arXiv subjects

Xinyu Li

Publications and source records attributed to Xinyu Li.

At least 181 records · Page 10Linked to original sources

arXiv2022

Sentiment Analysis on Inflation after Covid-19

We implement traditional machine learning and deep learning methods for global tweets from 2017-2022 to build a high-frequency measure of the public's sentiment index on inflation and analyze its correlation with other online data sources such as google trend and market-oriented inflation index. We use manually labeled trigrams to test the prediction performance of several machine learning models(logistic regression,random forest etc.) and choose Bert model for final demonstration. Later, we sum daily tweets' sentiment scores gained from Bert model to obtain the predicted inflation sentiment index, and we further analyze the regional and pre/post covid patterns of these inflation indexes. Lastly, we take other empirical inflation-related data as references and prove that twitter-based inflation sentiment analysis method has an outstanding capability to predict inflation. The results suggest that Twitter combined with deep learning methods can be a novel and timely method to utilize existing abundant data sources on inflation expectations and provide daily indicators of consumers' perception on inflation.

econ.EM↗

arXiv2022

The impact of moving expenses on social segregation: a simulation with RL and ABM

Over the past decades, breakthroughs such as Reinforcement Learning (RL) and Agent-based modeling (ABM) have made simulations of economic models feasible. Recently, there has been increasing interest in applying ABM to study the impact of residential preferences on neighborhood segregation in the Schelling Segregation Model. In this paper, RL is combined with ABM to simulate a modified Schelling Segregation model, which incorporates moving expenses as an input parameter. In particular, deep Q network (DQN) is adopted as RL agents' learning algorithm to simulate the behaviors of households and their preferences. This paper studies the impact of moving expenses on the overall segregation pattern and its role in social integration. A more comprehensive simulation of the segregation model is built for policymakers to forecast the potential consequences of their policies.

econ.GN↗

arXiv2022

If dark matter is fuzzy, the first stars form in massive pancakes

Fuzzy dark matter (FDM) is a proposed modification for the standard cold dark matter (CDM) model motivated by small-scale discrepancies in low-mass galaxies. Composed of ultra-light (mass $\sim 10^{-22}$ eV) axions with kpc-scale de Broglie wavelengths, this is one of a class of candidates that predicts that the first collapsed objects form in relatively massive dark matter halos. This implies that the formation history of the first stars and galaxies would be very different, potentially placing strong constraints on such models. Here we numerically simulate the formation of the first stars in an FDM cosmology, following the collapse in a representative volume all the way down to primordial protostar formation including a primordial non-equilibrium chemical network and cooling for the first time. We find two novel results: first, the large-scale collapse results in a very thin and flat gas "pancake"; second, despite the very different cosmology, this pancake fragments until it forms protostellar objects indistinguishable from those in CDM. Combined, these results indicate that the first generation of stars in this model are also likely to be massive and, because of the sheet morphology, do not self-regulate, resulting in a massive Pop III starburst. We estimate the total number of first stars forming in this extended structure to be $10^4$ over 20 Myr using a simple model to account for the ionizing feedback from the stars, and should be observable with JWST. These predictions provide a potential smoking gun signature of FDM and similar dark matter candidates.

astro-ph.GA↗

arXiv2022

Robust Direct Learning for Causal Data Fusion

In the era of big data, the explosive growth of multi-source heterogeneous data offers many exciting challenges and opportunities for improving the inference of conditional average treatment effects. In this paper, we investigate homogeneous and heterogeneous causal data fusion problems under a general setting that allows for the presence of source-specific covariates. We provide a direct learning framework for integrating multi-source data that separates the treatment effect from other nuisance functions, and achieves double robustness against certain misspecification. To improve estimation precision and stability, we propose a causal information-aware weighting function motivated by theoretical insights from the semiparametric efficiency theory; it assigns larger weights to samples containing more causal information with high interpretability. We introduce a two-step algorithm, the weighted multi-source direct learner, based on constructing a pseudo-outcome and regressing it on covariates under a weighted least square criterion; it offers us a powerful tool for causal data fusion, enjoying the advantages of easy implementation, double robustness and model flexibility. In simulation studies, we demonstrate the effectiveness of our proposed methods in both homogeneous and heterogeneous causal data fusion scenarios.

stat.ML↗

arXiv2022

Propagation of a Strong Fast Magnetosonic Wave in the Magnetosphere of a Neutron Star

