arXiv subjects

Yue Zhao

Publications and source records attributed to Yue Zhao.

At least 325 records · Page 18Linked to original sources

arXiv2023

Online Kernel Sliced Inverse Regression

Online dimension reduction is a common method for high-dimensional streaming data processing. Online principal component analysis, online sliced inverse regression, online kernel principal component analysis and other methods have been studied in depth, but as far as we know, online supervised nonlinear dimension reduction methods have not been fully studied. In this article, an online kernel sliced inverse regression method is proposed. By introducing the approximate linear dependence condition and dictionary variable sets, we address the problem of increasing variable dimensions with the sample size in the online kernel sliced inverse regression method, and propose a reduced-order method for updating variables online. We then transform the problem into an online generalized eigen-decomposition problem, and use the stochastic optimization method to update the centered dimension reduction directions. Simulations and the real data analysis show that our method can achieve close performance to batch processing kernel sliced inverse regression.

stat.CO↗

arXiv2023

The average degree of edge chromatic critical graphs with maximum degree seven

In this paper, by developing several new adjacency lemmas about a path on $4$ or $5$ vertices, we show that the average degree of 7-critical graphs is at least 6. It implies Vizing's planar graph conjecture for planar graphs with maximum degree $7$ and its extension to graphs embeddable in a surface with nonnegative Euler characteristic due to Sanders and Zhao (J. Combin. Theory Ser. B 83 (2001) 201-212 and J. Combin. Theory Ser. B 87 (2003) 254-263) and Zhang (Graphs and Combinatorics 16 (2000) 467-495).

math.CO↗

arXiv2022

Detection of Early-Universe Gravitational Wave Signatures and Fundamental Physics

Detection of a gravitational-wave signal of non-astrophysical origin would be a landmark discovery, potentially providing a significant clue to some of our most basic, big-picture scientific questions about the Universe. In this white paper, we survey the leading early-Universe mechanisms that may produce a detectable signal -- including inflation, phase transitions, topological defects, as well as primordial black holes -- and highlight the connections to fundamental physics. We review the complementarity with collider searches for new physics, and multimessenger probes of the large-scale structure of the Universe.

gr-qc↗

arXiv2022

Learning Video Representations from Large Language Models

We introduce LaViLa, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video narrators. Our auto-generated narrations offer a number of advantages, including dense coverage of long videos, better temporal synchronization of the visual information and text, and much higher diversity of text. The video-text embedding learned contrastively with these additional auto-generated narrations outperforms the previous state-of-the-art on multiple first-person and third-person video tasks, both in zero-shot and finetuned setups. Most notably, LaViLa obtains an absolute gain of 10.1% on EGTEA classification and 5.9% Epic-Kitchens-100 multi-instance retrieval benchmarks. Furthermore, LaViLa trained with only half the narrations from the Ego4D dataset outperforms baseline models trained on the full set, and shows positive scaling behavior on increasing pre-training data and model size.

cs.CV↗

arXiv2022

ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels

Existing works on anomaly detection (AD) rely on clean labels from human annotators that are expensive to acquire in practice. In this work, we propose a method to leverage weak/noisy labels (e.g., risk scores generated by machine rules for detecting malware) that are cheaper to obtain for anomaly detection. Specifically, we propose ADMoE, the first framework for anomaly detection algorithms to learn from noisy labels. In a nutshell, ADMoE leverages mixture-of-experts (MoE) architecture to encourage specialized and scalable learning from multiple noisy sources. It captures the similarities among noisy labels by sharing most model parameters, while encouraging specialization by building "expert" sub-networks. To further juice out the signals from noisy labels, ADMoE uses them as input features to facilitate expert learning. Extensive results on eight datasets (including a proprietary enterprise security dataset) demonstrate the effectiveness of ADMoE, where it brings up to 34% performance improvement over not using it. Also, it outperforms a total of 13 leading baselines with equivalent network parameters and FLOPS. Notably, ADMoE is model-agnostic to enable any neural network-based detection methods to handle noisy labels, where we showcase its results on both multiple-layer perceptron (MLP) and the leading AD method DeepSAD.

cs.LG↗

arXiv2022

A natural ionic liquid: low molecular mass compounds of aggregate glue droplets on spider orb webs

