arXiv subjects

Kun Wang

Publications and source records attributed to Kun Wang.

At least 325 records · Page 18Linked to original sources

arXiv2024

All Nodes are created Not Equal: Node-Specific Layer Aggregation and Filtration for GNN

The ever-designed Graph Neural Networks, though opening a promising path for the modeling of the graph-structure data, unfortunately introduce two daunting obstacles to their deployment on devices. (I) Most of existing GNNs are shallow, due mostly to the over-smoothing and gradient-vanish problem as they go deeper as convolutional architectures. (II) The vast majority of GNNs adhere to the homophily assumption, where the central node and its adjacent nodes share the same label. This assumption often poses challenges for many GNNs working with heterophilic graphs. Addressing the aforementioned issue has become a looming challenge in enhancing the robustness and scalability of GNN applications. In this paper, we take a comprehensive and systematic approach to overcoming the two aforementioned challenges for the first time. We propose a Node-Specific Layer Aggregation and Filtration architecture, termed NoSAF, a framework capable of filtering and processing information from each individual nodes. NoSAF introduces the concept of "All Nodes are Created Not Equal" into every layer of deep networks, aiming to provide a reliable information filter for each layer's nodes to sieve out information beneficial for the subsequent layer. By incorporating a dynamically updated codebank, NoSAF dynamically optimizes the optimal information outputted downwards at each layer. This effectively overcomes heterophilic issues and aids in deepening the network. To compensate for the information loss caused by the continuous filtering in NoSAF, we also propose NoSAF-D (Deep), which incorporates a compensation mechanism that replenishes information in every layer of the model, allowing NoSAF to perform meaningful computations even in very deep layers.

cs.LG↗

arXiv2024

Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning

Trajectory modeling refers to characterizing human movement behavior, serving as a pivotal step in understanding mobility patterns. Nevertheless, existing studies typically ignore the confounding effects of geospatial context, leading to the acquisition of spurious correlations and limited generalization capabilities. To bridge this gap, we initially formulate a Structural Causal Model (SCM) to decipher the trajectory representation learning process from a causal perspective. Building upon the SCM, we further present a Trajectory modeling framework (TrajCL) based on Causal Learning, which leverages the backdoor adjustment theory as an intervention tool to eliminate the spurious correlations between geospatial context and trajectories. Extensive experiments on two real-world datasets verify that TrajCL markedly enhances performance in trajectory classification tasks while showcasing superior generalization and interpretability.

cs.LG↗

arXiv2024

Asteroid (101955) Bennu in the Laboratory: Properties of the Sample Collected by OSIRIS-REx

On 24 September 2023, the NASA OSIRIS-REx mission dropped a capsule to Earth containing approximately 120 g of pristine carbonaceous regolith from Bennu. We describe the delivery and initial allocation of this asteroid sample and introduce its bulk physical, chemical, and mineralogical properties from early analyses. The regolith is very dark overall, with higher-reflectance inclusions and particles interspersed. Particle sizes range from sub-micron dust to a stone about 3.5 cm long. Millimeter-scale and larger stones typically have hummocky or angular morphologies. A subset of the stones appears mottled by brighter material that occurs as veins and crusts. Hummocky stones have the lowest densities and mottled stones have the highest. Remote sensing of the surface of Bennu detected hydrated phyllosilicates, magnetite, organic compounds, carbonates, and scarce anhydrous silicates, all of which the sample confirms. We also find sulfides, presolar grains, and, less expectedly, Na-rich phosphates, as well as other trace phases. The sample composition and mineralogy indicate substantial aqueous alteration and resemble those of Ryugu and the most chemically primitive, low-petrologic-type carbonaceous chondrites. Nevertheless, we find distinct hydrogen, nitrogen, and oxygen isotopic compositions, and some of the material we analyzed is enriched in fluid-mobile elements. Our findings underscore the value of sample return, especially for low-density material that may not readily survive atmospheric entry, and lay the groundwork for more comprehensive analyses.

astro-ph.EP↗

arXiv2024

Exploring Heavy Higgs Bosons at a 100 TeV Hadron Collider within the Semi-Constrained NMSSM

