arXiv subjects

Xi Chen

Publications and source records attributed to Xi Chen.

At least 703 records · Page 39Linked to original sources

arXiv2023

EEGSN: Towards Efficient Low-latency Decoding of EEG with Graph Spiking Neural Networks

A vast majority of spiking neural networks (SNNs) are trained based on inductive biases that are not necessarily a good fit for several critical tasks that require low-latency and power efficiency. Inferring brain behavior based on the associated electroenchephalography (EEG) signals is an example of how networks training and inference efficiency can be heavily impacted by learning spatio-temporal dependencies. Up to now, SNNs rely solely on general inductive biases to model the dynamic relations between different data streams. Here, we propose a graph spiking neural network architecture for multi-channel EEG classification (EEGSN) that learns the dynamic relational information present in the distributed EEG sensors. Our method reduced the inference computational complexity by $\times 20$ compared to the state-of-the-art SNNs, while achieved comparable accuracy on motor execution classification tasks. Overall, our work provides a framework for interpretable and efficient training of graph spiking networks that are suitable for low-latency and low-power real-time applications.

cs.NE↗

arXiv2023

Head-tail Loss: A simple function for Oriented Object Detection and Anchor-free models

This paper presents a new loss function for the prediction of oriented bounding boxes, named head-tail-loss. The loss function consists in minimizing the distance between the prediction and the annotation of two key points that are representing the annotation of the object. The first point is the center point and the second is the head of the object. However, for the second point, the minimum distance between the prediction and either the head or tail of the groundtruth is used. On this way, either prediction is valid (with the head pointing to the tail or the tail pointing to the head). At the end the importance is to detect the direction of the object but not its heading. The new loss function has been evaluated on the DOTA and HRSC2016 datasets and has shown potential for elongated objects such as ships and also for other types of objects with different shapes.

cs.CV↗

arXiv2023

FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead

We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI). Different from existing data-driven weather forecast methods, FengWu solves the medium-range forecast problem from a multi-modal and multi-task perspective. Specifically, a deep learning architecture equipped with model-specific encoder-decoders and cross-modal fusion Transformer is elaborately designed, which is learned under the supervision of an uncertainty loss to balance the optimization of different predictors in a region-adaptive manner. Besides this, a replay buffer mechanism is introduced to improve medium-range forecast performance. With 39-year data training based on the ERA5 reanalysis, FengWu is able to accurately reproduce the atmospheric dynamics and predict the future land and atmosphere states at 37 vertical levels on a 0.25° latitude-longitude resolution. Hindcasts of 6-hourly weather in 2018 based on ERA5 demonstrate that FengWu performs better than GraphCast in predicting 80\% of the 880 reported predictands, e.g., reducing the root mean square error (RMSE) of 10-day lead global z500 prediction from 733 to 651 $m^{2}/s^2$. In addition, the inference cost of each iteration is merely 600ms on NVIDIA Tesla A100 hardware. The results suggest that FengWu can significantly improve the forecast skill and extend the skillful global medium-range weather forecast out to 10.75 days lead (with ACC of z500 > 0.6) for the first time.

cs.AI↗

arXiv2023

Complexity of Equilibria in First-Price Auctions under General Tie-Breaking Rules

We study the complexity of finding an approximate (pure) Bayesian Nash equilibrium in a first-price auction with common priors when the tie-breaking rule is part of the input. We show that the problem is PPAD-complete even when the tie-breaking rule is trilateral (i.e., it specifies item allocations when no more than three bidders are in tie, and adopts the uniform tie-breaking rule otherwise). This is the first hardness result for equilibrium computation in first-price auctions with common priors. On the positive side, we give a PTAS for the problem under the uniform tie-breaking rule.

cs.GT↗

arXiv2023

Detecting Everything in the Open World: Towards Universal Object Detection

In this paper, we formally address universal object detection, which aims to detect every scene and predict every category. The dependence on human annotations, the limited visual information, and the novel categories in the open world severely restrict the universality of traditional detectors. We propose UniDetector, a universal object detector that has the ability to recognize enormous categories in the open world. The critical points for the universality of UniDetector are: 1) it leverages images of multiple sources and heterogeneous label spaces for training through the alignment of image and text spaces, which guarantees sufficient information for universal representations. 2) it generalizes to the open world easily while keeping the balance between seen and unseen classes, thanks to abundant information from both vision and language modalities. 3) it further promotes the generalization ability to novel categories through our proposed decoupling training manner and probability calibration. These contributions allow UniDetector to detect over 7k categories, the largest measurable category size so far, with only about 500 classes participating in training. Our UniDetector behaves the strong zero-shot generalization ability on large-vocabulary datasets like LVIS, ImageNetBoxes, and VisualGenome - it surpasses the traditional supervised baselines by more than 4\% on average without seeing any corresponding images. On 13 public detection datasets with various scenes, UniDetector also achieves state-of-the-art performance with only a 3\% amount of training data.