We study the propagation of a strong, low frequency, linearly polarized fast magnetosonic wave inside the magnetosphere of a neutron star. The relative strength $δB/B$ of the wave grows as a function of radius before it reaches the light cylinder, and what starts as a small perturbation can grow to become nonlinear before it escapes the magnetosphere. Using first-principles Particle-in-Cell (PIC) simulations, we study in detail the evolution of the wave as it becomes nonlinear. We find that an initially sinusoidal wave becomes strongly distorted as $δB/B$ approaches order unity. The wave steepens into a shock in each wavelength. The plasma particles drift into the shock and undergo coherent gyration in the rest of the wave, and subsequently become thermalized. This process quickly dissipates the energy of an FRB emitted deep within the magnetosphere of magnetar, effectively preventing GHz waves produced in the closed field line zone from escaping. This mechanism may also provide an effective way to launch shocks in the magnetosphere from kHz fast magnetosonic waves without requiring a relativistic ejecta. The resulting shock can propagate to large distances and may produce FRBs as a synchrotron maser.

astro-ph.HE↗

arXiv2022

HouseX: A Fine-grained House Music Dataset and its Potential in the Music Industry

Machine sound classification has been one of the fundamental tasks of music technology. A major branch of sound classification is the classification of music genres. However, though covering most genres of music, existing music genre datasets often do not contain fine-grained labels that indicate the detailed sub-genres of music. In consideration of the consistency of genres of songs in a mixtape or in a DJ (live) set, we have collected and annotated a dataset of house music that provide 4 sub-genre labels, namely future house, bass house, progressive house and melodic house. Experiments show that our annotations well exhibit the characteristics of different categories. Also, we have built baseline models that classify the sub-genre based on the mel-spectrograms of a track, achieving strongly competitive results. Besides, we have put forward a few application scenarios of our dataset and baseline model, with a simulated sci-fi tunnel as a short demo built and rendered in a 3D modeling software, with the colors of the lights automated by the output of our model.

cs.SD↗

arXiv2022

Quantum fluctuations masquerade as halos: Bounds on ultra-light dark matter from quadruply-imaged quasars

Ultra-light dark matter (ULDM) refers to a class of theories, including ultra-light axions, in which particles with mass $m_ψ < 10^{-20}\, \rm{eV}$ comprise a significant fraction of the dark matter. A galactic scale de Broglie wavelength distinguishes these theories from cold dark matter (CDM), suppressing the overall abundance of structure on sub-galactic scales, and producing wave-like interference phenomena in the density profiles of halos. With the aim of constraining the particle mass, we analyze the flux ratios in a sample of eleven quadruple-image strong gravitational lenses. We account for the suppression of the halo mass function and concentration-mass relation predicted by ULDM theories, and the wave-like fluctuations in the host halo density profile, calibrating the model for the wave interference against numerical simulations of galactic-scale halos. We show that the granular structure of halo density profiles, in particular, the amplitude of the fluctuations, significantly impacts image flux ratios, and therefore inferences on the particle mass derived from these data. We infer relative likelihoods of CDM to ULDM of 8:1, 7:1, 6:1, and 4:1 for particle masses $\log_{10}(m_ψ/\rm{eV})\in[-22.5,-22.25], [-22.25,-22.0],[-22.0,-21.75], [-21.75,-21.5]$, respectively. Repeating the analysis and omitting fluctuations associated with the wave interference effects, we obtain relative likelihoods of CDM to ULDM with a particle mass in the same ranges of 98:1, 48:1, 26:1 and 18:1, highlighting the significant perturbation to image flux ratios associated with the fluctuations. Nevertheless, our results disfavor the lightest particle masses with $m_ψ < 10^{-21.5}\,\rm{eV}$, adding to mounting pressure on ultra-light axions as a viable dark matter candidate.

astro-ph.CO↗

arXiv2022

A New Knowledge Distillation Network for Incremental Few-Shot Surface Defect Detection

Surface defect detection is one of the most essential processes for industrial quality inspection. Deep learning-based surface defect detection methods have shown great potential. However, the well-performed models usually require large training data and can only detect defects that appeared in the training stage. When facing incremental few-shot data, defect detection models inevitably suffer from catastrophic forgetting and misclassification problem. To solve these problems, this paper proposes a new knowledge distillation network, called Dual Knowledge Align Network (DKAN). The proposed DKAN method follows a pretraining-finetuning transfer learning paradigm and a knowledge distillation framework is designed for fine-tuning. Specifically, an Incremental RCNN is proposed to achieve decoupled stable feature representation of different categories. Under this framework, a Feature Knowledge Align (FKA) loss is designed between class-agnostic feature maps to deal with catastrophic forgetting problems, and a Logit Knowledge Align (LKA) loss is deployed between logit distributions to tackle misclassification problems. Experiments have been conducted on the incremental Few-shot NEU-DET dataset and results show that DKAN outperforms other methods on various few-shot scenes, up to 6.65% on the mean Average Precision metric, which proves the effectiveness of the proposed method.

