arXiv subjects

Rui Ding

Publications and source records attributed to Rui Ding.

69 records · Page 4Linked to original sources

arXiv2023

Demonstration of InsightPilot: An LLM-Empowered Automated Data Exploration System

Exploring data is crucial in data analysis, as it helps users understand and interpret the data more effectively. However, performing effective data exploration requires in-depth knowledge of the dataset and expertise in data analysis techniques. Not being familiar with either can create obstacles that make the process time-consuming and overwhelming for data analysts. To address this issue, we introduce InsightPilot, an LLM (Large Language Model)-based, automated data exploration system designed to simplify the data exploration process. InsightPilot automatically selects appropriate analysis intents, such as understanding, summarizing, and explaining. Then, these analysis intents are concretized by issuing corresponding intentional queries (IQueries) to create a meaningful and coherent exploration sequence. In brief, an IQuery is an abstraction and automation of data analysis operations, which mimics the approach of data analysts and simplifies the exploration process for users. By employing an LLM to iteratively collaborate with a state-of-the-art insight engine via IQueries, InsightPilot is effective in analyzing real-world datasets, enabling users to gain valuable insights through natural language inquiries. We demonstrate the effectiveness of InsightPilot in a case study, showing how it can help users gain valuable insights from their datasets.

cs.DB↗

arXiv2023

FRGNN: Mitigating the Impact of Distribution Shift on Graph Neural Networks via Test-Time Feature Reconstruction

Due to inappropriate sample selection and limited training data, a distribution shift often exists between the training and test sets. This shift can adversely affect the test performance of Graph Neural Networks (GNNs). Existing approaches mitigate this issue by either enhancing the robustness of GNNs to distribution shift or reducing the shift itself. However, both approaches necessitate retraining the model, which becomes unfeasible when the model structure and parameters are inaccessible. To address this challenge, we propose FR-GNN, a general framework for GNNs to conduct feature reconstruction. FRGNN constructs a mapping relationship between the output and input of a well-trained GNN to obtain class representative embeddings and then uses these embeddings to reconstruct the features of labeled nodes. These reconstructed features are then incorporated into the message passing mechanism of GNNs to influence the predictions of unlabeled nodes at test time. Notably, the reconstructed node features can be directly utilized for testing the well-trained model, effectively reducing the distribution shift and leading to improved test performance. This remarkable achievement is attained without any modifications to the model structure or parameters. We provide theoretical guarantees for the effectiveness of our framework. Furthermore, we conduct comprehensive experiments on various public datasets. The experimental results demonstrate the superior performance of FRGNN in comparison to multiple categories of baseline methods.

cs.LG↗

arXiv2023

Novel Online-Offline MA2C-DDPG for Efficient Spectrum Allocation and Trajectory Optimization in Dynamic Spectrum Sharing UAV Networks

Unmanned aerial vehicle (UAV) communication is of crucial importance for diverse practical applications. However, it is susceptible to the severe spectrum scarcity problem and interference since it operates in the unlicensed spectrum band. In order to tackle those issues, a dynamic spectrum sharing network is considered with the anti-jamming technique. Moreover, an intelligent spectrum allocation and trajectory optimization scheme is proposed to adapt to diverse jamming models by exploiting our designed novel online-offline multi-agent actor-critic and deep deterministic policy-gradient framework. Simulation results demonstrate the high efficiency of our proposed framework. It is also shown that our proposed scheme achieves the largest transmission rate among all benchmark schemes.

eess.SP↗

arXiv2023

A Partially Observable Deep Multi-Agent Active Inference Framework for Resource Allocation in 6G and Beyond Wireless Communications Networks

Resource allocation is of crucial importance in wireless communications. However, it is extremely challenging to design efficient resource allocation schemes for future wireless communication networks since the formulated resource allocation problems are generally non-convex and consist of various coupled variables. Moreover, the dynamic changes of practical wireless communication environment and user service requirements thirst for efficient real-time resource allocation. To tackle these issues, a novel partially observable deep multi-agent active inference (PODMAI) framework is proposed for realizing intelligent resource allocation. A belief based learning method is exploited for updating the policy by minimizing the variational free energy. A decentralized training with a decentralized execution multi-agent strategy is designed to overcome the limitations of the partially observable state information. Exploited the proposed framework, an intelligent spectrum allocation and trajectory optimization scheme is developed for a spectrum sharing unmanned aerial vehicle (UAV) network with dynamic transmission rate requirements as an example. Simulation results demonstrate that our proposed framework can significantly improve the sum transmission rate of the secondary network compared to various benchmark schemes. Moreover, the convergence speed of the proposed PODMAI is significantly improved compared with the conventional reinforcement learning framework. Overall, our proposed framework can enrich the intelligent resource allocation frameworks and pave the way for realizing real-time resource allocation.

