Indoor temperature prediction is crucial for decision-making in central heating systems. Beyond accuracy, predictions shall be interpretable, i.e. conform to the laws of physics; otherwise, it may lead to system failures or unsafe conditions. However, deep learning models often face criticism regarding interpretability, which limits their application in such settings. To this end, we propose a Spatio-Temporal Consistency enhanced Differential Network (CONST) for interpretable indoor temperature prediction. Our approach mainly consists of a differential predictive module and a spatio-temporal consistency module. Modeling the influential factors, the first module solves the issue of multicollinearity through the differential operation. Considering the heterogeneity of global and local data distributions, the second module characterizes the temporal and spatial consistency to mine the universal pattern by multi-task learning, thereby improving the prediction interpretability. Besides, we propose a set of interpretability metrics to overcome the drawbacks of partial dependence plot metric, which are more practical, zero-centered, flexible, and numerical. We conclude experiments on a real-world dataset with four heating stations. The results demonstrate the advantages of our approach over various baselines, where the interpretability can be improved by more than 8 times on cRPD while maintaining high accuracy. We developed CONST on the SmartHeat system, providing hourly indoor temperature forecasts for 13 heating stations in northern China.
论文检索
输入标题、作者或关键词，从 3,314 篇学术成果中精准定位
Product assortment selection is a critical challenge facing physical retailers. Effectively aligning inventory with the preferences of shoppers can increase sales and decrease out-of-stocks. However, in real-world settings the problem is challenging due to the combinatorial explosion of product assortment possibilities. Consumer preferences are typically heterogeneous across space and time, making inventory-preference alignment challenging. Additionally, existing strategies rely on syndicated data, which tends to be aggregated, low resolution, and suffer from high latency. To solve these challenges, we introduce a real-time recommendation system, which we call EdgeRec3D. Our system utilizes recent advances in 3D computer vision for perception and automatic, fine grained sales estimation. These perceptual components run on the edge of the network and facilitate real-time reward signals. Additionally, we develop a Bayesian payoff model to account for noisy estimates from 3D LIDAR data. We rely on spatial clustering to allow the system to adapt to heterogeneous consumer preferences, and a graph-based candidate generation algorithm to address the combinatorial search problem. We test our system in real-world stores across two, 6-8 week A/B tests with beverage products and demonstrate a 35% and 27% increase in sales respectively. Finally, we monitor the deployed system for a period of 28 weeks with an observational study and show a 9.4% increase in sales.
Incorporating Euclidean symmetries (e.g. rotation equivariance) as inductive biases into graph neural networks has improved their generalization ability and data efficiency in unbounded physical dynamics modeling. However, in various scientific and engineering applications, the symmetries of dynamics are frequently discrete due to the boundary conditions. Thus, existing GNNs either over-look necessary symmetry, resulting in suboptimal representation ability, or impose excessive equivariance, which fails to generalize to unobserved symmetric dynamics. In this work, we propose a general Discrete Equivariant Graph Neural Network (DEGNN) that guarantees equivariance to a given discrete point group. Specifically, we show that such discrete equivariant message passing could be constructed by transforming geometric features into permutation-invariant embeddings. Through relaxing continuous equivariant constraints, DEGNN can employ more geometric feature combinations to approximate unobserved physical object interaction functions. Two implementation approaches of DEGNN are proposed based on ranking or pooling permutation-invariant functions. We apply DEGNN to various physical dynamics, ranging from particle, molecular, crowd to vehicle dynamics. In twenty scenarios, DEGNN significantly outperforms existing state-of-the-art approaches. Moreover, we show that DEGNN is data efficient, learning with less data, and can generalize across scenarios such as unobserved orientation.
Maritime traffic management increasingly relies on vessel position information provided by terrestrial and satellite networks of the Automatic Identification System (AIS). Unfortunately, the problem of missing AIS data can lead to long-term gaps in vessel trajectory, raising corresponding security concerns regarding collision risks and illicit activities. Existing imputation approaches are often constrained by vehicle-based low-sampling trajectories, hindering their ability to address unique characteristics of maritime transportation systems and long-term missing scenarios. To tackle these challenges, we propose a novel generative framework for long-term vessel trajectory imputation. Our framework considers irregular tracks of vessels, which differ from those of cars due to the absence of a structured road network, and ensures the continuity of multi-point imputed trajectories. Specifically, we first utilize a pre-trained trajectory embedding block to capture patterns of vessel movements. Subsequently, we introduce a diffusion-based model for generating missing trajectories, where observed trajectory modeling with transformer encoding architecture and embeddings of both historical vessel trajectory and external factors serve as conditional information. In particular, we design a physics-guided discriminator in the training stage, which imposes kinematic constraints between locations and angles to improve the continuity of the imputed trajectories. Comprehensive experiments and analysis on a real-world AIS dataset confirm the effectiveness of our proposed approach.