cs.CV↗

arXiv2023

Optimal control and ultimate bounds of 1:2 nonlinear quantum systems

Using optimal control, we establish and link the ultimate bounds in time (referred to as quantum speed limit) and energy of two- and three-level quantum nonlinear systems which feature 1:2 resonance. Despite the unreachable complete inversion, by using the Pontryagin maximum principle, we determine the optimal time, pulse area, or energy, for a given arbitrary accuracy. We show that the third-order Kerr terms can be absorbed in the detuning in order to lock the dynamics to the resonance. In the two-level problem, we determine the non-linear counterpart of the optimal $π$-pulse inversion for a given accuracy. In the three-level problem, we obtain an intuitive pulse sequence similar to the linear counterpart but with different shapes. We prove the (slow) logarithmic increasing of the optimal time as a function of the accuracy.

quant-ph↗

arXiv2023

CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis

MRI synthesis promises to mitigate the challenge of missing MRI modality in clinical practice. Diffusion model has emerged as an effective technique for image synthesis by modelling complex and variable data distributions. However, most diffusion-based MRI synthesis models are using a single modality. As they operate in the original image domain, they are memory-intensive and less feasible for multi-modal synthesis. Moreover, they often fail to preserve the anatomical structure in MRI. Further, balancing the multiple conditions from multi-modal MRI inputs is crucial for multi-modal synthesis. Here, we propose the first diffusion-based multi-modality MRI synthesis model, namely Conditioned Latent Diffusion Model (CoLa-Diff). To reduce memory consumption, we design CoLa-Diff to operate in the latent space. We propose a novel network architecture, e.g., similar cooperative filtering, to solve the possible compression and noise in latent space. To better maintain the anatomical structure, brain region masks are introduced as the priors of density distributions to guide diffusion process. We further present auto-weight adaptation to employ multi-modal information effectively. Our experiments demonstrate that CoLa-Diff outperforms other state-of-the-art MRI synthesis methods, promising to serve as an effective tool for multi-modal MRI synthesis.

eess.IV↗

arXiv2023

High-Dimensional Dynamic Pricing under Non-Stationarity: Learning and Earning with Change-Point Detection

We consider a high-dimensional dynamic pricing problem under non-stationarity, where a firm sells products to $T$ sequentially arriving consumers that behave according to an unknown demand model with potential changes at unknown times. The demand model is assumed to be a high-dimensional generalized linear model (GLM), allowing for a feature vector in $\mathbb R^d$ that encodes products and consumer information. To achieve optimal revenue (i.e., least regret), the firm needs to learn and exploit the unknown GLMs while monitoring for potential change-points. To tackle such a problem, we first design a novel penalized likelihood-based online change-point detection algorithm for high-dimensional GLMs, which is the first algorithm in the change-point literature that achieves optimal minimax localization error rate for high-dimensional GLMs. A change-point detection assisted dynamic pricing (CPDP) policy is further proposed and achieves a near-optimal regret of order $O(s\sqrt{Υ_T T}\log(Td))$, where $s$ is the sparsity level and $Υ_T$ is the number of change-points. This regret is accompanied with a minimax lower bound, demonstrating the optimality of CPDP (up to logarithmic factors). In particular, the optimality with respect to $Υ_T$ is seen for the first time in the dynamic pricing literature, and is achieved via a novel accelerated exploration mechanism. Extensive simulation experiments and a real data application on online lending illustrate the efficiency of the proposed policy and the importance and practical value of handling non-stationarity in dynamic pricing.

stat.ME↗

arXiv2023

ScribbleSeg: Scribble-based Interactive Image Segmentation

Interactive segmentation enables users to extract masks by providing simple annotations to indicate the target, such as boxes, clicks, or scribbles. Among these interaction formats, scribbles are the most flexible as they can be of arbitrary shapes and sizes. This enables scribbles to provide more indications of the target object. However, previous works mainly focus on click-based configuration, and the scribble-based setting is rarely explored. In this work, we attempt to formulate a standard protocol for scribble-based interactive segmentation. Basically, we design diversified strategies to simulate scribbles for training, propose a deterministic scribble generator for evaluation, and construct a challenging benchmark. Besides, we build a strong framework ScribbleSeg, consisting of a Prototype Adaption Module(PAM) and a Corrective Refine Module (CRM), for the task. Extensive experiments show that ScribbleSeg performs notably better than previous click-based methods. We hope this could serve as a more powerful and general solution for interactive segmentation. Our code will be made available.

