Search for: All records

This paper studies the problem of modeling multi-agent dynamical systems, where agents could interact mutually to influence their behaviors. Recent research predominantly uses geometric graphs to depict these mutual interactions, which are then captured by powerful graph neural networks (GNNs). However, predicting interacting dynamics in challenging scenarios such as out-of-distribution shift and complicated underlying rules remains unsolved. In this paper, we propose a new approach named Prototypical Graph ODE (PGODE) to address the problem. The core of PGODE is to incorporate prototype decomposition from contextual knowledge into a continuous graph ODE framework. Specifically, PGODE employs representation disentanglement and system parameters to extract both object-level and system-level contexts from historical trajectories, which allows us to explicitly model their independent influence and thus enhances the generalization capability under system changes. Then, we integrate these disentangled latent representations into a graph ODE model, which determines a combination of various interacting prototypes for enhanced model expressivity. The entire model is optimized using an end-to-end variational inference framework to maximize the likelihood. Extensive experiments in both in-distribution and out-of-distribution settings validate the superiority of PGODE compared to various baselines. 

Plasmonic metasurfaces with adjustable optical responses can be achieved through phase change materials (PCMs) with high optical contrast. However, the on–off behavior of the phase change process results in the binary response of photonic devices, limiting the applications to the two-stage modulation. In this work, we propose a reconfigurable metasurface emitter based on a gold nanorod array on a VO2 thin film for achieving continuously tunable narrowband thermal emission. The electrode line connecting the center of each nanorod not only enables emission excitation electrically but also activates the phase transition of VO2 beneath the array layer due to Joule heating. The change in the dielectric environment due to the VO2 phase transition results in the modulation of emissivity from the plasmonic metasurfaces. The device performances regarding critical geometrical parameters are analyzed based on a fully coupled electro-thermo-optical finite element model. This new metasurface structure extends the binary nature of PCM based modulations to continuous reconfigurability and provides new possibilities toward smart metasurface emitters, reflectors, and other nanophotonic devices. 

Multi-agent dynamical systems refer to scenarios where multiple units (aka agents) interact with each other and evolve collectively over time. For instance, people’s health conditions are mutually influenced. Receiving vaccinations not only strengthens the longterm health status of one unit but also provides protection for those in their immediate surroundings. To make informed decisions in multi-agent dynamical systems, such as determining the optimal vaccine distribution plan, it is essential for decision-makers to estimate the continuous-time counterfactual outcomes. However, existing studies of causal inference over time rely on the assumption that units are mutually independent, which is not valid for multi-agent dynamical systems. In this paper, we aim to bridge this gap and study how to estimate counterfactual outcomes in multi-agent dynamical systems. Causal inference in a multi-agent dynamical system has unique challenges: 1) Confounders are timevarying and are present in both individual unit covariates and those of other units; 2) Units are affected by not only their own but also others’ treatments; 3) The treatments are naturally dynamic, such as receiving vaccines and boosters in a seasonal manner. To this end, we model a multi-agent dynamical system as a graph and propose a novel model called CF-GODE (CounterFactual Graph Ordinary Differential Equations). CF-GODE is a causal model that estimates continuous-time counterfactual outcomes in the presence of inter-dependencies between units. To facilitate continuous-time estimation,we propose Treatment-Induced GraphODE, a novel ordinary differential equation based on graph neural networks (GNNs), which can incorporate dynamical treatments as additional inputs to predict potential outcomes over time. To remove confounding bias, we propose two domain adversarial learning based objectives that learn balanced continuous representation trajectories, which are not predictive of treatments and interference. We further provide theoretical justification to prove their effectiveness. Experiments on two semi-synthetic datasets confirm that CF-GODE outperforms baselines on counterfactual estimation. We also provide extensive analyses to understand how our model works. 

Nanoantennas and their arrays (metasurfaces) provide a versatile platform for controlling the coherence of thermal emission. Conventional designs rely on global heating, which impedes emission efficiency and on-chip integration. In this work, we propose an electrically driven metasurface composed of a Yagi-Uda nanoantenna array interconnected by S-shaped electrode wires, which enables the concurrent manipulation of thermal emission spectrally and directionally. A direct simulation approach based on the Wiener-chaos expansion method is employed for quantitative analysis. Our metasurface device exhibits a narrowband emission with high directivity, which is one order higher than that of a single nanorod antenna case. The modeling framework established in this work opens a promising route for realizing coherent mid-infrared emission by metasurfaces. 

Semantic relationships, such as hyponym–hypernym, cause–effect, meronym–holonym etc., between a pair of entities in a sentence are usually reflected through syntactic patterns. Automatic extraction of such patterns benefits several downstream tasks, including, entity extraction, ontology building, and question answering. Unfortunately, automatic extraction of such patterns has not yet received much attention from NLP and information retrieval researchers. In this work, we propose an attention-based supervised deep learning model, ASPER, which extracts syntactic patterns between entities exhibiting a given semantic relation in the sentential context. We validate the performance of ASPER on three distinct semantic relations—hyponym–hypernym, cause–effect, and meronym–holonym on six datasets. Experimental results show that for all these semantic relations, ASPER can automatically identify a collection of syntactic patterns reflecting the existence of such a relation between a pair of entities in a sentence. In comparison to the existing methodologies of syntactic pattern extraction, ASPER’s performance is substantially superior.