The aggregate glue of spider orb web is an excellent natural adhesive. Orb-weaver spiders use micron-scale aggregate glue droplets to retain prey in the capture spiral silks of their orb web. In aggregate glue droplets, highly glycosylated and phosphorylated proteins dissolve in low molecular mass compounds. The aggregate glue droplets show a heterogeneous structural distribution after attaching to the substrate. Although components of the aggregate glue droplets have been well analyzed and determined in past studies, visualization of the spatial distribution of their chemical components before and after their attachment is the key to exploring their adhesion mechanisms. Here, we investigated the distribution of low molecular mass compounds and glycoproteins in aggregate glue droplets using the in situ measurement methods and visualized the role of specific low molecular mass compounds in promoting glycoprotein modification in the aggregate glue. The results of the analysis suggest that the constituents of aggregate glue droplets include at least one ionic liquid: hydrated choline dihydrogen phosphate, while the modification of glycoproteins in aggregate glue depends on the concentration of this ionic liquid. This natural ionic liquid does not affect the fluorescence activity of fluorescent proteins, indicating that proteins of aggregate glue droplets can be dissolved well and maintain the stability of their higher-order structures in that ionic liquid. As a natural ionic liquid, aggregate glue droplets from the spider orb webs may be an excellent ionic liquid material model.

cond-mat.soft↗

arXiv2022

Decomposition of class II graphs into two class I graphs

Mkrtchyan and Steffen [J. Graph Theory, 70 (4), 473--482, 2012] showed that every class II simple graph can be decomposed into a maximum $Δ$-edge-colorable subgraph and a matching. They further conjectured that every graph $G$ with chromatic index $Δ(G)+k$ ($k\geq 1$) can be decomposed into a maximum $Δ(G)$-edge-colorable subgraph (not necessarily class I) and a $k$-edge-colorable subgraph. In this paper, we first generalize their result to multigraphs and show that every multigraph $G$ with multiplicity $μ$ can be decomposed into a maximum $Δ(G)$-edge-colorable subgraph and a subgraph with maximum degree at most $μ$. Then we prove that every graph $G$ with chromatic index $Δ(G)+k$ can be decomposed into two class I subgraphs $H_1$ and $H_2$ such that $Δ(H_1) = Δ(G)$ and $Δ(H_2) = k$, which is a variation of their conjecture.

math.CO↗

arXiv2022

On the topological surface states of the intrinsic magnetic topological insulator Mn-Bi-Te family

We review recent progress in the electronic structure study of intrinsic magnetic topological insulators (MnBi$_2$Te$_4$)(Bi$_2$Te$_3$)$_n$ ($n=0,1,2,3$) family. Specifically, we focus on the ubiquitously (nearly) gapless behavior of the topological surface state Dirac cone observed by photoemission spectroscopy, even though a large Dirac gap is expected because of surface ferromagnetic order. The dichotomy between experiment and theory concerning this gap behavior is perhaps the most critical and puzzling question in this frontier. We discuss various proposals accounting for the lack of magnetic effect on the topological surface state Dirac cone, which are mainly categorized into two pictures, magnetic reconfiguration, and topological surface state redistribution. Band engineering towards opening a magnetic gap of topological surface states provides great opportunities to realize quantized topological transport and axion electrodynamics at higher temperatures.

cond-mat.mes-hall↗

arXiv2022

Toward Unsupervised Outlier Model Selection

Today there exists no shortage of outlier detection algorithms in the literature, yet the complementary and critical problem of unsupervised outlier model selection (UOMS) is vastly understudied. In this work we propose ELECT, a new approach to select an effective candidate model, i.e. an outlier detection algorithm and its hyperparameter(s), to employ on a new dataset without any labels. At its core, ELECT is based on meta-learning; transferring prior knowledge (e.g. model performance) on historical datasets that are similar to the new one to facilitate UOMS. Uniquely, it employs a dataset similarity measure that is performance-based, which is more direct and goal-driven than other measures used in the past. ELECT adaptively searches for similar historical datasets, as such, it can serve an output on-demand, being able to accommodate varying time budgets. Extensive experiments show that ELECT significantly outperforms a wide range of basic UOMS baselines, including no model selection (always using the same popular model such as iForest) as well as more recent selection strategies based on meta-features.