In this study, we explore the detectability of heavy Higgs bosons in the $pp \to b\bar{b}H/A \to b\bar{b}t\bar{t}$ channel at a 100 TeV hadron collider within the semi-constrained Next-to-Minimal Supersymmetric Standard Model (NMSSM). We calculate their production cross sections and decay branching ratios, comparing these with simulation results from existing reference. We focus on the heavy, doublet-dominated CP-even Higgs $H$ and CP-odd Higgs $A$, with mass limits set below 10 TeV to ensure detectability. We find that at a collider with 3 ab$^{-1}$ of integrated luminosity, the potential for detecting heavy Higgs bosons varies significantly with their mass and $\tanβ$. Heavy Higgs bosons below 2 TeV are within the testable range, while those heavier than 7 TeV fall below the exclusion and discovery thresholds, rendering them undetectable. For masses between 2 and 7 TeV, heavy Higgs bosons with $\tanβ$ less than 20 can be detected, whereas those with $\tanβ$ greater than 20 are beyond the current discovery or exclusion capabilities.

hep-ph↗

arXiv2024

Artificial Chemotaxis under Electrodiffusiophoresis

Diffusiophoretic motion induced by gradients of dissolved species has enabled the manipulation of colloids over large distances, spanning hundreds of microns. Nonetheless, studies have primarily focused on simple geometries that feature 1D gradients of solutes generated by reactions or selective dissolution. Thus, our understanding of 3D diffusiophoresis remains elusive despite its importance in wide-ranging scenarios, such as cellular transport and nanofluidics. Herein, we present a strategy to generate 3D chemical gradients under electric fields. In this approach, faradaic reactions at electrodes induce global pH gradients that drive long-range transport through electrodiffusiophoresis. Simultaneously, the electric field induces local pH gradients by driving the particle's double layer far from equilibrium. As a result, while global pH gradients lead to 2D focusing away from electrodes, local pH gradients induce aggregation in the third dimension. Resulting interparticle interactions display a strong dependence on surface chemistry, and particle size. Furthermore, pH gradients can be readily tuned by adjusting the voltage and frequency of the electric field. For large Péclet numbers, we observed a chemotactic-like collapse. Remarkably, such collapse occurs without reactions at a particle's surface. By mixing particles with different sizes, we also demonstrate the emergence of non-reciprocal interactions through experiments and Brownian dynamics simulations. These findings suggest a wide array of possibilities for the dynamic assembly of materials and the design of responsive matter.

cond-mat.soft↗

arXiv2024

Fuel-optimal powered descent guidance for lunar pinpoint landing using neural networks

This paper presents a Neural Networks (NNs) based approach for designing the Fuel-Optimal Powered Descent Guidance (FOPDG) for lunar pinpoint landing. According to Pontryagin's Minimum Principle, the optimality conditions are first derived. To generate the dataset of optimal trajectories for training NNs, we formulate a parameterized system, which allows for generating each optimal trajectory by a simple propagation without using any optimization method. Then, a dataset containing the optimal state and optimal thrust vector pairs can be readily collected. Since it is challenging for NNs to approximate bang-bang (or discontinuous) type of optimal thrust magnitude, we introduce a regularisation function to the switching function so that the regularized switching function approximated by a simple NN can be used to represent the optimal thrust magnitude. Meanwhile, another two well-trained NNs are used to predict the thrust steering angle and time of flight given a flight state. Finally, numerical simulations show that the proposed method is capable of generating the FOPDG that steers the lunar lander to the desired landing site with acceptable landing errors.

math.OC↗

arXiv2024

Fuel-Optimal Trajectory Planning for Lunar Vertical Landing

In this paper, we consider a trajectory planning problem arising from a lunar vertical landing with minimum fuel consumption. The vertical landing requirement is written as a final steering angle constraint, and a nonnegative regularization term is proposed to modify the cost functional. In this way, the final steering angle constraint will be inherently satisfied according to Pontryagin's Minimum Principle. As a result, the modified optimal steering angle has to be determined by solving a transcendental equation. To this end, a transforming procedure is employed, which allows for finding the desired optimal steering angle by a simple bisection method. Consequently, the modified optimal control problem can be solved by the indirect shooting method. Finally, some numerical examples are presented to demonstrate and verify the developments of the paper.

