Deterministic and stochastic control of kirigami topology.

Kirigami, the creative art of paper cutting, is a promising paradigm for mechanical metamaterials. However, to make kirigami-inspired structures a reality requires controlling the topology of kirigami to achieve connectivity and rigidity. We address this question by deriving the maximum number of cuts (minimum number of links) that still allow us to preserve global rigidity and connectivity of the kirigami. A deterministic hierarchical construction method yields an efficient topological way to control both the number of connected pieces and the total degrees of freedom. A statistical approach to the control of rigidity and connectivity in kirigami with random cuts complements the deterministic pathway, and shows that both the number of connected pieces and the degrees of freedom show percolation transitions as a function of the density of cuts (links). Together, this provides a general framework for the control of rigidity and connectivity in planar kirigami.

Rigidity percolation and geometric information in floppy origami.

Origami structures with a large number of excess folds are capable of storing distinguishable geometric states that are energetically equivalent. As the number of excess folds is reduced, the system has fewer equivalent states and can eventually become rigid. We quantify this transition from a floppy to a rigid state as a function of the presence of folding constraints in a classic origami tessellation, Miura-ori. We show that in a fully triangulated Miura-ori that is maximally floppy, adding constraints via the elimination of diagonal folds in the quads decreases the number of degrees of freedom in the system, first linearly and then nonlinearly. In the nonlinear regime, mechanical cooperativity sets in via a redundancy in the assignment of constraints, and the degrees of freedom depend on constraint density in a scale-invariant manner. A percolation transition in the redundancy in the constraints as a function of constraint density suggests how excess folds in an origami structure can be used to store geometric information in a scale-invariant way.

Dynamic-group-aware networks for multi-agent trajectory prediction with relational reasoning.

Demystifying the interactions among multiple agents from their past trajectories is fundamental to precise and interpretable trajectory prediction. However, previous works mainly consider static, pairwise interactions with limited relational reasoning. To more comprehensively model interactions and reason relations, we propose DynGroupNet, a dynamic-group-aware network, which (i) models time-varying interactions in highly dynamic scenes; (ii) captures both pairwise and group-wise interactions; and (iii) reasons both interaction strength and category without direct supervision. Based on DynGroupNet, we further design a prediction system to forecast socially plausible trajectories with dynamic relational reasoning. The proposed prediction system leverages the Gaussian mixture model, multiple sampling and prediction refinement to promote prediction diversity for multiple future possibilities capturing, training stability for efficient model learning and trajectory smoothness for more realistic predictions, respectively. The proposed complex interaction modeling of DynGroupNet, future diversity capturing, efficient model training and trajectory smoothing of prediction system together to promote more accurate and plausible future predictions. Extensive experiments show that: (1) DynGroupNet can capture time-varying group behaviors, infer time-varying interaction category and interaction strength during prediction; (2) DynGroupNet significantly outperforms the state-of-the-art trajectory prediction methods by 28.0%, 34.9%, 13.0% in FDE on the NBA, NFL and SDD datasets.

Ontogenetic color change in the tail of blue-tailed skinks (Plestodion elegans).

Ontogenetic color change in animals is an interesting evolution-related phenomenon that has been studied by evolutionary biologists for decades. However, obtaining quantitative and continuous color measurements throughout the life cycle of animals is a challenge. To understand the rhythm of change in tail color and sexual dichromatism, we used a spectrometer to measure the tail color of blue-tailed skink (Plestiodon elegans) from birth to sexual maturity. Lab color space was selected due to its simplicity, fastness, and accuracy and depends on the visual sense of the observer for measuring the tail color of skinks. A strong relationship was observed between color indexes (values of L*, a*, b*) and growth time of skink. The luminance of tail color decreased from juveniles to adults in both sexes. Moreover, we observed differences in color rhythms between the sexes, which may be influenced by different behavioral strategies used by them. This study provides continuous measurements of change in tail color in skinks from juveniles to adults and offers insights into their sex-based differences. While this study does not provide direct evidence to explain the potential factors that drive dichromatism between the sexes of lizards, our finding could serve as a reference for future studies exploring possible mechanisms of ontogenetic color change in reptiles.

MPED: Quantifying Point Cloud Distortion Based on Multiscale Potential Energy Discrepancy.