eess.SY↗

arXiv2023

XInsight: eXplainable Data Analysis Through The Lens of Causality

In light of the growing popularity of Exploratory Data Analysis (EDA), understanding the underlying causes of the knowledge acquired by EDA is crucial. However, it remains under-researched. This study promotes a transparent and explicable perspective on data analysis, called eXplainable Data Analysis (XDA). For this reason, we present XInsight, a general framework for XDA. XInsight provides data analysis with qualitative and quantitative explanations of causal and non-causal semantics. This way, it will significantly improve human understanding and confidence in the outcomes of data analysis, facilitating accurate data interpretation and decision making in the real world. XInsight is a three-module, end-to-end pipeline designed to extract causal graphs, translate causal primitives into XDA semantics, and quantify the quantitative contribution of each explanation to a data fact. XInsight uses a set of design concepts and optimizations to address the inherent difficulties associated with integrating causality into XDA. Experiments on synthetic and real-world datasets as well as a user study demonstrate the highly promising capabilities of XInsight.

cs.DB↗

arXiv2023

f-Betas and Portfolio Optimization with f-Divergence induced Risk Measures

In this paper, we build on using the class of f-divergence induced coherent risk measures for portfolio optimization and derive its necessary optimality conditions formulated in CAPM format. We derive a new f-Beta similar to the Standard Betas and also extended it to previous works in Drawdown Betas. The f-Beta evaluates portfolio performance under an optimally perturbed market probability measure, and this family of Beta metrics gives various degrees of flexibility and interpretability. We conduct numerical experiments using selected stocks against a chosen S\&P 500 market index as the optimal portfolio to demonstrate the new perspectives provided by Hellinger-Beta as compared with Standard Beta and Drawdown Betas. In our experiments, the squared Hellinger distance is chosen to be the particular choice of the f-divergence function in the f-divergence induced risk measures and f-Betas. We calculate Hellinger-Beta metrics based on deviation measures and further extend this approach to calculate Hellinger-Betas based on drawdown measures, resulting in another new metric which is termed Hellinger-Drawdown Beta. We compare the resulting Hellinger-Beta values under various choices of the risk aversion parameter to study their sensitivity to increasing stress levels.

q-fin.PM↗

arXiv2023

Statistical Depth Function Random Variables for Univariate Distributions and induced Divergences

In this paper, we show that the halfspace depth random variable for samples from a univariate distribution with a notion of center is distributed as a uniform distribution on the interval [0,1/2]. The simplicial depth random variable has a distribution that first-order stochastic dominates that of the halfspace depth random variable and relates to a Beta distribution. Depth-induced divergences between two univariate distributions can be defined using divergences on the distributions for the statistical depth random variables in-between these two distributions. We discuss the properties of such induced divergences, particularly the depth-induced TVD distance based on halfspace or simplicial depth functions, and how empirical two-sample estimators benefit from such transformations.

stat.ME↗

arXiv2023

ML4C: Seeing Causality Through Latent Vicinity

Supervised Causal Learning (SCL) aims to learn causal relations from observational data by accessing previously seen datasets associated with ground truth causal relations. This paper presents a first attempt at addressing a fundamental question: What are the benefits from supervision and how does it benefit? Starting from seeing that SCL is not better than random guessing if the learning target is non-identifiable a priori, we propose a two-phase paradigm for SCL by explicitly considering structure identifiability. Following this paradigm, we tackle the problem of SCL on discrete data and propose ML4C. The core of ML4C is a binary classifier with a novel learning target: it classifies whether an Unshielded Triple (UT) is a v-structure or not. Specifically, starting from an input dataset with the corresponding skeleton provided, ML4C orients each UT once it is classified as a v-structure. These v-structures are together used to construct the final output. To address the fundamental question of SCL, we propose a principled method for ML4C featurization: we exploit the vicinity of a given UT (i.e., the neighbors of UT in skeleton), and derive features by considering the conditional dependencies and structural entanglement within the vicinity. We further prove that ML4C is asymptotically correct. Last but foremost, thorough experiments conducted on benchmark datasets demonstrate that ML4C remarkably outperforms other state-of-the-art algorithms in terms of accuracy, reliability, robustness and tolerance. In summary, ML4C shows promising results on validating the effectiveness of supervision for causal learning. Our codes are publicly available at https://github.com/microsoft/ML4C.

