Search

Multi-person motion prediction is a complex and emerging field with significant real-world applications. Current state-of-the-art methods typically adopt dual-path networks to separately modeling spatial features and temporal features. However, the uncertain compatibility of the two networks brings a challenge for spatio-temporal features fusion and violate the spatio-temporal coherence and coupling of human motions by nature. To address this issue, we propose a novel graph structure, UnityGraph, which treats spatio-temporal features as a whole, enhancing model coherence and coupling.spatio-temporal features as a whole, enhancing model coherence and coupling. Specifically, UnityGraph is a hypervariate graph based network. The flexibility of the hypergraph allows us to consider the observed motions as graph nodes. We then leverage hyperedges to bridge these nodes for exploring spatio-temporal features. This perspective considers spatio-temporal dynamics unitedly and reformulates multi-person motion prediction into a problem on a single graph. Leveraging the dynamic message passing based on this hypergraph, our model dynamically learns from both types of relations to generate targeted messages that reflect the relevance among nodes. Extensive experiments on several datasets demonstrates that our method achieves state-of-the-art performance, confirming its effectiveness and innovative design., Comment: 13pages, 12 figures. arXiv admin note: text overlap with arXiv:2411.03729

Multi-person motion prediction is an emerging and intricate task with broad real-world applications. Unlike single person motion prediction, it considers not just the skeleton structures or human trajectories but also the interactions between others. Previous methods use various networks to achieve impressive predictions but often overlook that the joints relations within an individual (intra-relation) and interactions among groups (inter-relation) are distinct types of representations. These methods often lack explicit representation of inter&intra-relations, and inevitably introduce undesired dependencies. To address this issue, we introduce a new collaborative framework for multi-person motion prediction that explicitly modeling these relations:a GCN-based network for intra-relations and a novel reasoning network for inter-relations.Moreover, we propose a novel plug-and-play aggregation module called the Interaction Aggregation Module (IAM), which employs an aggregate-attention mechanism to seamlessly integrate these relations. Experiments indicate that the module can also be applied to other dual-path models. Extensive experiments on the 3DPW, 3DPW-RC, CMU-Mocap, MuPoTS-3D, as well as synthesized datasets Mix1 & Mix2 (9 to 15 persons), demonstrate that our method achieves state-of-the-art performance., Comment: Submitted to IEEE Transactions on Multimedia

To meet the growing demand for accurate, rapid, and cost-effective at-home clinical testing, we developed a radical-mediated enzyme assay (REEA) integrated with a paper fluidic system and electrically read by a handheld field-effect transistor (FET) device. The REEA utilizes horseradish peroxidase (HRP) to catalyze the conversion of aromatic substrates into radical forms, producing protons detected by an ion-sensitive FET for biomarker quantification. Through screening 14 phenolic compounds, halogenated phenols emerged as optimal substrates for the REEA. Encased in an affordable cartridge ($0.55 per test), the system achieved a detection limit of 146 fg/mL for estradiol (E2), with a coefficient of variation (CV) below 9.2% in E2-spiked samples and an r2 of 0.963 across a measuring range of 19 to 4,551 pg/mL in clinical plasma samples, providing results in under 10 minutes. This adaptable system not only promises to offer a fast and reliable platform, but also holds significant potential for expansion to a wide array of biomarkers, paving the way for broader clinical and home-based applications.

In this paper, we study the existence of normalized solutions for the following $(2, q)$-Laplacian equation \begin{equation*}\label{Eq-Equation1} \left\{\begin{array}{l} -\Delta u-\Delta_q u+\lambda u=f(u) \quad x \in \mathbb{R}^N , \\ \int_{\mathbb{R}^N}u^2 d x=c^2, \\ \end{array}\right. \end{equation*} where $10$ is a constant. The nonlinearity $f:\mathbb{R}\rightarrow \mathbb{R}$ is continuous, with mass-subcritical growth at the origin, mass-supercritical growth at infinity, and is more general than the sum of two powers. Under different assumptions, we prove the existence of a locally least-energy solution and the existence of a second solution with higher energy., Comment: arXiv admin note: substantial text overlap with arXiv:2405.05194 by other authors

The performance of graph neural networks (GNNs) is susceptible to discrepancies between training and testing sample distributions. Prior studies have attempted to enhance GNN performance by reconstructing node features during the testing phase without modifying the model parameters. However, these approaches lack theoretical analysis of the proximity between predictions and ground truth at test time. In this paper, we propose a novel node feature reconstruction method grounded in Lyapunov stability theory. Specifically, we model the GNN as a control system during the testing phase, considering node features as control variables. A neural controller that adheres to the Lyapunov stability criterion is then employed to reconstruct these node features, ensuring that the predictions progressively approach the ground truth at test time. We validate the effectiveness of our approach through extensive experiments across multiple datasets, demonstrating significant performance improvements.