In this article, we propose a new distortion quantification method for point clouds, the multiscale potential energy discrepancy (MPED). Currently, there is a lack of effective distortion quantification for a variety of point cloud perception tasks. Specifically, in human vision tasks, a distortion quantification method is used to predict human subjective scores and optimize the selection of human perception task parameters, such as dense point cloud compression and enhancement. In machine vision tasks, a distortion quantification method usually serves as loss function to guide the training of deep neural networks for unsupervised learning tasks (e.g., sparse point cloud reconstruction, completion, and upsampling). Therefore, an effective distortion quantification should be differentiable, distortion discriminable, and have low computational complexity. However, current distortion quantification cannot satisfy all three conditions. To fill this gap, we propose a new point cloud feature description method, the point potential energy (PPE), inspired by classical physics. We regard the point clouds are systems that have potential energy and the distortion can change the total potential energy. By evaluating various neighborhood sizes, the proposed MPED achieves global-local tradeoffs, capturing distortion in a multiscale fashion. We further theoretically show that classical Chamfer distance is a special case of our MPED. Extensive experiments show that the proposed MPED is superior to current methods on both human and machine perception tasks. Our code is available at https://github.com/Qi-Yangsjtu/MPED.

Discriminative Radial Domain Adaptation.

Domain adaptation methods reduce domain shift typically by learning domain-invariant features. Most existing methods are built on distribution matching, e.g., adversarial domain adaptation, which tends to corrupt feature discriminability. In this paper, we propose Discriminative Radial Domain Adaptation (DRDR) which bridges source and target domains via a shared radial structure. It's motivated by the observation that as the model is trained to be progressively discriminative, features of different categories expand outwards in different directions, forming a radial structure. We show that transferring such an inherently discriminative structure would enable to enhance feature transferability and discriminability simultaneously. Specifically, we represent each domain with a global anchor and each category a local anchor to form a radial structure and reduce domain shift via structure matching. It consists of two parts, namely isometric transformation to align the structure globally and local refinement to match each category. To enhance the discriminability of the structure, we further encourage samples to cluster close to the corresponding local anchors based on optimal-transport assignment. Extensively experimenting on multiple benchmarks, our method is shown to consistently outperforms state-of-the-art approaches on varied tasks, including the typical unsupervised domain adaptation, multi-source domain adaptation, domain-agnostic learning, and domain generalization.

Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory Forecasting.

In multi-modal multi-agent trajectory forecasting, two major challenges have not been fully tackled: 1) how to measure the uncertainty brought by the interaction module that causes correlations among the predicted trajectories of multiple agents; 2) how to rank the multiple predictions and select the optimal predicted trajectory. In order to handle the aforementioned challenges, this work first proposes a novel concept, collaborative uncertainty (CU), which models the uncertainty resulting from interaction modules. Then we build a general CU-aware regression framework with an original permutation-equivariant uncertainty estimator to do both tasks of regression and uncertainty estimation. Furthermore, we apply the proposed framework to current SOTA multi-agent multi-modal forecasting systems as a plugin module, which enables the SOTA systems to: 1) estimate the uncertainty in the multi-agent multi-modal trajectory forecasting task; 2) rank the multiple predictions and select the optimal one based on the estimated uncertainty. We conduct extensive experiments on a synthetic dataset and two public large-scale multi-agent trajectory forecasting benchmarks. Experiments show that: 1) on the synthetic dataset, the CU-aware regression framework allows the model to appropriately approximate the ground-truth Laplace distribution; 2) on the multi-agent trajectory forecasting benchmarks, the CU-aware regression framework steadily helps SOTA systems improve their performances. Especially, the proposed framework helps VectorNet improve by 262 cm regarding the Final Displacement Error of the chosen optimal prediction on the nuScenes dataset; 3) in multi-agent multi-modal trajectory forecasting, prediction uncertainty is proportional to future stochasticity; 4) the estimated CU values are highly related to the interactive information among agents. The proposed framework can guide the development of more reliable and safer forecasting systems in the future.

Efficient and Stable Graph Scattering Transforms via Pruning.