cs.CV↗

arXiv2023

Active Relation Discovery: Towards General and Label-aware Open Relation Extraction

Open Relation Extraction (OpenRE) aims to discover novel relations from open domains. Previous OpenRE methods mainly suffer from two problems: (1) Insufficient capacity to discriminate between known and novel relations. When extending conventional test settings to a more general setting where test data might also come from seen classes, existing approaches have a significant performance decline. (2) Secondary labeling must be performed before practical application. Existing methods cannot label human-readable and meaningful types for novel relations, which is urgently required by the downstream tasks. To address these issues, we propose the Active Relation Discovery (ARD) framework, which utilizes relational outlier detection for discriminating known and novel relations and involves active learning for labeling novel relations. Extensive experiments on three real-world datasets show that ARD significantly outperforms previous state-of-the-art methods on both conventional and our proposed general OpenRE settings. The source code and datasets will be available for reproducibility.

cs.CL↗

arXiv2023

Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph Alignment

Entity alignment (EA) for knowledge graphs (KGs) plays a critical role in knowledge engineering. Existing EA methods mostly focus on utilizing the graph structures and entity attributes (including literals), but ignore images that are common in modern multi-modal KGs. In this study we first constructed Multi-OpenEA -- eight large-scale, image-equipped EA benchmarks, and then evaluated some existing embedding-based methods for utilizing images. In view of the complementary nature of visual modal information and logical deduction, we further developed a new multi-modal EA method named LODEME using logical deduction and multi-modal KG embedding, with state-of-the-art performance achieved on Multi-OpenEA and other existing multi-modal EA benchmarks.

cs.AI↗

arXiv2023

Knowledge-augmented Few-shot Visual Relation Detection

Visual Relation Detection (VRD) aims to detect relationships between objects for image understanding. Most existing VRD methods rely on thousands of training samples of each relationship to achieve satisfactory performance. Some recent papers tackle this problem by few-shot learning with elaborately designed pipelines and pre-trained word vectors. However, the performance of existing few-shot VRD models is severely hampered by the poor generalization capability, as they struggle to handle the vast semantic diversity of visual relationships. Nonetheless, humans have the ability to learn new relationships with just few examples based on their knowledge. Inspired by this, we devise a knowledge-augmented, few-shot VRD framework leveraging both textual knowledge and visual relation knowledge to improve the generalization ability of few-shot VRD. The textual knowledge and visual relation knowledge are acquired from a pre-trained language model and an automatically constructed visual relation knowledge graph, respectively. We extensively validate the effectiveness of our framework. Experiments conducted on three benchmarks from the commonly used Visual Genome dataset show that our performance surpasses existing state-of-the-art models with a large improvement.

cs.CV↗

arXiv2023

Existence of modified wave operators and infinite cascade result for a half wave Schr{ö}dinger equation on the plane

We consider the following half wave Schr{ö}dinger equation,$$\left(i \partial_{t}+\partial_{x }^2-\left|D_{y}\right|\right) U=|U|^{2} U$$on the plane $\mathbb{R}_x \times \mathbb{R}_y$. We prove the existence of modified wave operators between small decaying solutions to this equation and small decaying solutions to the non chiral cubic Szeg\H o equation, which is similar to the the existence result of modified wave operators on $\mathbb{R}_x \times \mathbb{T}_y$ obtained by H. Xu [16]. We then combine our modified wave operators result with a recent cascade result [7] for the cubic Szeg\H o equation by P. G{é}rard and A. Pushnitski to deduce that there exists solutions $U$ to the half wave Schr{ö}dinger equation such that $\|U(t)\|_{L_{x}^{2} H_{y}^{1}}$ tends to infinity as $\log t$ when $t \rightarrow +\infty$. It indicates that the half wave Schr{ö}dinger equation on the plane is one of the very few dispersive equations admitting global solutions with small and smooth data such that the $H^s$ norms are going to infinity as $t$ tends to infinity.