Consistent bi-directional inferences are the key for many machine learning applications. Without consistency, inverse learning-based inferences can cause fuzzy images, erroneous control signals, and cascading failure in SCADA systems. Since standard deep neural networks (DNNs) are not inherently invertible to offer consistency, some past methods reconstruct DNN architecture analytically for one-to-one correspondence but compromise key features such as universal approximation. Other work maintains the capability of universal approximation in DNNs via iterative numerical approximation. However, these methods limit their applications significantly due to Lipschitz conditions and issues of numerical convergence. The dilemma of the analytical and numerical methods is the incompatibility between nonlinear layer compositions and bijective function construction for inverse modeling. Based on the observation, we propose decomposed-invertible-pathway DNNs (DipDNN). It relaxes the redundant reconstruction of nested DNN in the former methods and eases the Lipschitz constraint. As a result, we strictly guarantee the consistency of global inverse modeling without harming DNN's capability for universal approximation. As numerical stability and generalizability are keys for controlling critical infrastructures, we integrate contractive property with a parallel structure for inductive biases, leading to stable performance. Numerical results show that DipDNN performs significantly better than past methods, thanks to its enforcement of inverse consistency, numerical stability, and physical regularization.
In this paper, we study cascading failures in power grids through the lens of information diffusion models. Similar to the spread of rumors or influence in an online social network, it has been observed that failures (outages) in a power grid can spread contagiously, driven by viral spread mechanisms. We employ a stochastic diffusion model that is Markovian (memoryless) and local (the activation of one node, i.e., transmission line, can only be caused by its neighbors). Our model integrates viral diffusion principles with physics-based concepts, by correlating the diffusion weights (contagion probabilities between transmission lines) with the hyperparametric Information Cascades (IC) model. We show that this diffusion model can be learned from traces of cascading failures, enabling accurate modeling and prediction of failure propagation. This approach facilitates actionable information through well-understood and efficient graph analysis methods and graph diffusion simulations. Furthermore, by leveraging the hyperparametric model, we can predict diffusion and mitigate the risks of cascading failures even in unseen grid configurations, whereas existing methods falter due to a lack of training data. Extensive experiments based on a benchmark power grid and simulations therein show that our approach effectively captures the failure diffusion phenomena and guides decisions to strengthen the grid, reducing the risk of large-scale cascading failures. Additionally, we characterize our model's sample complexity, improving upon the existing bound.
Modeling the evolution of physical dynamics is a foundational problem in science and engineering, and it is regarded as the modeling of an operator mapping between infinite-dimensional functional spaces. Operator learning methods, learning the underlying infinite-dimensional operator in a high-dimensional latent space, have shown significant potential in modeling physical dynamics. However, there remains insufficient research on how to approximate an infinite-dimensional operator using a finite-dimensional parameter space. Inappropriate dimensionality representation of the underlying operator leads to convergence difficulties, decreasing generalization capability, and violating the physical consistency. To address the problem, we present Neural Manifold Operator (NMO) to learn the invariant subspace with the intrinsic dimension to parameterize infinite-dimensional underlying operators. NMO achieves state-of-the-art performance in statistical and physical metrics and gains 23.35% average improvement on three real-world scenarios and four equation-governed scenarios across a wide range of multi-disciplinary fields. Our paradigm has demonstrated universal effectiveness across various model structure implementations, including Multi-Layer Perceptron, Convolutional Neural Networks, and Transformers. Experimentally, we prove that the intrinsic dimension calculated by our paradigm is the optimal dimensional representation of the underlying operators. We release our code at https://github.com/AI4EarthLab/Neural-Manifold-Operators.
Learning from Emergence: A Study on Proactively Inhibiting the Monosemantic Neurons of Artificial Neural Networks
PDF ↗Recently, emergence has received widespread attention from the research community along with the success of large-scale models. Different from the literature, we hypothesize a key factor that promotes the performance during the increase of scale: the reduction of monosemantic neurons that can only form one-to-one correlations with specific features. Monosemantic neurons tend to be sparser and have negative impacts on the performance in large models. Inspired by this insight, we propose an intuitive idea to identify monosemantic neurons and inhibit them. However, achieving this goal is a non-trivial task as there is no unified quantitative evaluation metric and simply banning monosemantic neurons does not promote polysemanticity in neural networks. Therefore, we first propose a new metric to measure the monosemanticity of neurons with the guarantee of efficiency for online computation, then introduce a theoretically supported method to suppress monosemantic neurons and proactively promote the ratios of polysemantic neurons in training neural networks. We validate our conjecture that monosemanticity brings about performance change at different model scales on a variety of neural networks and benchmark datasets in different areas, including language, image, and physics simulation tasks. Further experiments validate our analysis and theory regarding the inhibition of monosemanticity.