Graph convolutional networks (GCNs) have well-documented performance in various graph learning tasks, but their analysis is still at its infancy. Graph scattering transforms (GSTs) offer training-free deep GCN models that extract features from graph data, and are amenable to generalization and stability analyses. The price paid by GSTs is exponential complexity in space and time that increases with the number of layers. This discourages deployment of GSTs when a deep architecture is needed. The present work addresses the complexity limitation of GSTs by introducing an efficient so-termed pruned (p)GST approach. The resultant pruning algorithm is guided by a graph-spectrum-inspired criterion, and retains informative scattering features on-the-fly while bypassing the exponential complexity associated with GSTs. Stability of the novel pGSTs is also established when the input graph data or the network structure are perturbed. Furthermore, the sensitivity of pGST to random and localized signal perturbations is investigated analytically and experimentally. Numerical tests showcase that pGST performs comparably to the baseline GST at considerable computational savings. Furthermore, pGST achieves comparable performance to state-of-the-art GCNs in graph and 3D point cloud classification tasks. Upon analyzing the pGST pruning patterns, it is shown that graph data in different domains call for different network architectures, and that the pruning algorithm may be employed to guide the design choices for contemporary GCNs.

Cell clustering for spatial transcriptomics data with graph neural networks.

Spatial transcriptomics data can provide high-throughput gene expression profiling and the spatial structure of tissues simultaneously. Most studies have relied on only the gene expression information but cannot utilize the spatial information efficiently. Taking advantage of spatial transcriptomics and graph neural networks, we introduce cell clustering for spatial transcriptomics data with graph neural networks, an unsupervised cell clustering method based on graph convolutional networks to improve ab initio cell clustering and discovery of cell subtypes based on curated cell category annotation. On the basis of its application to five in vitro and in vivo spatial datasets, we show that cell clustering for spatial transcriptomics outperforms other spatial clustering approaches on spatial transcriptomics datasets and can clearly identify all four cell cycle phases from multiplexed error-robust fluorescence in situ hybridization data of cultured cells. From enhanced sequential fluorescence in situ hybridization data of brain, cell clustering for spatial transcriptomics finds functional cell subtypes with different micro-environments, which are all validated experimentally, inspiring biological hypotheses about the underlying interactions among the cell state, cell type and micro-environment.

Online Multi-Agent Forecasting With Interpretable Collaborative Graph Neural Networks.

This article considers predicting future statuses of multiple agents in an online fashion by exploiting dynamic interactions in the system. We propose a novel collaborative prediction unit (CoPU), which aggregates the predictions from multiple collaborative predictors according to a collaborative graph. Each collaborative predictor is trained to predict the agent status by integrating the impact of another agent. The edge weights of the collaborative graph reflect the importance of each predictor. The collaborative graph is adjusted online by multiplicative update, which can be motivated by minimizing an explicit objective. With this objective, we also conduct regret analysis to indicate that, along with training, our CoPU achieves similar performance with the best individual collaborative predictor in hindsight. This theoretical interpretability distinguishes our method from many other graph networks. To progressively refine predictions, multiple CoPUs are stacked to form a collaborative graph neural network. Extensive experiments are conducted on three tasks: online simulated trajectory prediction, online human motion prediction, and online traffic speed prediction, and our methods outperform state-of-the-art works on the three tasks by 28.6%, 17.4%, and 21.0% on average, respectively; in addition, the proposed CoGNNs have lower average time costs in one online training/testing iteration than most previous methods.

Learning on Attribute-Missing Graphs.

Graphs with complete node attributes have been widely explored recently. While in practice, there is a graph where attributes of only partial nodes could be available and those of the others might be entirely missing. This attribute-missing graph is related to numerous real-world applications and there are limited studies investigating the corresponding learning problems. Existing graph learning methods including the popular GNN cannot provide satisfied learning performance since they are not specified for attribute-missing graphs. Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community. In this article, we make a shared-latent space assumption on graphs and develop a novel distribution matching-based GNN called structure-attribute transformer (SAT) for attribute-missing graphs. SAT leverages structures and attributes in a decoupled scheme and achieves the joint distribution modeling of structures and attributes by distribution matching techniques. It could not only perform the link prediction task but also the newly introduced node attribute completion task. Furthermore, practical measures are introduced to quantify the performance of node attribute completion. Extensive experiments on seven real-world datasets indicate SAT shows better performance than other methods on both link prediction and node attribute completion tasks.