math.AP↗

arXiv2023

Self-Attentive Sequential Recommendation with Cheap Causal Convolutions

Sequential Recommendation is a prominent topic in current research, which uses user behavior sequence as an input to predict future behavior. By assessing the correlation strength of historical behavior through the dot product, the model based on the self-attention mechanism can capture the long-term preference of the sequence. However, it has two limitations. On the one hand, it does not effectively utilize the items' local context information when determining the attention and creating the sequence representation. On the other hand, the convolution and linear layers often contain redundant information, which limits the ability to encode sequences. In this paper, we propose a self-attentive sequential recommendation model based on cheap causal convolution. It utilizes causal convolutions to capture items' local information for calculating attention and generating sequence embedding. It also uses cheap convolutions to improve the representations by lightweight structure. We evaluate the effectiveness of the proposed model in terms of both accurate and calibrated sequential recommendation. Experiments on benchmark datasets show that the proposed model can perform better in single- and multi-objective recommendation scenarios.

cs.IR↗

arXiv2023

The most probable dynamics of receptor-ligand binding on cell membrane

We devise a method for predicting certain receptor-ligand binding behaviors, based on stochastic dynamical modelling. We consider the dynamics of a receptor binding to a ligand on the cell membrane, where the receptor and ligand perform different motions and are thus modeled by stochastic differential equations with Gaussian noise or non-Gaussian noise. We use neural networks based on Onsager-Machlup function to compute the probability $P_1$ of the unbounded receptor diffusing to the cell membrane. Meanwhile, we compute the probability $P_2$ of extracellular ligand arriving at the cell membrane by solving the associated Fokker-Planck equation. Then, we could predict the most probable binding probability by combining $P_1$ and $P_2$. In this way, we conclude with some indication about where the ligand will most probably encounter the receptor, contributing to better understanding of cell's response to external stimuli and communication with other cells.

q-bio.MN↗

arXiv2023

Thermal Conductivity of BAs under Pressure

The thermal conductivity of boron arsenide (BAs) is believed to be influenced by phonon scattering selection rules due to its special phonon dispersion. Compression of BAs leads to significant changes in phonon dispersion, which allows for a test of first principles theories for how phonon dispersion affects three- and four-phonon scattering rates. This study reports the thermal conductivity of BAs from 0 to 30 GPa. Thermal conductivity vs. pressure of BAs is measured by time-domain thermoreflectance with a diamond anvil cell. In stark contrast to what is typical for nonmetallic crystals, BAs is observed to have a pressure independent thermal conductivity below 30 GPa. The thermal conductivity of nonmetallic crystals typically increases upon compression. The unusual pressure independence of thermal conductivity of BAs shows the important relationship between phonon dispersion properties and three- and four-phonon scattering rates.

cond-mat.mtrl-sci↗

arXiv2023

Towards Prediction of Financial Crashes with a D-Wave Quantum Computer

Prediction of financial crashes in a complex financial network is known to be an NP-hard problem, which means that no known algorithm can guarantee to find optimal solutions efficiently. We experimentally explore a novel approach to this problem by using a D-Wave quantum computer, benchmarking its performance for attaining financial equilibrium. To be specific, the equilibrium condition of a nonlinear financial model is embedded into a higher-order unconstrained binary optimization (HUBO) problem, which is then transformed to a spin-$1/2$ Hamiltonian with at most two-qubit interactions. The problem is thus equivalent to finding the ground state of an interacting spin Hamiltonian, which can be approximated with a quantum annealer. The size of the simulation is mainly constrained by the necessity of a large quantity of physical qubits representing a logical qubit with the correct connectivity. Our experiment paves the way to codify this quantitative macroeconomics problem in quantum computers.

quant-ph↗

arXiv2023

3D Molecular Generation via Virtual Dynamics

Structure-based drug design, i.e., finding molecules with high affinities to the target protein pocket, is one of the most critical tasks in drug discovery. Traditional solutions, like virtual screening, require exhaustively searching on a large molecular database, which are inefficient and cannot return novel molecules beyond the database. The pocket-based 3D molecular generation model, i.e., directly generating a molecule with a 3D structure and binding position in the pocket, is a new promising way to address this issue. Herein, we propose VD-Gen, a novel pocket-based 3D molecular generation pipeline. VD-Gen consists of several carefully designed stages to generate fine-grained 3D molecules with binding positions in the pocket cavity end-to-end. Rather than directly generating or sampling atoms with 3D positions in the pocket like in early attempts, in VD-Gen, we first randomly initialize many virtual particles in the pocket; then iteratively move these virtual particles, making the distribution of virtual particles approximate the distribution of molecular atoms. After virtual particles are stabilized in 3D space, we extract a 3D molecule from them. Finally, we further refine atoms in the extracted molecule by iterative movement again, to get a high-quality 3D molecule, and predict a confidence score for it. Extensive experiment results on pocket-based molecular generation demonstrate that VD-Gen can generate novel 3D molecules to fill the target pocket cavity with high binding affinities, significantly outperforming previous baselines.

q-bio.BM↗