cs.LG↗

arXiv2022

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

Detecting which nodes in graphs are outliers is a relatively new machine learning task with numerous applications. Despite the proliferation of algorithms developed in recent years for this task, there has been no standard comprehensive setting for performance evaluation. Consequently, it has been difficult to understand which methods work well and when under a broad range of settings. To bridge this gap, we present--to the best of our knowledge--the first comprehensive benchmark for unsupervised outlier node detection on static attributed graphs called BOND, with the following highlights. (1) We benchmark the outlier detection performance of 14 methods ranging from classical matrix factorization to the latest graph neural networks. (2) Using nine real datasets, our benchmark assesses how the different detection methods respond to two major types of synthetic outliers and separately to "organic" (real non-synthetic) outliers. (3) Using an existing random graph generation technique, we produce a family of synthetically generated datasets of different graph sizes that enable us to compare the running time and memory usage of the different outlier detection algorithms. Based on our experimental results, we discuss the pros and cons of existing graph outlier detection algorithms, and we highlight opportunities for future research. Importantly, our code is freely available and meant to be easily extendable: https://github.com/pygod-team/pygod/tree/main/benchmark

cs.LG↗

arXiv2022

Hyperparameter Optimization for Unsupervised Outlier Detection

Given an unsupervised outlier detection (OD) algorithm, how can we optimize its hyperparameter(s) (HP) on a new dataset, without any labels? In this work, we address this challenging hyperparameter optimization for unsupervised OD problem, and propose the first systematic approach called HPOD that is based on meta-learning. HPOD capitalizes on the prior performance of a large collection of HPs on existing OD benchmark datasets, and transfers this information to enable HP evaluation on a new dataset without labels. Moreover, HPOD adapts a prominent sampling paradigm to identify promising HPs efficiently. Extensive experiments show that HPOD works with both deep (e.g., Robust AutoEncoder) and shallow (e.g., Local Outlier Factor (LOF) and Isolation Forest (iForest)) OD algorithms on discrete and continuous HP spaces, and outperforms a wide range of baselines with on average 58% and 66% performance improvement over the default HPs of LOF and iForest.

cs.LG↗

arXiv2022

Probing Early Universe Supercooled Phase Transitions with Gravitational Wave Data

We investigate the reach of the LIGO/Virgo/KAGRA detectors in the search for signatures of first-order phase transitions in the early Universe. Utilising data from the first three observing runs, we derive constraints on the parameters of the underlying gravitational-wave background, focusing on transitions characterised by strong supercooling. As an application of our analysis, we determine bounds on the parameter space of two representative particle physics models. We also comment on the expected reach of third-generation detectors in probing supercooled phase transitions.

hep-ph↗

arXiv2022

Birefringence Tomography for Axion Cloud

An axion cloud surrounding a supermassive black hole can be naturally produced through the superradiance process. Its existence can be examined by the axion induced birefringence effect. It predicts an oscillation of the electric vector position angle of linearly polarized radiations. Stringent constraints of the existence of the axion in a particular mass window has been obtained based on the recent Event Horizon Telescope measurement on M87$^\star$. The future Very-Long-Baseline Interferometry (VLBI) observations will be able to measure the vicinity of many supermassive black holes, thus it opens the possibility to search for the existence of axions in a wide mass regime. In this paper, we study how different black hole properties and accretion flows influence the signatures of the axion induced birefringence. We include the impacts of black hole inclination angles, spins, magnetic fields, plasma velocity distributions, the thickness of the accretion flows. We pay special attention to characterize the washout effects induced by the finite thickness of the accretion flows and the lensed photons. Based on this study, we give prospects on how to optimize the axion search using future VLBI observations, such as the next-generation Event Horizon Telescope, to further increase the sensitivity.

hep-ph↗

arXiv2022

Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks

Deep learning models have achieved excellent recognition results on large-scale video benchmarks. However, they perform poorly when applied to videos with rare scenes or objects, primarily due to the bias of existing video datasets. We tackle this problem from two different angles: algorithm and dataset. From the perspective of algorithms, we propose Spatial-aware Multi-Aspect Debiasing (SMAD), which incorporates both explicit debiasing with multi-aspect adversarial training and implicit debiasing with the spatial actionness reweighting module, to learn a more generic representation invariant to non-action aspects. To neutralize the intrinsic dataset bias, we propose OmniDebias to leverage web data for joint training selectively, which can achieve higher performance with far fewer web data. To verify the effectiveness, we establish evaluation protocols and perform extensive experiments on both re-distributed splits of existing datasets and a new evaluation dataset focusing on the action with rare scenes. We also show that the debiased representation can generalize better when transferred to other datasets and tasks.