Symbiotic Graph Neural Networks for 3D Skeleton-Based Human Action Recognition and Motion Prediction.

3D skeleton-based action recognition and motion prediction are two essential problems of human activity understanding. In many previous works: 1) they studied two tasks separately, neglecting internal correlations; and 2) they did not capture sufficient relations inside the body. To address these issues, we propose a symbiotic model to handle two tasks jointly; and we propose two scales of graphs to explicitly capture relations among body-joints and body-parts. Together, we propose symbiotic graph neural networks, which contain a backbone, an action-recognition head, and a motion-prediction head. Two heads are trained jointly and enhance each other. For the backbone, we propose multi-branch multiscale graph convolution networks to extract spatial and temporal features. The multiscale graph convolution networks are based on joint-scale and part-scale graphs. The joint-scale graphs contain actional graphs, capturing action-based relations, and structural graphs, capturing physical constraints. The part-scale graphs integrate body-joints to form specific parts, representing high-level relations. Moreover, dual bone-based graphs and networks are proposed to learn complementary features. We conduct extensive experiments for skeleton-based action recognition and motion prediction with four datasets, NTU-RGB+D, Kinetics, Human3.6M, and CMU Mocap. Experiments show that our symbiotic graph neural networks achieve better performances on both tasks compared to the state-of-the-art methods.

Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction.

We propose a multiscale spatio-temporal graph neural network (MST-GNN) to predict the future 3D skeleton-based human poses in an action-category-agnostic manner. The core of MST-GNN is a multiscale spatio-temporal graph that explicitly models the relations in motions at various spatial and temporal scales. Different from many previous hierarchical structures, our multiscale spatio-temporal graph is built in a data-adaptive fashion, which captures nonphysical, yet motion-based relations. The key module of MST-GNN is a multiscale spatio-temporal graph computational unit (MST-GCU) based on the trainable graph structure. MST-GCU embeds underlying features at individual scales and then fuses features across scales to obtain a comprehensive representation. The overall architecture of MST-GNN follows an encoder-decoder framework, where the encoder consists of a sequence of MST-GCUs to learn the spatial and temporal features of motions, and the decoder uses a graph-based attention gate recurrent unit (GA-GRU) to generate future poses. Extensive experiments are conducted to show that the proposed MST-GNN outperforms state-of-the-art methods in both short and long-term motion prediction on the datasets of Human 3.6M, CMU Mocap and 3DPW, where MST-GNN outperforms previous works by 5.33% and 3.67% of mean angle errors in average for short-term and long-term prediction on Human 3.6M, and by 11.84% and 4.71% of mean angle errors for short-term and long-term prediction on CMU Mocap, and by 1.13% of mean angle errors on 3DPW in average, respectively. We further investigate the learned multiscale graphs for interpretability.

Control of connectivity and rigidity in prismatic assemblies.

How can we manipulate the topological connectivity of a three-dimensional prismatic assembly to control the number of internal degrees of freedom and the number of connected components in it? To answer this question in a deterministic setting, we use ideas from elementary number theory to provide a hierarchical deterministic protocol for the control of rigidity and connectivity. We then show that it is possible to also use a stochastic protocol to achieve the same results via a percolation transition. Together, these approaches provide scale-independent algorithms for the cutting or gluing of three-dimensional prismatic assemblies to control their overall connectivity and rigidity.

Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering.

