arXiv subjects

Tian Xie

Publications and source records attributed to Tian Xie.

At least 73 records · Page 4Linked to original sources

arXiv2024

Learning under Imitative Strategic Behavior with Unforeseeable Outcomes

Machine learning systems have been widely used to make decisions about individuals who may behave strategically to receive favorable outcomes, e.g., they may genuinely improve the true labels or manipulate observable features directly to game the system without changing labels. Although both behaviors have been studied (often as two separate problems) in the literature, most works assume individuals can (i) perfectly foresee the outcomes of their behaviors when they best respond; (ii) change their features arbitrarily as long as it is affordable, and the costs they need to pay are deterministic functions of feature changes. In this paper, we consider a different setting and focus on imitative strategic behaviors with unforeseeable outcomes, i.e., individuals manipulate/improve by imitating the features of those with positive labels, but the induced feature changes are unforeseeable. We first propose a Stackelberg game to model the interplay between individuals and the decision-maker, under which we examine how the decision-maker's ability to anticipate individual behavior affects its objective function and the individual's best response. We show that the objective difference between the two can be decomposed into three interpretable terms, with each representing the decision-maker's preference for a certain behavior. By exploring the roles of each term, we theoretically illustrate how a decision-maker with adjusted preferences may simultaneously disincentivize manipulation, incentivize improvement, and promote fairness. Such theoretical results provide a guideline for decision-makers to inform better and socially responsible decisions in practice.

cs.AI↗

arXiv2024

Adaptive Joint Estimation of Temporal Vertex and Edge Signals

The adaptive estimation of coexisting temporal vertex (node) and edge signals on graphs is a critical task when a change in edge signals influences the temporal dynamics of the vertex signals. However, the current Graph Signal Processing algorithms mostly consider only the signals existing on the graph vertices and have neglected the fact that signals can reside on the edges. We propose an Adaptive Joint Vertex-Edge Estimation (AJVEE) algorithm for jointly estimating time-varying vertex and edge signals through a time-varying regression, incorporating both vertex signal filtering and edge signal filtering. Accompanying AJVEE is a newly proposed Adaptive Least Mean Square procedure based on the Hodge Laplacian (ALMS-Hodge), which is inspired by classical adaptive filters combining simplicial filtering and simplicial regression. AJVEE is able to operate jointly on the vertices and edges by merging two ALMS-Hodge specified on the vertices and edges into a unified formulation. A more generalized case extending AJVEE beyond the vertices and edges is being discussed. Experimenting on real-world traffic networks and population mobility networks, we have confirmed that our proposed AJVEE algorithm could accurately and jointly track time-varying vertex and edge signals on graphs.

cs.SI↗

arXiv2024

ECGN: A Cluster-Aware Approach to Graph Neural Networks for Imbalanced Classification

Classifying nodes in a graph is a common problem. The ideal classifier must adapt to any imbalances in the class distribution. It must also use information in the clustering structure of real-world graphs. Existing Graph Neural Networks (GNNs) have not addressed both problems together. We propose the Enhanced Cluster-aware Graph Network (ECGN), a novel method that addresses these issues by integrating cluster-specific training with synthetic node generation. Unlike traditional GNNs that apply the same node update process for all nodes, ECGN learns different aggregations for different clusters. We also use the clusters to generate new minority-class nodes in a way that helps clarify the inter-class decision boundary. By combining cluster-aware embeddings with a global integration step, ECGN enhances the quality of the resulting node embeddings. Our method works with any underlying GNN and any cluster generation technique. Experimental results show that ECGN consistently outperforms its closest competitors by up to 11% on some widely studied benchmark datasets.

