Industrial Analytics over Knowledge Graphs with Ontology Reshaping

Industrial analytics that includes among others equipment diagnosis and anomaly detection heavily relies on integration of heterogeneous production data. Knowledge Graphs (KGs) as the data format and ontologies as the unified data schemata are a prominent solution that offers high quality data integration and a convenient and standardised way to exchange data and to layer analytical applications over it. However, poor design of ontologies of high degree of mismatch between them and industrial data naturally lead to KGs of low quality that impede the adoption and scalability of industrial analytics. Indeed, such KGs substantially increase the training time of writing queries for users, consume high volume of storage for redundant information, and are hard to maintain and update. To address this problem we propose an ontology reshaping approach to transform ontologies into KG schemata that better reflect the underlying data and thus help to construct better KGs. In this poster we present a preliminary discussion of our on-going research, evaluate our approach with a rich set of SPARQL queries on real-world industry data at Bosch and discuss our findings.

cs.DB↗

arXiv2022

Towards Ontology Reshaping for KG Generation with User-in-the-Loop: Applied to Bosch Welding

Knowledge graphs (KG) are used in a wide range of applications. The automation of KG generation is very desired due to the data volume and variety in industries. One important approach of KG generation is to map the raw data to a given KG schema, namely a domain ontology, and construct the entities and properties according to the ontology. However, the automatic generation of such ontology is demanding and existing solutions are often not satisfactory. An important challenge is a trade-off between two principles of ontology engineering: knowledge-orientation and data-orientation. The former one prescribes that an ontology should model the general knowledge of a domain, while the latter one emphasises on reflecting the data specificities to ensure good usability. We address this challenge by our method of ontology reshaping, which automates the process of converting a given domain ontology to a smaller ontology that serves as the KG schema. The domain ontology can be designed to be knowledge-oriented and the KG schema covers the data specificities. In addition, our approach allows the option of including user preferences in the loop. We demonstrate our on-going research on ontology reshaping and present an evaluation using real industrial data, with promising results.

cs.AI↗

arXiv2022

Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation

Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community. Existing approaches typically follow the prototype learning paradigm to perform meta-inference, which fails to fully exploit the underlying information from support image-mask pairs, resulting in various segmentation failures, e.g., incomplete objects, ambiguous boundaries, and distractor activation. To this end, we propose a simple yet versatile framework in the spirit of divide-and-conquer. Specifically, a novel self-reasoning scheme is first implemented on the annotated support image, and then the coarse segmentation mask is divided into multiple regions with different properties. Leveraging effective masked average pooling operations, a series of support-induced proxies are thus derived, each playing a specific role in conquering the above challenges. Moreover, we devise a unique parallel decoder structure that integrates proxies with similar attributes to boost the discrimination power. Our proposed approach, named divide-and-conquer proxies (DCP), allows for the development of appropriate and reliable information as a guide at the "episode" level, not just about the object cues themselves. Extensive experiments on PASCAL-5i and COCO-20i demonstrate the superiority of DCP over conventional prototype-based approaches (up to 5~10% on average), which also establishes a new state-of-the-art. Code is available at github.com/chunbolang/DCP.

cs.CV↗

arXiv2022

Clues Before Answers: Generation-Enhanced Multiple-Choice QA

A trending paradigm for multiple-choice question answering (MCQA) is using a text-to-text framework. By unifying data in different tasks into a single text-to-text format, it trains a generative encoder-decoder model which is both powerful and universal. However, a side effect of twisting a generation target to fit the classification nature of MCQA is the under-utilization of the decoder and the knowledge that can be decoded. To exploit the generation capability and underlying knowledge of a pre-trained encoder-decoder model, in this paper, we propose a generation-enhanced MCQA model named GenMC. It generates a clue from the question and then leverages the clue to enhance a reader for MCQA. It outperforms text-to-text models on multiple MCQA datasets.