We propose a deep autoencoder with graph topology inference and filtering to achieve compact representations of unorganized 3D point clouds in an unsupervised manner. Many previous works discretize 3D points to voxels and then use lattice-based methods to process and learn 3D spatial information; however, this leads to inevitable discretization errors. In this work, we try to handle raw 3D points without such compromise. The proposed networks follow the autoencoder framework with a focus on designing the decoder. The encoder of the proposed networks adopts similar architectures as in PointNet, which is a well-acknowledged method for supervised learning of 3D point clouds. The decoder of the proposed networks involves three novel modules: the folding module, the graph-topology-inference module, and the graph-filtering module. The folding module folds a canonical 2D lattice to the underlying surface of a 3D point cloud, achieving coarse reconstruction; the graph-topology-inference module learns a graph topology to represent pairwise relationships between 3D points, pushing the latent code to preserve both coordinates and pairwise relationships of points in 3D point clouds; and the graph-filtering module couples the above two modules, refining the coarse reconstruction through a learnt graph topology to obtain the final reconstruction. The proposed decoder leverages a learnable graph topology to push the codeword to preserve representative features and further improve the unsupervised-learning performance. We further provide theoretical analyses of the proposed architecture. We provide an upper bound for the reconstruction loss and further show the superiority of graph smoothness over spatial smoothness as a prior to model 3D point clouds. In the experiments, we validate the proposed networks in three tasks, including 3D point cloud reconstruction, visualization, and transfer classification. The experimental results show that (1) the proposed networks outperform the state-of-the-art methods in various tasks, including reconstruction and transfer classification; (2) a graph topology can be inferred as auxiliary information without specific supervision on graph topology inference; (3) graph filtering refines the reconstruction, leading to better performances; and (4) designing a powerful decoder could improve the unsupervised-learning performance, just like a powerful encoder.

Dynamic responses, GPS positions and environmental conditions of two light rail vehicles in Pittsburgh.

We present DR-Train, the first long-term open-access dataset recording dynamic responses from in-service light rail vehicles. Specifically, the dataset contains measurements from multiple sensor channels mounted on two in-service light rail vehicles that run on a 42.2-km light rail network in the city of Pittsburgh, Pennsylvania. This dataset provides dynamic responses of in-service trains via vibration data collected by accelerometers, which enables a low-cost way of monitoring rail tracks more frequently. Such an approach will result in more reliable and economical ways to monitor rail infrastructure. The dataset also includes corresponding GPS positions of the trains, environmental conditions (including temperature, wind, weather, and precipitation), and track maintenance logs. The data, which is stored in a MAT-file format, can be conveniently loaded for various potential uses, such as validating anomaly detection and data fusion as well as investigating environmental influences on train responses.

Network Motifs Capable of Decoding Transcription Factor Dynamics.

Transcription factors (TFs) can encode the information of upstream signal in terms of its temporal activation dynamics. However, it remains unclear how different types of TF dynamics are decoded by downstream signalling networks. In this work, we studied all three-node transcriptional networks for their ability to distinguish two types of TF dynamics: amplitude modulation (AM), where the TF is activated with a constant amplitude, and frequency modulation (FM), where the TF activity displays an oscillatory behavior. We found two sets of network topologies: one set can differentially respond to AM TF signal but not to FM; the other set to FM signal but not to AM. Interestingly, there is little overlap between the two sets. We identified the prevalent topological features in each set and gave a mechanistic explanation as to why they can differentially respond to only one type of TF signal. We also found that some network topologies have a weak (not robust) ability to differentially respond to both AM and FM input signals by using different values of parameters for AM and FM cases. Our results provide a novel network mechanism for decoding different TF dynamics.

Morphogen gradient reconstitution reveals Hedgehog pathway design principles.

In developing tissues, cells estimate their spatial position by sensing graded concentrations of diffusible signaling proteins called morphogens. Morphogen-sensing pathways exhibit diverse molecular architectures, whose roles in controlling patterning dynamics and precision have been unclear. In this work, combining cell-based in vitro gradient reconstitution, genetic rewiring, and mathematical modeling, we systematically analyzed the distinctive architectural features of the Sonic Hedgehog pathway. We found that the combination of double-negative regulatory logic and negative feedback through the PTCH receptor accelerates gradient formation and improves robustness to variation in the morphogen production rate compared with alternative designs. The ability to isolate morphogen patterning from concurrent developmental processes and to compare the patterning behaviors of alternative, rewired pathway architectures offers a powerful way to understand and engineer multicellular patterning.

Synthesis of a mixed valence state Ce-MOF as an oxidase mimetic for the colorimetric detection of biothiols.

We demonstrate a facile and rapid in situ partial oxidation synthetic strategy for the fabrication of a mixed valence state Ce-MOF (MVCM) which exhibits intrinsic oxidase-like activity. Furthermore, on the basis of the excellent catalytic activity of the MCVM, a colorimetric approach for the high-throughput detection of biothiols in serum samples was established.