cs.LG↗

arXiv2024

Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions

As machine learning (ML) models are increasingly used in social domains to make consequential decisions about humans, they often have the power to reshape data distributions. Humans, as strategic agents, continuously adapt their behaviors in response to the learning system. As populations change dynamically, ML systems may need frequent updates to ensure high performance. However, acquiring high-quality human-annotated samples can be highly challenging and even infeasible in social domains. A common practice to address this issue is using the model itself to annotate unlabeled data samples. This paper investigates the long-term impacts when ML models are retrained with model-annotated samples when they incorporate human strategic responses. We first formalize the interactions between strategic agents and the model and then analyze how they evolve under such dynamic interactions. We find that agents are increasingly likely to receive positive decisions as the model gets retrained, whereas the proportion of agents with positive labels may decrease over time. We thus propose a refined retraining process to stabilize the dynamics. Last, we examine how algorithmic fairness can be affected by these retraining processes and find that enforcing common fairness constraints at every round may not benefit the disadvantaged group in the long run. Experiments on (semi-)synthetic and real data validate the theoretical findings.

cs.LG↗

arXiv2024

Algorithmic Decision-Making under Agents with Persistent Improvement

This paper studies algorithmic decision-making under human's strategic behavior, where a decision maker uses an algorithm to make decisions about human agents, and the latter with information about the algorithm may exert effort strategically and improve to receive favorable decisions. Unlike prior works that assume agents benefit from their efforts immediately, we consider realistic scenarios where the impacts of these efforts are persistent and agents benefit from efforts by making improvements gradually. We first develop a dynamic model to characterize persistent improvements and based on this construct a Stackelberg game to model the interplay between agents and the decision-maker. We analytically characterize the equilibrium strategies and identify conditions under which agents have incentives to improve. With the dynamics, we then study how the decision-maker can design an optimal policy to incentivize the largest improvements inside the agent population. We also extend the model to settings where 1) agents may be dishonest and game the algorithm into making favorable but erroneous decisions; 2) honest efforts are forgettable and not sufficient to guarantee persistent improvements. With the extended models, we further examine conditions under which agents prefer honest efforts over dishonest behavior and the impacts of forgettable efforts.

cs.GT↗

arXiv2024

Superconductivity and spin canting in spin-orbit proximitized rhombohedral trilayer graphene

Graphene and transition metal dichalcogenide flat-band systems show similar phase diagrams, replete with magnetic and superconducting phases. An abiding question has been whether magnetic ordering competes with superconductivity or facilitates pairing. The advent of crystalline graphene superconductors enables a new generation of controlled experiments to probe the microscopic origin of superconductivity. For example, recent studies of Bernal bilayer graphene show a dramatic increase in the observed domain and critical temperature $T_c$ of superconducting states in the presence of enhanced spin-orbit coupling; the mechanism for this enhancement, however, remains unclear. Here, we show that introducing spin-orbit coupling in rhombohedral trilayer graphene (RTG) via substrate proximity effect generates new superconducting pockets for both electron and hole doping, with maximal $T_c\approx$ 300mK three times larger than in RTG encapsulated by hexagonal boron nitride alone. Using local magnetometry and thermodynamic compressibility measurements, we show that superconductivity straddles an apparently continuous transition between a spin-canted state with a finite in-plane magnetic moment and a state with complete spin-valley locking. This transition is reproduced in our Hartree-Fock calculations, where it is driven by the competition between spin-orbit coupling and the carrier-density-tuned Hund's interaction. Our experiment suggests that the enhancement of superconductivity by spin-orbit coupling is driven not by a change in the ground state symmetry or degeneracy but rather by a quantitative change in the canting angle. These results align with a recently proposed mechanism for the enhancement of superconductivity in spin-orbit coupled rhombohedral multilayers, in which fluctuations in the spin-canting order contribute to the pairing interaction.