cs.CV↗

arXiv2022

Real-time Online Video Detection with Temporal Smoothing Transformers

Streaming video recognition reasons about objects and their actions in every frame of a video. A good streaming recognition model captures both long-term dynamics and short-term changes of video. Unfortunately, in most existing methods, the computational complexity grows linearly or quadratically with the length of the considered dynamics. This issue is particularly pronounced in transformer-based architectures. To address this issue, we reformulate the cross-attention in a video transformer through the lens of kernel and apply two kinds of temporal smoothing kernel: A box kernel or a Laplace kernel. The resulting streaming attention reuses much of the computation from frame to frame, and only requires a constant time update each frame. Based on this idea, we build TeSTra, a Temporal Smoothing Transformer, that takes in arbitrarily long inputs with constant caching and computing overhead. Specifically, it runs $6\times$ faster than equivalent sliding-window based transformers with 2,048 frames in a streaming setting. Furthermore, thanks to the increased temporal span, TeSTra achieves state-of-the-art results on THUMOS'14 and EPIC-Kitchen-100, two standard online action detection and action anticipation datasets. A real-time version of TeSTra outperforms all but one prior approaches on the THUMOS'14 dataset.

cs.CV↗

arXiv2022

TOD: GPU-accelerated Outlier Detection via Tensor Operations

Outlier detection (OD) is a key learning task for finding rare and deviant data samples, with many time-critical applications such as fraud detection and intrusion detection. In this work, we propose TOD, the first tensor-based system for efficient and scalable outlier detection on distributed multi-GPU machines. A key idea behind TOD is decomposing complex OD applications into a small collection of basic tensor algebra operators. This decomposition enables TOD to accelerate OD computations by leveraging recent advances in deep learning infrastructure in both hardware and software. Moreover, to deploy memory-intensive OD applications on modern GPUs with limited on-device memory, we introduce two key techniques. First, provable quantization speeds up OD computations and reduces its memory footprint by automatically performing specific floating-point operations in lower precision while provably guaranteeing no accuracy loss. Second, to exploit the aggregated compute resources and memory capacity of multiple GPUs, we introduce automatic batching, which decomposes OD computations into small batches for both sequential execution on a single GPU and parallel execution on multiple GPUs. TOD supports a diverse set of OD algorithms. Extensive evaluation on 11 real and 3 synthetic OD datasets shows that TOD is on average 10.9x faster than the leading CPU-based OD system PyOD (with a maximum speedup of 38.9x), and can handle much larger datasets than existing GPU-based OD systems. In addition, TOD allows easy integration of new OD operators, enabling fast prototyping of emerging and yet-to-discovered OD algorithms.

cs.LG↗

arXiv2022

ADBench: Anomaly Detection Benchmark

Given a long list of anomaly detection algorithms developed in the last few decades, how do they perform with regard to (i) varying levels of supervision, (ii) different types of anomalies, and (iii) noisy and corrupted data? In this work, we answer these key questions by conducting (to our best knowledge) the most comprehensive anomaly detection benchmark with 30 algorithms on 57 benchmark datasets, named ADBench. Our extensive experiments (98,436 in total) identify meaningful insights into the role of supervision and anomaly types, and unlock future directions for researchers in algorithm selection and design. With ADBench, researchers can easily conduct comprehensive and fair evaluations for newly proposed methods on the datasets (including our contributed ones from natural language and computer vision domains) against the existing baselines. To foster accessibility and reproducibility, we fully open-source ADBench and the corresponding results.

cs.LG↗

arXiv2022

ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions

Outlier detection refers to the identification of data points that deviate from a general data distribution. Existing unsupervised approaches often suffer from high computational cost, complex hyperparameter tuning, and limited interpretability, especially when working with large, high-dimensional datasets. To address these issues, we present a simple yet effective algorithm called ECOD (Empirical-Cumulative-distribution-based Outlier Detection), which is inspired by the fact that outliers are often the "rare events" that appear in the tails of a distribution. In a nutshell, ECOD first estimates the underlying distribution of the input data in a nonparametric fashion by computing the empirical cumulative distribution per dimension of the data. ECOD then uses these empirical distributions to estimate tail probabilities per dimension for each data point. Finally, ECOD computes an outlier score of each data point by aggregating estimated tail probabilities across dimensions. Our contributions are as follows: (1) we propose a novel outlier detection method called ECOD, which is both parameter-free and easy to interpret; (2) we perform extensive experiments on 30 benchmark datasets, where we find that ECOD outperforms 11 state-of-the-art baselines in terms of accuracy, efficiency, and scalability; and (3) we release an easy-to-use and scalable (with distributed support) Python implementation for accessibility and reproducibility.

cs.LG↗