Developing advanced catalysts for acidic oxygen evolution reaction (OER) is crucial for sustainable hydrogen production. This study introduces a novel, multi-stage machine learning (ML) approach to streamline the discovery and optimization of complex multi-metallic catalysts. Our method integrates data mining, active learning, and domain adaptation throughout the materials discovery process. Unlike traditional trial-and-error methods, this approach systematically narrows the exploration space using domain knowledge with minimized reliance on subjective intuition. Then the active learning module efficiently refines element composition and synthesis conditions through iterative experimental feedback. The process culminated in the discovery of a promising Ru-Mn-Ca-Pr oxide catalyst. Our workflow also enhances theoretical simulations with domain adaptation strategy, providing deeper mechanistic insights aligned with experimental findings. By leveraging diverse data sources and multiple ML strategies, we establish an efficient pathway for electrocatalyst discovery and optimization. This comprehensive, data-driven approach represents a paradigm shift and potentially new benchmark in electrocatalysts research., Comment: 95 pages (main text 37 pages; supplementary materials 58 pages); 38 figures (main text 6 figures; supplementary materials 32 figures)

Differentiable causal discovery has made significant advancements in the learning of directed acyclic graphs. However, its application to real-world datasets remains restricted due to the ubiquity of latent confounders and the requirement to learn maximal ancestral graphs (MAGs). To date, existing differentiable MAG learning algorithms have been limited to small datasets and failed to scale to larger ones (e.g., with more than 50 variables). The key insight in this paper is that the causal skeleton, which is the undirected version of the causal graph, has potential for improving accuracy and reducing the search space of the optimization procedure, thereby enhancing the performance of differentiable causal discovery. Therefore, we seek to address a two-fold challenge to harness the potential of the causal skeleton for differentiable causal discovery in the presence of latent confounders: (1) scalable and accurate estimation of skeleton and (2) universal integration of skeleton estimation with differentiable causal discovery. To this end, we propose SPOT (Skeleton Posterior-guided OpTimization), a two-phase framework that harnesses skeleton posterior for differentiable causal discovery in the presence of latent confounders. On the contrary to a ``point-estimation'', SPOT seeks to estimate the posterior distribution of skeletons given the dataset. It first formulates the posterior inference as an instance of amortized inference problem and concretizes it with a supervised causal learning (SCL)-enabled solution to estimate the skeleton posterior. To incorporate the skeleton posterior with differentiable causal discovery, SPOT then features a skeleton posterior-guided stochastic optimization procedure to guide the optimization of MAGs. [abridged due to length limit]

In this paper, we consider the existence and multiplicity of normalized solutions for the following $(2, q)$-Laplacian equation \begin{equation}\label{Equation} \left\{\begin{aligned} &-\Delta u-\Delta_q u+\lambda u=g(u),\quad x \in \mathbb{R}^N, &\|u\|_2^2 =c^2, \end{aligned}\right. \tag{$\mathscr E_\lambda$} \end{equation} where $10$ is a constant. The nonlinearity $g:\mathbb{R}\rightarrow \mathbb{R}$ is continuous and the behaviour of $g$ at the origin is allowed to be strongly sublinear, i.e., $\lim \limits_{s \rightarrow 0} g(s) / s=-\infty$, which includes the logarithmic nonlinearity $$g(s)= s \log s^2.$$ We consider a family of approximating problems that can be set in $H^1\left(\mathbb{R}^N\right)\cap D^{1, q}\left(\mathbb{R}^N\right)$ and the corresponding least-energy solutions. Then, we prove that such a family of solutions converges to a least-energy solution to the original problem. Additionally, under certain assumptions about $g$ that allow us to work in a suitable subspace of $H^1\left(\mathbb{R}^N\right)\cap D^{1, q}\left(\mathbb{R}^N\right)$, we prove the existence of infinitely many solutions of the above $(2, q)$-Laplacian equation., Comment: arXiv admin note: text overlap with arXiv:2306.06015 by other authors