cs.CV↗

arXiv2022

Integrated Human Activity Sensing and Communications

Advances in wireless communication and signal processing facilitate integrated sensing and communication a compelling technology that intrinsically combines sensing and communication functionalities for the dual purpose exploitation of wireless hardware resources and pursues mutual benefits. Consequently, the next generation communications network will be perceptive. In this article, we provide a review of human related sensing in the context of ISAC. We first present a general ISAC receiver signal processing framework, with a focus on human activity recognition. Based on its specific spatial deployments, we then categorize ISAC HAR into monostatic, bistatic, and distributed deployments, and discuss their properties, critical research problems and solutions. To facilitate the system's realization and improve its recognition performance, we then explore the inherent connections between the physical layer system parameters and HAR performance metrics. Experimental results are presented for characterizing the sensing potentials of different ISAC systems. Finally, we review the technical challenges and identify the open research problems.

eess.SP↗

arXiv2022

What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions

We propose a novel one-stage Transformer-based semantic and spatial refined transformer (SSRT) to solve the Human-Object Interaction detection task, which requires to localize humans and objects, and predicts their interactions. Differently from previous Transformer-based HOI approaches, which mostly focus at improving the design of the decoder outputs for the final detection, SSRT introduces two new modules to help select the most relevant object-action pairs within an image and refine the queries' representation using rich semantic and spatial features. These enhancements lead to state-of-the-art results on the two most popular HOI benchmarks: V-COCO and HICO-DET.

cs.CV↗

arXiv2022

TubeR: Tubelet Transformer for Video Action Detection

We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we propose to directly detect an action tubelet in a video by simultaneously performing action localization and recognition from a single representation. TubeR learns a set of tubelet-queries and utilizes a tubelet-attention module to model the dynamic spatio-temporal nature of a video clip, which effectively reinforces the model capacity compared to using actor-positional hypotheses in the spatio-temporal space. For videos containing transitional states or scene changes, we propose a context aware classification head to utilize short-term and long-term context to strengthen action classification, and an action switch regression head for detecting the precise temporal action extent. TubeR directly produces action tubelets with variable lengths and even maintains good results for long video clips. TubeR outperforms the previous state-of-the-art on commonly used action detection datasets AVA, UCF101-24 and JHMDB51-21.

cs.CV↗

arXiv2022

Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos. It is based on the finding that gradients from incomplete execution for backpropagation can still effectively train the models with minimal accuracy loss, which attributes to the high redundancy of video. SBP keeps all forward paths but randomly and independently removes the backward paths for each network layer in each training step. It reduces the GPU memory cost by eliminating the need to cache activation values corresponding to the dropped backward paths, whose amount can be controlled by an adjustable keep-ratio. Experiments show that SBP can be applied to a wide range of models for video tasks, leading to up to 80.0% GPU memory saving and 10% training speedup with less than 1% accuracy drop on action recognition and temporal action detection.

cs.CV↗

arXiv2022

Dynamical Effects of Colliding Outflows in Binary Systems

The outflow of an object traveling in a fluid can shape the fluid morphology by forming a forward bow shock which accelerates the object via gravitational feedback. This dynamical effect, namely "dynamical anti-friction", has been studied in idealized infinite uniform media, which suffers from the convergence problem due to the long-range nature of gravitation. In this work, we conduct global 3D hydrodynamic simulations to study this effect in the scenario of a binary system, where the collision of outflows from both stars creates a suitable configuration. We demonstrate with simulations that a dense and slow outflow can give rise to a positive torque on the binary and lead to the expansion of the orbit. As an application, we show that binaries consisting of an AGB star and an outflowing pulsar can experience $\sim 10~\%$ orbit expansion during the AGB stage, in addition to the contribution from mass-loss. We also prove that the gravitational force drops as $O(r^{-3})$ from the center of mass in the binary scenarios, which guarantees a quick converge of the overall effect.

astro-ph.SR↗

arXiv2022

Improving short-term bike sharing demand forecast through an irregular convolutional neural network