Predicting Long-term Dynamics of Complex Networks via Identifying Skeleton in Hyperbolic Space
PDF ↗Learning complex network dynamics is fundamental for understanding, modeling, and controlling real-world complex systems. Though great efforts have been made to predict the future states of nodes on networks, the capability of capturing long-term dynamics remains largely limited. This is because they overlook the fact that long-term dynamics in complex network are predominantly governed by their inherent low-dimensional manifolds, i.e., skeletons. Therefore, we propose the Dynamics-Invariant Skeleton Neural Network (DiskNet), which identifies skeletons of complex networks based on the renormalization group structure in hyperbolic space to preserve both topological and dynamics properties. Specifically, we first condense complex networks with various dynamics into simple skeletons through physics-informed hyperbolic embeddings. Further, we design graph neural ordinary differential equations to capture the condensed dynamics on the skeletons. Finally, we recover the skeleton networks and dynamics to the original ones using a degree-based super-resolution module. Extensive experiments across three representative dynamics as well as five real-world and two synthetic networks demonstrate the superior performances of the proposed DiskNet, which outperforms the state-of-the-art baselines by an average of 10.18% in terms of long-term prediction accuracy. Code for reproduction is available at: https://github.com/tsinghua-fib-lab/DiskNet.
Urban mobility undergoes a profound decline in the aftermath of a disaster, subsequently exhibiting a complex recovery trajectory. Effectively capturing and predicting this dynamic recovery process holds paramount importance for devising more efficient post-disaster recovery strategies, such as resource allocation to areas with protracted recovery periods. Existing models for post-disaster mobility recovery predominantly employ basic mathematical methods, which are strongly based on simplifying assumptions, and their limited parameters restrict their capacity to fully capture the mobility recovery patterns. In response to this gap, we introduce the Coupled Dynamic Graph ODE Network (CDGON) to model the intricate dynamics of post-disaster mobility recovery. Our model seamlessly integrates existing physical knowledge pertaining to post-disaster mobility recovery and incorporates the nuanced interactions between intra-regional and inter-regional population flows. Extensive experimental results demonstrate the efficiency of our model in capturing the dynamic recovery patterns of urban population mobility in post-disaster scenarios, surpassing the capabilities of current dynamic graph prediction models.
The development of the smart manufacturing trend includes the integration of Artificial Intelligence technologies into industrial processes. One example of such implementation is deep learning models that diagnose the current state of a technological process. Recent studies have demonstrated that small data perturbations, named adversarial attacks, can significantly affect the correct predictions of such models. This fact is critical in industrial systems, where AI-based decisions can be made to manage physical equipment. In this work, we present a system which can help to evaluate the robustness of technological process diagnosis models to adversarial attacks, as well as consider protection options. We briefly review the system's modules and also consider some useful applications. Our demo video is available at: http://tinyurl.com/3by9zcj5
Partially observable Markov decision processes (POMDPs) provide a flexible representation for real-world decision and control problems. However, POMDPs are notoriously difficult to solve, especially when the state and observation spaces are continuous or hybrid, which is often the case for physical systems. While recent online sampling-based POMDP algorithms that plan with observation likelihood weighting have shown practical effectiveness, a general theory characterizing the approximation error of the particle filtering techniques that these algorithms use has not previously been proposed. Our main contribution is bounding the error between any POMDP and its corresponding finite sample particle belief MDP (PB-MDP) approximation. This fundamental bridge between PB-MDPs and POMDPs allows us to adapt any sampling-based MDP algorithm to a POMDP by solving the corresponding particle belief MDP, thereby extending the convergence guarantees of the MDP algorithm to the POMDP. Practically, this is implemented by using the particle filter belief transition model as the generative model for the MDP solver. While this requires access to the observation density model from the POMDP, it only increases the transition sampling complexity of the MDP solver by a factor of O(C), where C is the number of particles. Thus, when combined with sparse sampling MDP algorithms, this approach can yield algorithms for POMDPs that have no direct theoretical dependence on the size of the state and observation spaces. In addition to our theoretical contribution, we perform five numerical experiments on benchmark POMDPs to demonstrate that a simple MDP algorithm adapted using PB-MDP approximation, Sparse-PFT, achieves performance competitive with other leading continuous observation POMDP solvers.