math.OC↗

arXiv2024

ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced Adapter

The success of large language models (LLMs) has inspired an emerging research field of multimodal learning. However, a grand challenge of exploiting LLMs for multimodal learning is the size of pre-trained LLMs which are always with billions of parameters. To tackle this challenge, models such as MiniGPT-4 and LLaVA have been developed to fine-tune the pre-trained models using fewer parameters. Despite their promising performance, these models remain limited in their understanding of artistic imagery. To facilitate better artistic-understanding, in this paper, we propose ArtGPT-4, a pioneering large vision-language model tailored to address the limitations of existing models in artistic comprehension. The key innovation of ArtGPT-4 lies in its craft for the sophisticated challenge of artistic image comprehension, setting it apart from other models that overlook fine details for broader themes. Specifically, it works by integrating some specialized adapter layers into the LLM, enabling the model to more efficiently and effectively parse and interpret complex visual tokens, instead of fine-tuning the whole LLM as in the existing method. ArtGPT-4 has demonstrated its outstanding performance on the efficiency: utilizing a Tesla A100 device, its training can be completed in mere 2 hours with an image-text pair dataset comprising approximately 0.52M entries. Additionally, ArtGPT-4 has also achieved state-of-the-art performance on the ArtEmis and ArtEmis-v2.0 datasets as well as the benchmarks established in this work, lagging behind professional artists' descriptions by a negligible 0.15 points on a 6-point scale. The outstanding performance of ArtGPT-4 shows that it can render images with an artistic-understanding and convey the emotions they inspire, mirroring human interpretation. The code and the pre-trained model are accessible in \url{https://github.com/DLYuanGod/ArtGPT-4}.

cs.CL↗

arXiv2024

Tri-Perspective View Decomposition for Geometry-Aware Depth Completion

Depth completion is a vital task for autonomous driving, as it involves reconstructing the precise 3D geometry of a scene from sparse and noisy depth measurements. However, most existing methods either rely only on 2D depth representations or directly incorporate raw 3D point clouds for compensation, which are still insufficient to capture the fine-grained 3D geometry of the scene. To address this challenge, we introduce Tri-Perspective view Decomposition (TPVD), a novel framework that can explicitly model 3D geometry. In particular, (1) TPVD ingeniously decomposes the original point cloud into three 2D views, one of which corresponds to the sparse depth input. (2) We design TPV Fusion to update the 2D TPV features through recurrent 2D-3D-2D aggregation, where a Distance-Aware Spherical Convolution (DASC) is applied. (3) By adaptively choosing TPV affinitive neighbors, the newly proposed Geometric Spatial Propagation Network (GSPN) further improves the geometric consistency. As a result, our TPVD outperforms existing methods on KITTI, NYUv2, and SUN RGBD. Furthermore, we build a novel depth completion dataset named TOFDC, which is acquired by the time-of-flight (TOF) sensor and the color camera on smartphones. Project page: https://yanzq95.github.io/projectpage/TOFDC/index.html

cs.CV↗

arXiv2024

Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidance

This paper proposes a two-stage framework named ST-PAD for spatio-temporal fluid dynamics modeling in the field of earth sciences, aiming to achieve high-precision simulation and prediction of fluid dynamics through spatio-temporal physics awareness and parameter diffusion guidance. In the upstream stage, we design a vector quantization reconstruction module with temporal evolution characteristics, ensuring balanced and resilient parameter distribution by introducing general physical constraints. In the downstream stage, a diffusion probability network involving parameters is utilized to generate high-quality future states of fluids, while enhancing the model's generalization ability by perceiving parameters in various physical setups. Extensive experiments on multiple benchmark datasets have verified the effectiveness and robustness of the ST-PAD framework, which showcase that ST-PAD outperforms current mainstream models in fluid dynamics modeling and prediction, especially in effectively capturing local representations and maintaining significant advantages in OOD generations.