cond-mat.mes-hall↗

arXiv2024

Scalable microwave-to-optical transducers at single photon level with spins

Microwave-to-optical transduction of single photons will play an essential role in interconnecting future superconducting quantum devices, with applications in distributed quantum computing and secure communications. Various transducers that couple microwave and optical modes via an optical drive have been developed, utilizing nonlinear phenomena such as the Pockels effect and a combination of electromechanical, piezoelectric, and optomechanical couplings. However, the limited strength of these nonlinearities, set by bulk material properties, requires the use of high quality factor resonators, often in conjunction with sophisticated nano-fabrication of suspended structures. Thus, an efficient and scalable transduction technology is still an outstanding goal. Rare-earth ion (REI) doped crystals provide high-quality atomic resonances that result in effective second-order nonlinearities stronger by many orders of magnitude compared to conventional materials. Here, we use ytterbium-171 ions doped in a YVO$_4$ crystal at 340 ppm with an effective resonant $χ^{(2)}$ nonlinearity of ~ 10$^7$ pm/V to implement an on-chip microwave-to-optical transducer. Without an engineered optical cavity, we achieve percent-level efficiencies with an added noise as low as 1.24(9) photons. To showcase scalability, we demonstrate the interference of photons originating from two simultaneously operated transducers, enabled by the inherent absolute frequencies of the atomic transitions. These results establish REI-based transducers as a highly competitive transduction platform, provide existing REI-based quantum technologies a native link to various leading quantum microwave platforms, and pave the way toward remote transducer-assisted entanglement of superconducting quantum machines.

quant-ph↗

arXiv2024

Optical Imaging of Flavor Order in Flat Band Graphene

Spin and valley flavor polarization plays a central role in the many-body physics of flat band graphene, with fermi surface reconstructions often accompanied by quantized anomalous Hall and superconducting state observed in a variety of experimental systems. Here we describe an optical technique that sensitively and selectively detects flavor textures via the exciton response of a proximal transition metal dichalcogenide layer. Through a systematic study of rhombohedral and rotationally faulted graphene bilayers and trilayers, we show that when the semiconducting dichalcogenide is in direct contact with the graphene, the exciton response is most sensitive to the large momentum rearrangement of the Fermi surface, providing information that is distinct from and complementary to electrical compressibility measurements. The wide-field imaging capability of optical probes allows us to obtain spatial maps of flavor orders with high throughput, and with broad temperature and device compatibility. Our work paves the way for optical probing and imaging of flavor orders in flat band graphene systems.

cond-mat.mes-hall↗

arXiv2024

MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures

Accurate and fast prediction of materials properties is central to the digital transformation of materials design. However, the vast design space and diverse operating conditions pose significant challenges for accurately modeling arbitrary material candidates and forecasting their properties. We present MatterSim, a deep learning model actively learned from large-scale first-principles computations, for efficient atomistic simulations at first-principles level and accurate prediction of broad material properties across the periodic table, spanning temperatures from 0 to 5000 K and pressures up to 1000 GPa. Out-of-the-box, the model serves as a machine learning force field, and shows remarkable capabilities not only in predicting ground-state material structures and energetics, but also in simulating their behavior under realistic temperatures and pressures, signifying an up to ten-fold enhancement in precision compared to the prior best-in-class. This enables MatterSim to compute materials' lattice dynamics, mechanical and thermodynamic properties, and beyond, to an accuracy comparable with first-principles methods. Specifically, MatterSim predicts Gibbs free energies for a wide range of inorganic solids with near-first-principles accuracy and achieves a 15 meV/atom resolution for temperatures up to 1000K compared with experiments. This opens an opportunity to predict experimental phase diagrams of materials at minimal computational cost. Moreover, MatterSim also serves as a platform for continuous learning and customization by integrating domain-specific data. The model can be fine-tuned for atomistic simulations at a desired level of theory or for direct structure-to-property predictions, achieving high data efficiency with a reduction in data requirements by up to 97%.

cond-mat.mtrl-sci↗

arXiv2024

Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint

Solving image inverse problems (e.g., super-resolution and inpainting) requires generating a high fidelity image that matches the given input (the low-resolution image or the masked image). By using the input image as guidance, we can leverage a pretrained diffusion generative model to solve a wide range of image inverse tasks without task specific model fine-tuning. To precisely estimate the guidance score function of the input image, we propose Diffusion Policy Gradient (DPG), a tractable computation method by viewing the intermediate noisy images as policies and the target image as the states selected by the policy. Experiments show that our method is robust to both Gaussian and Poisson noise degradation on multiple linear and non-linear inverse tasks, resulting into a higher image restoration quality on FFHQ, ImageNet and LSUN datasets.