DP-Font: Chinese Calligraphy Font Generation Using Diffusion Model and Physical Information Neural Network
PDF ↗As a typical visual art form, Chinese calligraphy has a long history and aesthetic value. However, current methods for generating Chinese fonts still struggle with complex character shapes and lack personalized writing styles. To address these issues, we propose a font generation method for Chinese Calligraphy based on diffusion model incorporating physical information neural network (PINN), which is named DP-Font. Firstly, the multi-attribute guidance is combined to guide the generation process of the diffusion model and introduce the critical constraint of stroke order in Chinese characters, aiming to significantly improve the quality of the generated results. We then incorporate physical constraints into the neural network loss function, utilizing physical equations to provide in-depth guidance and constraints on the learning process. By learning the movement rule of the nib and the diffusion pattern of the ink, DP-Font can generate personalized calligraphy styles. The generated fonts are very close to the calligraphers' works. Compared with existing deep learning-based techniques, DP-Font has made significant progress in enhancing the physical plausibility of the model, generating more realistic and high-quality results.
A Survival Guide for Iranian Women Prescribed by Iranian Women: Participatory AI to Investigate Intimate Partner Physical Violence in Iran
PDF ↗Intimate Partner Violence (IPV) is a global problem affecting more than 2 billion women worldwide. Our paper makes two key contributions. First, via a substantial corpus of 53,220 comments to 1,563 Intimate Partner Physical Violence (IPPV) posts gleaned from more than 10 million comments posted on 523,232 posts on a popular parental health website in Iran, we present the first-ever computational analysis of user comments on accounts of IPPV in Iran. We harness large language models and participatory AI and tackle extreme class imbalance and other linguistic challenges that arise from tackling low-resource languages to shed light on the gender struggles of a country with documented stark gender inequality. With active input from a woman with a history of advocacy for social rights and grounded in Iranian culture, we characterize comments on IPPV into three broad categories: empathy, confront, and conform, and analyze their distribution. Second, we release an important dataset of 3,400 comments on IPPV posts.
Streamflow Prediction with Uncertainty Quantification for Water Management: A Constrained Reasoning and Learning Approach
PDF ↗Predicting the spatiotemporal variation in streamflow along with uncertainty quantification enables decision-making for sustainable management of scarce water resources. Process-based hydrological models (aka physics-based models) are based on physical laws, but use simplifying assumptions which can lead to poor accuracy. Data-driven approaches offer a powerful alternative, but they require large amount of training data and tend to produce predictions that are inconsistent with physical laws. This paper studies a constrained reasoning and learning (CRL) approach where physical laws represented as logical constraints are integrated as a layer in the deep neural network. To address small data setting, we develop a theoretically-grounded training approach to improve the generalization accuracy of deep models. For uncertainty quantification, we combine the synergistic strengths of Gaussian processes (GPs) and deep temporal models by passing the learned latent representation as input to a standard distance-based kernel. Experiments on multiple real-world datasets demonstrate the effectiveness of both CRL and GP with deep kernel approaches over strong baseline methods.
Fitness Activity Recognition Using a Novel Pressure Sensing Mat and Machine Learning for the Future of Accessible Training
PDF ↗Physical inactivity is still a major problem contributing to a growing public health crisis despite a fast-expanding body of technological solutions and wellness research around fitness training. The inaccessibility of professional fitness training remains a leading cause of this gap for reasons encompassing socioeconomic factors, cultural and demographic barriers, and more recently the threat of global pandemics that disrupt traditional modes of staying physically active. Previous lines of work have explored using AI for fitness activity recognition from various sensing modalities such as computer vision, wearable sensors, and force and pressure sensors. However, these works are limited by their feasibility, deployability, and accessibility in real-world scenarios, in addition to the technical challenges faced by each modality for accurate and reliable activity recognition. In this paper, we propose an accessible system for gym activity recognition and correction focusing on foundational fitness activities using ML and a novel pressure sensing mat, and validate its deployability in a real-world use case in a natural gym setting. We present the detailed and previously under-investigated Centre of Pressure (COP) profile of four main gym activities in terms of several COP-related metrics specifically as targets for ML-based recognition tasks. Based on this, we identify COP displacement and COP balance measures as important features for ML-based recognition of these fitness activities for future research in this area. Furthermore, we compare the performance of several ML models in the activity recognition task, achieving 98.5% recognition accuracy using ML models suitable for real-time deployment. Finally, we demonstrate the feasibility of our system in a live real-world with use case in a natural gym environment.