cs.CL↗

arXiv2022

Anchor-free Oriented Proposal Generator for Object Detection

Oriented object detection is a practical and challenging task in remote sensing image interpretation. Nowadays, oriented detectors mostly use horizontal boxes as intermedium to derive oriented boxes from them. However, the horizontal boxes are inclined to get small Intersection-over-Unions (IoUs) with ground truths, which may have some undesirable effects, such as introducing redundant noise, mismatching with ground truths, detracting from the robustness of detectors, etc. In this paper, we propose a novel Anchor-free Oriented Proposal Generator (AOPG) that abandons horizontal box-related operations from the network architecture. AOPG first produces coarse oriented boxes by a Coarse Location Module (CLM) in an anchor-free manner and then refines them into high-quality oriented proposals. After AOPG, we apply a Fast R-CNN head to produce the final detection results. Furthermore, the shortage of large-scale datasets is also a hindrance to the development of oriented object detection. To alleviate the data insufficiency, we release a new dataset on the basis of our DIOR dataset and name it DIOR-R. Massive experiments demonstrate the effectiveness of AOPG. Particularly, without bells and whistles, we achieve the accuracy of 64.41%, 75.24% and 96.22% mAP on the DIOR-R, DOTA and HRSC2016 datasets respectively. Code and models are available at https://github.com/jbwang1997/AOPG.

cs.CV↗

arXiv2022

Learning What Not to Segment: A New Perspective on Few-Shot Segmentation

Recently few-shot segmentation (FSS) has been extensively developed. Most previous works strive to achieve generalization through the meta-learning framework derived from classification tasks; however, the trained models are biased towards the seen classes instead of being ideally class-agnostic, thus hindering the recognition of new concepts. This paper proposes a fresh and straightforward insight to alleviate the problem. Specifically, we apply an additional branch (base learner) to the conventional FSS model (meta learner) to explicitly identify the targets of base classes, i.e., the regions that do not need to be segmented. Then, the coarse results output by these two learners in parallel are adaptively integrated to yield precise segmentation prediction. Considering the sensitivity of meta learner, we further introduce an adjustment factor to estimate the scene differences between the input image pairs for facilitating the model ensemble forecasting. The substantial performance gains on PASCAL-5i and COCO-20i verify the effectiveness, and surprisingly, our versatile scheme sets a new state-of-the-art even with two plain learners. Moreover, in light of the unique nature of the proposed approach, we also extend it to a more realistic but challenging setting, i.e., generalized FSS, where the pixels of both base and novel classes are required to be determined. The source code is available at github.com/chunbolang/BAM.

cs.CV↗

arXiv2022

Ensemble Recognition in Reproducing Kernel Hilbert Spaces through Aggregated Measurements

In this paper, we study the problem of learning dynamical properties of ensemble systems from their collective behaviors using statistical approaches in reproducing kernel Hilbert space (RKHS). Specifically, we provide a framework to identify and cluster multiple ensemble systems through computing the maximum mean discrepancy (MMD) between their aggregated measurements in an RKHS, without any prior knowledge of the system dynamics of ensembles. Then, leveraging the gradient flow of the newly proposed notion of aggregated Markov parameters, we present a systematic framework to recognize and identify an ensemble systems using their linear approximations. Finally, we demonstrate that the proposed approaches can be extended to cluster multiple unknown ensembles in RKHS using their aggregated measurements. Numerical experiments show that our approach is reliable and robust to ensembles with different types of system dynamics.

cs.LG↗

arXiv2022

AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension

Recent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text. Conventional neural models are insufficient for logical reasoning, while symbolic reasoners cannot directly apply to text. To meet the challenge, we present a neural-symbolic approach which, to predict an answer, passes messages over a graph representing logical relations between text units. It incorporates an adaptive logic graph network (AdaLoGN) which adaptively infers logical relations to extend the graph and, essentially, realizes mutual and iterative reinforcement between neural and symbolic reasoning. We also implement a novel subgraph-to-node message passing mechanism to enhance context-option interaction for answering multiple-choice questions. Our approach shows promising results on ReClor and LogiQA.

cs.CL↗

arXiv2022

Bilinear Systems Induced by Proper Lie Group Actions

In the study of induced bilinear systems, the classical Lie algebra rank condition (LARC) is known to be impractical since it requires computing the rank everywhere. On the other hand, the transitive Lie algebra condition, while more commonly used, relies on the classification of transitive Lie algebras, which is elusive except for few simple geometric objects such as spheres. We prove in this note that for bilinear systems induced by proper Lie group actions, the underlying Lie algebra is closely related to the orbits of the group action. Knowing the pattern of the Lie algebra rank over the manifold, we show that the LARC can be relaxed so that it suffices to check the rank at an arbitrary single point. Moreover, it removes the necessity for classifying transitive Lie algebras. Finally, this relaxed rank condition also leads to a characterization of controllable submanifolds by orbits.