The rapid advancement of Large Language Models (LLMs) has ushered in an era where AI-generated text is increasingly indistinguishable from human-generated content. Detecting AI-generated text has become imperative to combat misinformation, ensure content authenticity, and safeguard against malicious uses of AI. In this paper, we propose a novel hybrid approach that combines traditional TF-IDF techniques with advanced machine learning models, including Bayesian classifiers, Stochastic Gradient Descent (SGD), Categorical Gradient Boosting (CatBoost), and 12 instances of Deberta-v3-large models. Our approach aims to address the challenges associated with detecting AI-generated text by leveraging the strengths of both traditional feature extraction methods and state-of-the-art deep learning models. Through extensive experiments on a comprehensive dataset, we demonstrate the effectiveness of our proposed method in accurately distinguishing between human and AI-generated text. Our approach achieves superior performance compared to existing methods. This research contributes to the advancement of AI-generated text detection techniques and lays the foundation for developing robust solutions to mitigate the challenges posed by AI-generated content.

Tabular data analysis is crucial in various fields, and large language models show promise in this area. However, current research mostly focuses on rudimentary tasks like Text2SQL and TableQA, neglecting advanced analysis like forecasting and chart generation. To address this gap, we developed the Text2Analysis benchmark, incorporating advanced analysis tasks that go beyond the SQL-compatible operations and require more in-depth analysis. We also develop five innovative and effective annotation methods, harnessing the capabilities of large language models to enhance data quality and quantity. Additionally, we include unclear queries that resemble real-world user questions to test how well models can understand and tackle such challenges. Finally, we collect 2249 query-result pairs with 347 tables. We evaluate five state-of-the-art models using three different metrics and the results show that our benchmark presents introduces considerable challenge in the field of tabular data analysis, paving the way for more advanced research opportunities., Comment: Accepted by AAAI'2024

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., Comment: Some technical errors occured in the manuscript

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.

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., Comment: Some technical errors occured in the manuscript

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., Comment: 15 pages, 3 figures

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.

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., Comment: 19 pages, 7 figures

Non-line-of-sight (NLOS) imaging aims to reconstruct the three-dimensional hidden scenes from the data measured in the line-of-sight, which uses photon time-of-flight information encoded in light after multiple diffuse reflections. The under-sampled scanning data can facilitate fast imaging. However, the resulting reconstruction problem becomes a serious ill-posed inverse problem, the solution of which is highly possibility to be degraded due to noises and distortions. In this paper, we propose novel NLOS reconstruction models based on curvature regularization, i.e., the object-domain curvature regularization model and the dual (signal and object)-domain curvature regularization model. In what follows, we develop efficient optimization algorithms relying on the alternating direction method of multipliers (ADMM) with the backtracking stepsize rule, for which all solvers can be implemented on GPUs. We evaluate the proposed algorithms on both synthetic and real datasets, which achieve state-of-the-art performance, especially in the compressed sensing setting. Based on GPU computing, our algorithm is the most effective among iterative methods, balancing reconstruction quality and computational time. All our codes and data are available at https://github.com/Duanlab123/CurvNLOS.

This paper studies optimization of the Conditional Value at Risk (CVaR) for a discounted total-cost Markov Decision Process (MDP) with finite state and action sets. This CVaR optimization problem can be reformulated as a Robust MDP(RMDP) with a compact state space. States in this RMDP are the original states of the problems augmented with tail risk levels, and the Decision Maker (DM) knows only the initial tail risk level at the initial state and time. Thus, in order to find an optimal policy following this approach, the DM needs to solve an RMDP with incomplete state observations because after the first move, the DM observes the states of the system, but the tail risk levels are unknown. This paper shows that for the CVaR optimization problem the corresponding RMDP can be solved by using the methods of convex analysis. This paper introduces the algorithm for computing and implementing an optimal CVaR policy by using the value function for the version of this RMDP with completely observable tail risk levels at all states. This algorithm and the major results of the paper are presented for a more general problem of optimization of sum of a mean and CVaR for possibly different cost functions.

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.

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.

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.

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.