Accurate streamflow prediction is critical for ensuring water supply and detecting floods, while also providing essential hydrological inputs for other scientific models in fields such as climate and agriculture. Recently, deep learning models have been shown to achieve state-of-the-art regionalization performance by building a global hydrologic model. These models predict streamflow given catchment physical characteristics and weather forcing data. However, these models are only focused on gauged basins and cannot adapt to ungaugaed basins, i.e., basins without training data. Prediction in Ungauged Basins (PUB) is considered one of the most important challenges in hydrology, as most basins in the United States and around the world have no observations. In this work, we propose a meta-transfer learning approach by enhancing imperfect physics equations that facilitate model adaptation. Intuitively, physical equations can often be used to regularize deep learning models to achieve robust regionalization performance under gauged scenarios, but they can be inaccurate due to the simplified representation of physics. We correct such uncertainty in physical equation by residual approximation and let these corrected equations guide the model training process. We evaluated the proposed method for predicting daily streamflow on the catchment attributes and meteorology for large-sample studies (CAMELS) dataset. The experiment results on hydrological data over 19 years demonstrate the effectiveness of the proposed method in ungauged scenarios.
This paper introduces a novel trajectory prediction approach for autonomous vehicles (AVs), adeptly addressing the challenges of missing observations and the need for adherence to physical laws in real-world driving environments. This study proposes a hierarchical two-stage trajectory prediction model for AVs. In the first stage we propose the Wavelet Reconstruction Network, an innovative tool expertly crafted for reconstructing missing observations, offering optional integration with state-of-the-art models to enhance their robustness. Additionally, the second stage of the model features the Wave Fusion Encoder, a quantum mechanics-inspired innovation for sophisticated vehicle interaction modeling. By incorporating the Kinematic Bicycle Model, we ensure that our predictions align with realistic vehicular kinematics. Complementing our methodological advancements, we introduce MoCAD-missing, a comprehensive real-world traffic dataset, alongside enhanced versions of the NGSIM and HighD datasets, designed to facilitate rigorous testing in environments with missing observations. Extensive evaluations demonstrate that our approach markedly outperforms existing methods, achieving high accuracy even in scenarios with up to 75% missing observations.
GRASP: A Novel Benchmark for Evaluating Language GRounding and Situated Physics Understanding in Multimodal Language Models
PDF ↗This paper presents GRASP, a novel benchmark to evaluate the language grounding and physical understanding capabilities of video-based multimodal large language models (LLMs). This evaluation is accomplished via a two-tier approach leveraging Unity simulations. The first level tests for language grounding by assessing a model's ability to relate simple textual descriptions with visual information. The second level evaluates the model's understanding of "Intuitive Physics" principles, such as object permanence and continuity. In addition to releasing the benchmark, we use it to evaluate several state-of-the-art multimodal LLMs. Our evaluation reveals significant shortcomings in the language grounding and intuitive physics capabilities of these models. Although they exhibit at least some grounding capabilities, particularly for colors and shapes, these capabilities depend heavily on the prompting strategy. At the same time, all models perform below or at the chance level of 50% in the Intuitive Physics tests, while human subjects are on average 80% correct. These identified limitations underline the importance of using benchmarks like GRASP to monitor the progress of future models in developing these competencies.
Towards Geometric Normalization Techniques in SE(3) Equivariant Graph Neural Networks for Physical Dynamics Simulations
PDF ↗SE(3) equivariance is a fundamental property that is highly desirable to maintain in physical dynamics modeling. This property ensures neural outputs to remain robust when the inputs are translated or rotated. Recently, there have been several proposals for SE(3) equivariant graph neural networks (GNNs) that have shown promising results in simulating particle dynamics. However, existing works have neglected an important issue that current SE(3) equivariant GNNs cannot scale to large particle systems. Although some simple normalization techniques are already in use to stabilize the training dynamics of equivariant graph networks, they actually break the SE(3) equivariance of the architectures. In this work, we first show the numerical instability of training equivariant GNNs on large particle systems and then analyze some existing normalization strategies adopted in modern works. We propose a new normalization layer called GeoNorm, which can satisfy the SE(3) equivariance and simultaneously stabilize the training process. We conduct comprehensive experiments on N-body system simulation tasks with larger particle system sizes. The experimental results demonstrate that GeoNorm successfully preserves the SE(3) equivariance compared to baseline techniques and stabilizes the training dynamics of SE(3) equivariant GNNs on large systems.