eess.IV↗

arXiv2024

MatterGen: a generative model for inorganic materials design

The design of functional materials with desired properties is essential in driving technological advances in areas like energy storage, catalysis, and carbon capture. Generative models provide a new paradigm for materials design by directly generating entirely novel materials given desired property constraints. Despite recent progress, current generative models have low success rate in proposing stable crystals, or can only satisfy a very limited set of property constraints. Here, we present MatterGen, a model that generates stable, diverse inorganic materials across the periodic table and can further be fine-tuned to steer the generation towards a broad range of property constraints. To enable this, we introduce a new diffusion-based generative process that produces crystalline structures by gradually refining atom types, coordinates, and the periodic lattice. We further introduce adapter modules to enable fine-tuning towards any given property constraints with a labeled dataset. Compared to prior generative models, structures produced by MatterGen are more than twice as likely to be novel and stable, and more than 15 times closer to the local energy minimum. After fine-tuning, MatterGen successfully generates stable, novel materials with desired chemistry, symmetry, as well as mechanical, electronic and magnetic properties. Finally, we demonstrate multi-property materials design capabilities by proposing structures that have both high magnetic density and a chemical composition with low supply-chain risk. We believe that the quality of generated materials and the breadth of MatterGen's capabilities represent a major advancement towards creating a universal generative model for materials design.

cond-mat.mtrl-sci↗

arXiv2024

Optimizing Medication Decisions for Patients with Atrial Fibrillation through Path Development Network

Atrial fibrillation (AF) is a common cardiac arrhythmia characterized by rapid and irregular contractions of the atria. It significantly elevates the risk of strokes due to slowed blood flow in the atria, especially in the left atrial appendage, which is prone to blood clot formation. Such clots can migrate into cerebral arteries, leading to ischemic stroke. To assess whether AF patients should be prescribed anticoagulants, doctors often use the CHA2DS2-VASc scoring system. However, anticoagulant use must be approached with caution as it can impact clotting functions. This study introduces a machine learning algorithm that predicts whether patients with AF should be recommended anticoagulant therapy using 12-lead ECG data. In this model, we use STOME to enhance time-series data and then process it through a Convolutional Neural Network (CNN). By incorporating a path development layer, the model achieves a specificity of 30.6% under the condition of an NPV of 1. In contrast, LSTM algorithms without path development yield a specificity of only 2.7% under the same NPV condition.

cs.LG↗

arXiv2023

Intervalley coherence and intrinsic spin-orbit coupling in rhombohedral trilayer graphene

Rhombohedral graphene multilayers provide a clean and highly reproducible platform to explore the emergence of superconductivity and magnetism in a strongly interacting electron system. Here, we use electronic compressibility and local magnetometry to explore the phase diagram of this material class in unprecedented detail. We focus on rhombohedral trilayer in the quarter metal regime, where the electronic ground state is characterized by the occupation of a single spin and valley isospin flavor. Our measurements reveal a subtle competition between valley imbalanced (VI) orbital ferromagnets and intervalley coherent (IVC) states in which electron wave functions in the two momentum space valleys develop a macroscopically coherent relative phase. Contrasting the in-plane spin susceptibility of the IVC and VI phases reveals the influence of graphene's intrinsic spin-orbit coupling, which drives the emergence of a distinct correlated phase with hybrid VI and IVC character. Spin-orbit also suppresses the in-plane magnetic susceptibility of the VI phase, which allows us to extract the spin-orbit coupling strength of $λ\approx 50μ$eV for our hexagonal boron nitride-encapsulated graphene system. We discuss the implications of finite spin-orbit coupling on the spin-triplet superconductors observed in both rhombohedral and twisted graphene multilayers.

cond-mat.mes-hall↗

arXiv2023

Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems

Making big purchases requires consumers to research or consult a salesperson to gain domain expertise. However, existing conversational recommender systems (CRS) often overlook users' lack of background knowledge, focusing solely on gathering preferences. In this work, we define a new problem space for conversational agents that aim to provide both product recommendations and educational value through mixed-type mixed-initiative dialog. We introduce SalesOps, a framework that facilitates the simulation and evaluation of such systems by leveraging recent advancements in large language models (LLMs). We build SalesBot and ShopperBot, a pair of LLM-powered agents that can simulate either side of the framework. A comprehensive human study compares SalesBot against professional salespeople, revealing that although SalesBot approaches professional performance in terms of fluency and informativeness, it lags behind in recommendation quality. We emphasize the distinct limitations both face in providing truthful information, highlighting the challenges of ensuring faithfulness in the CRS context. We release our code and make all data available.