eess.SY↗

arXiv2022

Adaptive neighborhood Metric learning

In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining. Since the inseparable samples are often mixed with hard samples, current informative sample mining strategies used to deal with inseparable problem may bring up some side-effects, such as instability of objective function, etc. To alleviate this problem, we propose a novel distance metric learning algorithm, named adaptive neighborhood metric learning (ANML). In ANML, we design two thresholds to adaptively identify the inseparable similar and dissimilar samples in the training procedure, thus inseparable sample removing and metric parameter learning are implemented in the same procedure. Due to the non-continuity of the proposed ANML, we develop an ingenious function, named \emph{log-exp mean function} to construct a continuous formulation to surrogate it, which can be efficiently solved by the gradient descent method. Similar to Triplet loss, ANML can be used to learn both the linear and deep embeddings. By analyzing the proposed method, we find it has some interesting properties. For example, when ANML is used to learn the linear embedding, current famous metric learning algorithms such as the large margin nearest neighbor (LMNN) and neighbourhood components analysis (NCA) are the special cases of the proposed ANML by setting the parameters different values. When it is used to learn deep features, the state-of-the-art deep metric learning algorithms such as Triplet loss, Lifted structure loss, and Multi-similarity loss become the special cases of ANML. Furthermore, the \emph{log-exp mean function} proposed in our method gives a new perspective to review the deep metric learning methods such as Prox-NCA and N-pairs loss. At last, promising experimental results demonstrate the effectiveness of the proposed method.

cs.LG↗

arXiv2022

Aerial Scene Parsing: From Tile-level Scene Classification to Pixel-wise Semantic Labeling

Given an aerial image, aerial scene parsing (ASP) targets to interpret the semantic structure of the image content, e.g., by assigning a semantic label to every pixel of the image. With the popularization of data-driven methods, the past decades have witnessed promising progress on ASP by approaching the problem with the schemes of tile-level scene classification or segmentation-based image analysis, when using high-resolution aerial images. However, the former scheme often produces results with tile-wise boundaries, while the latter one needs to handle the complex modeling process from pixels to semantics, which often requires large-scale and well-annotated image samples with pixel-wise semantic labels. In this paper, we address these issues in ASP, with perspectives from tile-level scene classification to pixel-wise semantic labeling. Specifically, we first revisit aerial image interpretation by a literature review. We then present a large-scale scene classification dataset that contains one million aerial images termed Million-AID. With the presented dataset, we also report benchmarking experiments using classical convolutional neural networks (CNNs). Finally, we perform ASP by unifying the tile-level scene classification and object-based image analysis to achieve pixel-wise semantic labeling. Intensive experiments show that Million-AID is a challenging yet useful dataset, which can serve as a benchmark for evaluating newly developed algorithms. When transferring knowledge from Million-AID, fine-tuning CNN models pretrained on Million-AID perform consistently better than those pretrained ImageNet for aerial scene classification. Moreover, our designed hierarchical multi-task learning method achieves the state-of-the-art pixel-wise classification on the challenging GID, bridging the tile-level scene classification toward pixel-wise semantic labeling for aerial image interpretation.

cs.CV↗

arXiv2021

On Uniform Ensemble Controllability of Diagonalizable Linear Ensemble Systems

In this paper, we study uniform ensemble controllability (UEC) of linear ensemble systems defined in an infinite-dimensional space through finite-dimensional settings. Specifically, with the help of the Stone-Weierstrass theorem for modules, we provide an algebraic framework for examining UEC of linear ensemble systems with diagonalizable drift vector fields through checking the controllability of finite-dimensional subsystems in the ensemble. The new framework renders a novel concept of ensemble controllability matrix, which rank-condition serves as a sufficient and necessary condition for UEC of linear ensembles. We provide several examples demonstrating that the proposed approach well-encompasses existing results and analyzes UEC of linear ensembles not addressed by literature.

math.OC↗

arXiv2021

When Retriever-Reader Meets Scenario-Based Multiple-Choice Questions

Scenario-based question answering (SQA) requires retrieving and reading paragraphs from a large corpus to answer a question which is contextualized by a long scenario description. Since a scenario contains both keyphrases for retrieval and much noise, retrieval for SQA is extremely difficult. Moreover, it can hardly be supervised due to the lack of relevance labels of paragraphs for SQA. To meet the challenge, in this paper we propose a joint retriever-reader model called JEEVES where the retriever is implicitly supervised only using QA labels via a novel word weighting mechanism. JEEVES significantly outperforms a variety of strong baselines on multiple-choice questions in three SQA datasets.