As an important task for the management of bike sharing systems, accurate forecast of travel demand could facilitate dispatch and relocation of bicycles to improve user satisfaction. In recent years, many deep learning algorithms have been introduced to improve bicycle usage forecast. A typical practice is to integrate convolutional (CNN) and recurrent neural network (RNN) to capture spatial-temporal dependency in historical travel demand. For typical CNN, the convolution operation is conducted through a kernel that moves across a "matrix-format" city to extract features over spatially adjacent urban areas. This practice assumes that areas close to each other could provide useful information that improves prediction accuracy. However, bicycle usage in neighboring areas might not always be similar, given spatial variations in built environment characteristics and travel behavior that affect cycling activities. Yet, areas that are far apart can be relatively more similar in temporal usage patterns. To utilize the hidden linkage among these distant urban areas, the study proposes an irregular convolutional Long-Short Term Memory model (IrConv+LSTM) to improve short-term bike sharing demand forecast. The model modifies traditional CNN with irregular convolutional architecture to extract dependency among "semantic neighbors". The proposed model is evaluated with a set of benchmark models in five study sites, which include one dockless bike sharing system in Singapore, and four station-based systems in Chicago, Washington, D.C., New York, and London. We find that IrConv+LSTM outperforms other benchmark models in the five cities. The model also achieves superior performance in areas with varying levels of bicycle usage and during peak periods. The findings suggest that "thinking beyond spatial neighbors" can further improve short-term travel demand prediction of urban bike sharing systems.

cs.AI↗

arXiv2021

Long Short-Term Transformer for Online Action Detection

We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm for online action detection, which employs a long- and short-term memory mechanism to model prolonged sequence data. It consists of an LSTR encoder that dynamically leverages coarse-scale historical information from an extended temporal window (e.g., 2048 frames spanning of up to 8 minutes), together with an LSTR decoder that focuses on a short time window (e.g., 32 frames spanning 8 seconds) to model the fine-scale characteristics of the data. Compared to prior work, LSTR provides an effective and efficient method to model long videos with fewer heuristics, which is validated by extensive empirical analysis. LSTR achieves state-of-the-art performance on three standard online action detection benchmarks, THUMOS'14, TVSeries, and HACS Segment. Code has been made available at: https://xumingze0308.github.io/projects/lstr

cs.CV↗

arXiv2021

Improving efficiency of inference in clinical trials with external control data

Suppose we are interested in the effect of a treatment in a clinical trial. The efficiency of inference may be limited due to small sample size. However, external control data are often available from historical studies. Motivated by an application to Helicobacter pylori infection, we show how to borrow strength from such data to improve efficiency of inference in the clinical trial. Under an exchangeability assumption about the potential outcome mean, we show that the semiparametric efficiency bound for estimating the average treatment effect can be reduced by incorporating both the clinical trial data and external controls. We then derive a doubly robust and locally efficient estimator. The improvement in efficiency is prominent especially when the external control dataset has a large sample size and small variability. Our method allows for a relaxed overlap assumption, and we illustrate with the case where the clinical trial only contains a treated group. We also develop doubly robust and locally efficient approaches that extrapolate the causal effect in the clinical trial to the external population and the overall population. Our results also offer a meaningful implication for trial design and data collection. We evaluate the finite-sample performance of the proposed estimators via simulation. In the Helicobacter pylori infection application, our approach shows that the combination treatment has potential efficacy advantages over the triple therapy.

stat.ME↗

arXiv2021

SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation

Temporal action segmentation is a task to classify each frame in the video with an action label. However, it is quite expensive to annotate every frame in a large corpus of videos to construct a comprehensive supervised training dataset. Thus in this work we propose an unsupervised method, namely SSCAP, that operates on a corpus of unlabeled videos and predicts a likely set of temporal segments across the videos. SSCAP leverages Self-Supervised learning to extract distinguishable features and then applies a novel Co-occurrence Action Parsing algorithm to not only capture the correlation among sub-actions underlying the structure of activities, but also estimate the temporal path of the sub-actions in an accurate and general way. We evaluate on both classic datasets (Breakfast, 50Salads) and the emerging fine-grained action dataset (FineGym) with more complex activity structures and similar sub-actions. Results show that SSCAP achieves state-of-the-art performance on all datasets and can even outperform some weakly-supervised approaches, demonstrating its effectiveness and generalizability.

cs.CV↗

arXiv2021

VidTr: Video Transformer Without Convolutions

We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal information via stacked attentions and provide better performance with higher efficiency. We first introduce the vanilla video transformer and show that transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage. We then present VidTr which reduces the memory cost by 3.3$\times$ while keeping the same performance. To further optimize the model, we propose the standard deviation based topK pooling for attention ($pool_{topK\_std}$), which reduces the computation by dropping non-informative features along temporal dimension. VidTr achieves state-of-the-art performance on five commonly used datasets with lower computational requirement, showing both the efficiency and effectiveness of our design. Finally, error analysis and visualization show that VidTr is especially good at predicting actions that require long-term temporal reasoning.

cs.CV↗