cs.LG↗

arXiv2024

TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation

Training on large-scale datasets can boost the performance of video instance segmentation while the annotated datasets for VIS are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific datasets, thus, it is appealing to jointly train models across the aggregation of datasets to enhance data volume and diversity. However, due to the heterogeneity in category space, as mask precision increases with the data volume, simply utilizing multiple datasets will dilute the attention of models on different taxonomies. Thus, increasing the data scale and enriching taxonomy space while improving classification precision is important. In this work, we analyze that providing extra taxonomy information can help models concentrate on specific taxonomy, and propose our model named Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation (TMT-VIS) to address this vital challenge. Specifically, we design a two-stage taxonomy aggregation module that first compiles taxonomy information from input videos and then aggregates these taxonomy priors into instance queries before the transformer decoder. We conduct extensive experimental evaluations on four popular and challenging benchmarks, including YouTube-VIS 2019, YouTube-VIS 2021, OVIS, and UVO. Our model shows significant improvement over the baseline solutions, and sets new state-of-the-art records on all benchmarks. These appealing and encouraging results demonstrate the effectiveness and generality of our approach. The code is available at https://github.com/rkzheng99/TMT-VIS .

cs.CV↗

arXiv2024

Causal-Story: Local Causal Attention Utilizing Parameter-Efficient Tuning For Visual Story Synthesis

The excellent text-to-image synthesis capability of diffusion models has driven progress in synthesizing coherent visual stories. The current state-of-the-art method combines the features of historical captions, historical frames, and the current captions as conditions for generating the current frame. However, this method treats each historical frame and caption as the same contribution. It connects them in order with equal weights, ignoring that not all historical conditions are associated with the generation of the current frame. To address this issue, we propose Causal-Story. This model incorporates a local causal attention mechanism that considers the causal relationship between previous captions, frames, and current captions. By assigning weights based on this relationship, Causal-Story generates the current frame, thereby improving the global consistency of story generation. We evaluated our model on the PororoSV and FlintstonesSV datasets and obtained state-of-the-art FID scores, and the generated frames also demonstrate better storytelling in visuals.

cs.CV↗

arXiv2024

AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization

Neural Radiance Fields (NeRF) have shown promise in generating realistic novel views from sparse scene images. However, existing NeRF approaches often encounter challenges due to the lack of explicit 3D supervision and imprecise camera poses, resulting in suboptimal outcomes. To tackle these issues, we propose AltNeRF -- a novel framework designed to create resilient NeRF representations using self-supervised monocular depth estimation (SMDE) from monocular videos, without relying on known camera poses. SMDE in AltNeRF masterfully learns depth and pose priors to regulate NeRF training. The depth prior enriches NeRF's capacity for precise scene geometry depiction, while the pose prior provides a robust starting point for subsequent pose refinement. Moreover, we introduce an alternating algorithm that harmoniously melds NeRF outputs into SMDE through a consistence-driven mechanism, thus enhancing the integrity of depth priors. This alternation empowers AltNeRF to progressively refine NeRF representations, yielding the synthesis of realistic novel views. Extensive experiments showcase the compelling capabilities of AltNeRF in generating high-fidelity and robust novel views that closely resemble reality.

cs.CV↗

arXiv2024

Neural-Network-Based Optimal Guidance for Lunar Vertical Landing

This paper addresses an optimal guidance problem concerning the vertical landing of a lunar lander with the objective of minimizing fuel consumption. The vertical landing imposes a final attitude constraint, which is treated as a final control constraint. To handle this constraint, we propose a nonnegative small regularization term to augment the original cost functional. This ensures the satisfaction of the final control constraint in accordance with Pontryagin's Minimum Principle. By leveraging the necessary conditions for optimality, we establish a parameterized system that facilitates the generation of numerous optimal trajectories, which contain the nonlinear mapping from the flight state to the optimal guidance command. Subsequently, a neural network is trained to approximate such mapping. Finally, numerical examples are presented to validate the proposed method.

math.OC↗

arXiv2024

Dueling Over Dessert, Mastering the Art of Repeated Cake Cutting

We consider the setting of repeated fair division between two players, denoted Alice and Bob, with private valuations over a cake. In each round, a new cake arrives, which is identical to the ones in previous rounds. Alice cuts the cake at a point of her choice, while Bob chooses the left piece or the right piece, leaving the remainder for Alice. We consider two versions: sequential, where Bob observes Alice's cut point before choosing left/right, and simultaneous, where he only observes her cut point after making his choice. The simultaneous version was first considered by Aumann and Maschler (1995). We observe that if Bob is almost myopic and chooses his favorite piece too often, then he can be systematically exploited by Alice through a strategy akin to a binary search. This strategy allows Alice to approximate Bob's preferences with increasing precision, thereby securing a disproportionate share of the resource over time. We analyze the limits of how much a player can exploit the other one and show that fair utility profiles are in fact achievable. Specifically, the players can enforce the equitable utility profile of $(1/2, 1/2)$ in the limit on every trajectory of play, by keeping the other player's utility to approximately $1/2$ on average while guaranteeing they themselves get at least approximately $1/2$ on average. We show this theorem using a connection with Blackwell approachability. Finally, we analyze a natural dynamic known as fictitious play, where players best respond to the empirical distribution of the other player. We show that fictitious play converges to the equitable utility profile of $(1/2, 1/2)$ at a rate of $O(1/\sqrt{T})$.