cs.CL↗

arXiv2021

Oriented R-CNN for Object Detection

Current state-of-the-art two-stage detectors generate oriented proposals through time-consuming schemes. This diminishes the detectors' speed, thereby becoming the computational bottleneck in advanced oriented object detection systems. This work proposes an effective and simple oriented object detection framework, termed Oriented R-CNN, which is a general two-stage oriented detector with promising accuracy and efficiency. To be specific, in the first stage, we propose an oriented Region Proposal Network (oriented RPN) that directly generates high-quality oriented proposals in a nearly cost-free manner. The second stage is oriented R-CNN head for refining oriented Regions of Interest (oriented RoIs) and recognizing them. Without tricks, oriented R-CNN with ResNet50 achieves state-of-the-art detection accuracy on two commonly-used datasets for oriented object detection including DOTA (75.87% mAP) and HRSC2016 (96.50% mAP), while having a speed of 15.1 FPS with the image size of 1024$\times$1024 on a single RTX 2080Ti. We hope our work could inspire rethinking the design of oriented detectors and serve as a baseline for oriented object detection. Code is available at https://github.com/jbwang1997/OBBDetection.

cs.CV↗

arXiv2021

Cosmological test of an extended quintessence model

We investigate the cosmological observational test of the extended quintessence model, i.e. a scalar-tensor gravity model with a scalar field potential serving as dark energy, by using the Planck 2018 cosmic microwave background (CMB) data, together with the baryon acoustic oscillations (BAO) and redshift-space distortion (RSD) data. As an example, we consider the model with a Brans-Dicke kinetic term $\frac{ω(ϕ)}ϕ ϕ_{;μ} ϕ^{;μ} $ and a quadratic scalar potential $V (ϕ) = A + B (ϕ- ϕ_0) + \frac{C}{2} (ϕ- ϕ_0)^2$, which reduces to general relativity (GR) in the limit $ω(ϕ) \to \infty$, and the cosmological constant in the limit $B=C=0$. In such a model the scalar field typically rolls down the potential and oscillates around the minimum of $V (ϕ)$. We find that the model parameter estimate for the CMB+BAO+RSD data set is given by $\lg α= -3.6 _{-0.54}^{+0.66}~ (68\%)$, corresponding to $ 3.8 \times 10^5 < ω_0 < 9.5 \times 10^7~ (68\%)$, and $\lg C = 4.9 \pm 1.4~ (68\%) $. However, the GR $Λ$CDM model can fit the data almost as good as this extended quintessence model, and is favored by the Akaike information criterion (AIC). The variation of the gravitational constant since the epoch of Recombination is constrained to be $0.97 < G_{\rm rec}/G_0 < 1.03~ (1 σ)$. In light of recent report that the CMB data favors a closed universe, we consider the case with non-flat geometry in our fit, and find that the mean value of $Ω_k$ shifts a little bit from $-0.049$ to $-0.036$, and the parameters in our model are not degenerate with $Ω_k$.

astro-ph.CO↗

arXiv2021

Entity Summarization: State of the Art and Future Challenges

The increasing availability of semantic data has substantially enhanced Web applications. Semantic data such as RDF data is commonly represented as entity-property-value triples. The magnitude of semantic data, in particular the large number of triples describing an entity, could overload users with excessive amounts of information. This has motivated fruitful research on automated generation of summaries for entity descriptions to satisfy users' information needs efficiently and effectively. We focus on this prominent topic of entity summarization, and our research objective is to present the first comprehensive survey of entity summarization research. Rather than separately reviewing each method, our contributions include (1) identifying and classifying technical features of existing methods to form a high-level overview, (2) identifying and classifying frameworks for combining multiple technical features adopted by existing methods, (3) collecting known benchmarks for intrinsic evaluation and efforts for extrinsic evaluation, and (4) suggesting research directions for future work. By investigating the literature, we synthesized two hierarchies of techniques. The first hierarchy categories generic technical features into several perspectives: frequency and centrality, informativeness, and diversity and coverage. In the second hierarchy we present domain-specific and task-specific technical features, including the use of domain knowledge, context awareness, and personalization. Our review demonstrated that existing methods are mainly unsupervised and they combine multiple technical features using various frameworks: random surfer models, similarity-based grouping, MMR-like re-ranking, or combinatorial optimization. We also found a few deep learning based methods in recent research.

cs.IR↗