cs.CL↗

arXiv2023

MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Design

Metal-organic frameworks (MOFs) are of immense interest in applications such as gas storage and carbon capture due to their exceptional porosity and tunable chemistry. Their modular nature has enabled the use of template-based methods to generate hypothetical MOFs by combining molecular building blocks in accordance with known network topologies. However, the ability of these methods to identify top-performing MOFs is often hindered by the limited diversity of the resulting chemical space. In this work, we propose MOFDiff: a coarse-grained (CG) diffusion model that generates CG MOF structures through a denoising diffusion process over the coordinates and identities of the building blocks. The all-atom MOF structure is then determined through a novel assembly algorithm. Equivariant graph neural networks are used for the diffusion model to respect the permutational and roto-translational symmetries. We comprehensively evaluate our model's capability to generate valid and novel MOF structures and its effectiveness in designing outstanding MOF materials for carbon capture applications with molecular simulations.

physics.chem-ph↗

arXiv2023

XGen-7B Technical Report

Large Language Models (LLMs) have become ubiquitous across various domains, transforming the way we interact with information and conduct research. However, most high-performing LLMs remain confined behind proprietary walls, hindering scientific progress. Most open-source LLMs, on the other hand, are limited in their ability to support longer sequence lengths, which is a key requirement for many tasks that require inference over an input context. To address this, we have trained XGen, a series of 7B parameter models on up to 8K sequence length for up to 1.5T tokens. We have also finetuned the XGen models on public-domain instructional data, creating their instruction-tuned counterparts (XGen-Inst). We open-source our models for both research advancements and commercial applications. Our evaluation on standard benchmarks shows that XGen models achieve comparable or better results when compared with state-of-the-art open-source LLMs. Our targeted evaluation on long sequence modeling tasks shows the benefits of our 8K-sequence models over 2K-sequence open-source LLMs.

cs.CL↗

arXiv2023

Simulate Time-integrated Coarse-grained Molecular Dynamics with Multi-Scale Graph Networks

Molecular dynamics (MD) simulation is essential for various scientific domains but computationally expensive. Learning-based force fields have made significant progress in accelerating ab-initio MD simulation but are not fast enough for many real-world applications due to slow inference for large systems and small time steps (femtosecond-level). We aim to address these challenges by learning a multi-scale graph neural network that directly simulates coarse-grained MD with a very large time step (nanosecond-level) and a novel refinement module based on diffusion models to mitigate simulation instability. The effectiveness of our method is demonstrated in two complex systems: single-chain coarse-grained polymers and multi-component Li-ion polymer electrolytes. For evaluation, we simulate trajectories much longer than the training trajectories for systems with different chemical compositions that the model is not trained on. Structural and dynamical properties can be accurately recovered at several orders of magnitude higher speed than classical force fields by getting out of the femtosecond regime.

cs.LG↗

arXiv2023

Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations

Molecular dynamics (MD) simulation techniques are widely used for various natural science applications. Increasingly, machine learning (ML) force field (FF) models begin to replace ab-initio simulations by predicting forces directly from atomic structures. Despite significant progress in this area, such techniques are primarily benchmarked by their force/energy prediction errors, even though the practical use case would be to produce realistic MD trajectories. We aim to fill this gap by introducing a novel benchmark suite for learned MD simulation. We curate representative MD systems, including water, organic molecules, a peptide, and materials, and design evaluation metrics corresponding to the scientific objectives of respective systems. We benchmark a collection of state-of-the-art (SOTA) ML FF models and illustrate, in particular, how the commonly benchmarked force accuracy is not well aligned with relevant simulation metrics. We demonstrate when and how selected SOTA methods fail, along with offering directions for further improvement. Specifically, we identify stability as a key metric for ML models to improve. Our benchmark suite comes with a comprehensive open-source codebase for training and simulation with ML FFs to facilitate future work.

physics.comp-ph↗