cs.GT↗

arXiv2024

Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts

In this paper, we address the issue of modeling and estimating changes in the state of the spatio-temporal dynamical systems based on a sequence of observations like video frames. Traditional numerical simulation systems depend largely on the initial settings and correctness of the constructed partial differential equations (PDEs). Despite recent efforts yielding significant success in discovering data-driven PDEs with neural networks, the limitations posed by singular scenarios and the absence of local insights prevent them from performing effectively in a broader real-world context. To this end, this paper propose the universal expert module -- that is, optical flow estimation component, to capture the evolution laws of general physical processes in a data-driven fashion. To enhance local insight, we painstakingly design a finer-grained physical pipeline, since local characteristics may be influenced by various internal contextual information, which may contradict the macroscopic properties of the whole system. Further, we harness currently popular neural discrete learning to unveil the underlying important features in its latent space, this process better injects interpretability, which can help us obtain a powerful prior over these discrete random variables. We conduct extensive experiments and ablations to demonstrate that the proposed framework achieves large performance margins, compared with the existing SOTA baselines.

cs.LG↗

arXiv2024

EXGC: Bridging Efficiency and Explainability in Graph Condensation

Graph representation learning on vast datasets, like web data, has made significant strides. However, the associated computational and storage overheads raise concerns. In sight of this, Graph condensation (GCond) has been introduced to distill these large real datasets into a more concise yet information-rich synthetic graph. Despite acceleration efforts, existing GCond methods mainly grapple with efficiency, especially on expansive web data graphs. Hence, in this work, we pinpoint two major inefficiencies of current paradigms: (1) the concurrent updating of a vast parameter set, and (2) pronounced parameter redundancy. To counteract these two limitations correspondingly, we first (1) employ the Mean-Field variational approximation for convergence acceleration, and then (2) propose the objective of Gradient Information Bottleneck (GDIB) to prune redundancy. By incorporating the leading explanation techniques (e.g., GNNExplainer and GSAT) to instantiate the GDIB, our EXGC, the Efficient and eXplainable Graph Condensation method is proposed, which can markedly boost efficiency and inject explainability. Our extensive evaluations across eight datasets underscore EXGC's superiority and relevance. Code is available at https://github.com/MangoKiller/EXGC.

cs.LG↗

arXiv2024

Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness

Graph Neural Networks (GNNs) excel in various graph learning tasks but face computational challenges when applied to large-scale graphs. A promising solution is to remove non-essential edges to reduce the computational overheads in GNN. Previous literature generally falls into two categories: topology-guided and semantic-guided. The former maintains certain graph topological properties yet often underperforms on GNNs due to low integration with neural network training. The latter performs well at lower sparsity on GNNs but faces performance collapse at higher sparsity levels. With this in mind, we take the first step to propose a new research line and concept termed Graph Sparse Training (GST), which dynamically manipulates sparsity at the data level. Specifically, GST initially constructs a topology & semantic anchor at a low training cost, followed by performing dynamic sparse training to align the sparse graph with the anchor. We introduce the Equilibria Sparsification Principle to guide this process, effectively balancing the preservation of both topological and semantic information. Ultimately, GST produces a sparse graph with maximum topological integrity and no performance degradation. Extensive experiments on 6 datasets and 5 backbones showcase that GST (I) identifies subgraphs at higher graph sparsity levels (1.67%~15.85% $\uparrow$) than state-of-the-art sparsification methods, (II) preserves more key spectral properties, (III) achieves 1.27-3.42$\times$ speedup in GNN inference and (IV) successfully helps graph adversarial defense and graph lottery tickets.

cs.LG↗