cs.LG↗

arXiv2023

A Unified and Fast Interpretable Model for Predictive Analytics

Predictive analytics aims to build machine learning models to predict behavior patterns and use predictions to guide decision-making. Predictive analytics is human involved, thus the machine learning model is preferred to be interpretable. In literature, Generalized Additive Model (GAM) is a standard for interpretability. However, due to the one-to-many and many-to-one phenomena which appear commonly in real-world scenarios, existing GAMs have limitations to serve predictive analytics in terms of both accuracy and training efficiency. In this paper, we propose FXAM (Fast and eXplainable Additive Model), a unified and fast interpretable model for predictive analytics. FXAM extends GAM's modeling capability with a unified additive model for numerical, categorical, and temporal features. FXAM conducts a novel training procedure called Three-Stage Iteration (TSI). TSI corresponds to learning over numerical, categorical, and temporal features respectively. Each stage learns a local optimum by fixing the parameters of other stages. We design joint learning over categorical features and partial learning over temporal features to achieve high accuracy and training efficiency. We prove that TSI is guaranteed to converge to the global optimum. We further propose a set of optimization techniques to speed up FXAM's training algorithm to meet the needs of interactive analysis. Thorough evaluations conducted on diverse data sets verify that FXAM significantly outperforms existing GAMs in terms of training speed, and modeling categorical and temporal features. In terms of interpretability, we compare FXAM with the typical post-hoc approach XGBoost+SHAP on two real-world scenarios, which shows the superiority of FXAM's inherent interpretability for predictive analytics.

cs.LG↗

arXiv2022

LRIP-Net: Low-Resolution Image Prior based Network for Limited-Angle CT Reconstruction

In the practical applications of computed tomography imaging, the projection data may be acquired within a limited-angle range and corrupted by noises due to the limitation of scanning conditions. The noisy incomplete projection data results in the ill-posedness of the inverse problems. In this work, we theoretically verify that the low-resolution reconstruction problem has better numerical stability than the high-resolution problem. In what follows, a novel low-resolution image prior based CT reconstruction model is proposed to make use of the low-resolution image to improve the reconstruction quality. More specifically, we build up a low-resolution reconstruction problem on the down-sampled projection data, and use the reconstructed low-resolution image as prior knowledge for the original limited-angle CT problem. We solve the constrained minimization problem by the alternating direction method with all subproblems approximated by the convolutional neural networks. Numerical experiments demonstrate that our double-resolution network outperforms both the variational method and popular learning-based reconstruction methods on noisy limited-angle reconstruction problems.

eess.IV↗

arXiv2022

Data-and-Knowledge Dual-Driven Automatic Modulation Recognition for Wireless Communication Networks

Automatic modulation classification is of crucial importance in wireless communication networks. Deep learning based automatic modulation classification schemes have attracted extensive attention due to the superior accuracy. However, the data-driven method relies on a large amount of training samples and the classification accuracy is poor in the low signal-to-noise radio (SNR). In order to tackle these problems, a novel data-and-knowledge dual-driven automatic modulation classification scheme based on radio frequency machine learning is proposed by exploiting the attribute features of different modulations. The visual model is utilized to extract visual features. The attribute learning model is used to learn the attribute semantic representations. The transformation model is proposed to convert the attribute representation into the visual space. Extensive simulation results demonstrate that our proposed automatic modulation classification scheme can achieve better performance than the benchmark schemes in terms of the classification accuracy, especially in the low SNR. Moreover, the confusion among high-order modulations is reduced by using our proposed scheme compared with other traditional schemes.

eess.SP↗

arXiv2022

Multibeam Satellite Communications with Energy Efficiency Optimization

Energy efficiency (EE) is an important aspect of satellite communications. Different with the existing algorithms that typically use the first-order Taylor lower bound approximation to convert non-convex EE maximization (EEM) problems into convex ones, in this letter a two-step quadratic transformation method is presented. In the first step, the fractional form of the achievable rate over the total power consumption is converted into a non-fractional form based on quadratic transformation. In the second step, the fractional form of the signal power over the interference-and-noise power is further converted into a non-fractional form, still based on quadratic transformation. After the two-step quadratic transformation, the original EEM problem is converted into an equivalent convex one. Then an alternating optimization algorithm is presented to solve it by iteratively performing two stages until a stop condition is satisfied. Simulation results show that the presented algorithm can fast converge and its performance is better than that of the sequential convex approximation algorithm and the multibeam interference mitigation algorithm.

cs.IT↗

arXiv2021

Location-Based Timing Advance Estimation for 5G Integrated LEO Satellite Communications

Integrated satellite-terrestrial communications networks aim to exploit both the satellite and the ground mobile communications, thus providing genuine ubiquitous coverage. For 5G integrated low earth orbit (LEO) satellite communication systems, the timing advance (TA) is required to be estimated in the initial random access procedure in order to facilitate the uplink frame alignment among different users. However, due to the inherent characteristics of LEO satellite communication systems, e.g., wide beam coverage and long propagation delays, the existing 5G terrestrial uplink TA scheme is not applicable in the satellite networks. In this paper, we investigate location-based TA estimation for 5G integrated LEO satellite communication systems. We obtain the time difference of arrival (TDOA) and frequency difference of arrival (FDOA) measurements in the downlink timing and frequency synchronization phase, which are made from the satellite at different time instants. We propose to take these measurements for either UE geolocation or ephemeris estimation, thus calculating the TA value. The estimation is then formulated as a quadratic optimization problem whose globally optimal solution can be obtained by a quadratic penalty algorithm. To reduce the computational complexity, we further propose an alternative approximation method based on iteratively performing a linearization procedure on the quadratic equality constraints. Numerical results show that the proposed methods can approach the constrained Cramer-Rao lower bound (CRLB) of the TA estimation and thus assure uplink frame alignment for different users.

cs.IT↗

arXiv2021

Finding $B_c(3S)$ States via Their Strong Decays

The experimentally known $B_c$ states are all below open bottom-charm threshold, which experience three main decay modes, and all induced by weak interaction. In this work, we investigate the mass spectrum and strong decays of the $B_c(3S)$ states, which just above the threshold, in the Bethe-Salpeter formalism and $^3P_0$ model. The numerical estimation gives $M(B_c(3^1S_0))=7273\ {\rm MeV}$, $M(B_c^*(3^3S_1))=7304\ {\rm MeV}$, $Γ\left(B_c(3^1S_0)\to B^*D\right)=26.02^{+2.33}_{-2.21}\ {\rm MeV}$, $Γ\left(B_c^*(3^3S_1)\to BD\right)=3.39^{+0.27}_{-0.26}\ {\rm MeV}$, $Γ\left(B_c^*(3^3S_1)\to B^*D\right)=14.77^{+1.40}_{-1.33}\ {\rm MeV}$ and $Γ\left(B_c^*(3^3S_1)\to BD^*\right)=6.14^{+0.58}_{-0.54}\ {\rm MeV}$. Compared with previous studies in non-relativistic approximation, our results indicate that the relativistic effects are notable in $B_c(3S)$ exclusive strong decays. According to the results, we suggest to find the $B_c(3S)$ states in their hadronic decays to $B$ and $D$ mesons in experiment, like the LHCb.

hep-ph↗

arXiv2020

A hybrid deep-learning approach for complex biochemical named entity recognition

Named entity recognition (NER) of chemicals and drugs is a critical domain of information extraction in biochemical research. NER provides support for text mining in biochemical reactions, including entity relation extraction, attribute extraction, and metabolic response relationship extraction. However, the existence of complex naming characteristics in the biomedical field, such as polysemy and special characters, make the NER task very challenging. Here, we propose a hybrid deep learning approach to improve the recognition accuracy of NER. Specifically, our approach applies the Bidirectional Encoder Representations from Transformers (BERT) model to extract the underlying features of the text, learns a representation of the context of the text through Bi-directional Long Short-Term Memory (BILSTM), and incorporates the multi-head attention (MHATT) mechanism to extract chapter-level features. In this approach, the MHATT mechanism aims to improve the recognition accuracy of abbreviations to efficiently deal with the problem of inconsistency in full-text labels. Moreover, conditional random field (CRF) is used to label sequence tags because this probabilistic method does not need strict independence assumptions and can accommodate arbitrary context information. The experimental evaluation on a publicly-available dataset shows that the proposed hybrid approach achieves the best recognition performance; in particular, it substantially improves performance in recognizing abbreviations, polysemes, and low-frequency entities, compared with the state-of-the-art approaches. For instance, compared with the recognition accuracies for low-frequency entities produced by the BILSTM-CRF algorithm, those produced by the hybrid approach on two entity datasets (MULTIPLE and IDENTIFIER) have been increased by 80% and 21.69%, respectively.

cs.CL↗