arXiv subjects

Chi Wang

Publications and source records attributed to Chi Wang.

At least 109 records · Page 6Linked to original sources

arXiv2024

Spatio-temporal Prompting Network for Robust Video Feature Extraction

Frame quality deterioration is one of the main challenges in the field of video understanding. To compensate for the information loss caused by deteriorated frames, recent approaches exploit transformer-based integration modules to obtain spatio-temporal information. However, these integration modules are heavy and complex. Furthermore, each integration module is specifically tailored for its target task, making it difficult to generalise to multiple tasks. In this paper, we present a neat and unified framework, called Spatio-Temporal Prompting Network (STPN). It can efficiently extract robust and accurate video features by dynamically adjusting the input features in the backbone network. Specifically, STPN predicts several video prompts containing spatio-temporal information of neighbour frames. Then, these video prompts are prepended to the patch embeddings of the current frame as the updated input for video feature extraction. Moreover, STPN is easy to generalise to various video tasks because it does not contain task-specific modules. Without bells and whistles, STPN achieves state-of-the-art performance on three widely-used datasets for different video understanding tasks, i.e., ImageNetVID for video object detection, YouTubeVIS for video instance segmentation, and GOT-10k for visual object tracking. Code is available at https://github.com/guanxiongsun/vfe.pytorch.

cs.CV↗

arXiv2023

Velocity Space Signatures of Resonant Energy Transfer between Whistler Waves and Electrons in the Earth's Magnetosheath

Wave--particle interactions play a crucial role in transferring energy between electromagnetic fields and charged particles in space and astrophysical plasmas. Despite the prevalence of different electromagnetic waves in space, there is still a lack of understanding of fundamental aspects of wave--particle interactions, particularly in terms of energy flow and velocity-space characteristics. In this study, we combine a novel quasilinear model with observations from the Magnetospheric Multiscale (MMS) mission to reveal the signatures of resonant interactions between electrons and whistler waves in magnetic holes, which are coherent structures often found in the Earth's magnetosheath. We investigate the energy transfer rates and velocity-space characteristics associated with Landau and cyclotron resonances between electrons and slightly oblique propagating whistler waves. In the case of our observed magnetic hole, the loss of electron kinetic energy primarily contributes to the growth of whistler waves through the $n=-1$ cyclotron resonance, where $n$ is the order of the resonance expansion in linear Vlasov--Maxwell theory. The excitation of whistler waves leads to a reduction of the temperature anisotropy and parallel heating of the electrons. Our study offers a new and self-consistent understanding of resonant energy transfer in turbulent plasmas.

physics.plasm-ph↗

arXiv2023

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.

cs.AI↗

arXiv2023

EcoAssistant: Using LLM Assistant More Affordably and Accurately

Today, users ask Large language models (LLMs) as assistants to answer queries that require external knowledge; they ask about the weather in a specific city, about stock prices, and even about where specific locations are within their neighborhood. These queries require the LLM to produce code that invokes external APIs to answer the user's question, yet LLMs rarely produce correct code on the first try, requiring iterative code refinement upon execution results. In addition, using LLM assistants to support high query volumes can be expensive. In this work, we contribute a framework, EcoAssistant, that enables LLMs to answer code-driven queries more affordably and accurately. EcoAssistant contains three components. First, it allows the LLM assistants to converse with an automatic code executor to iteratively refine code or to produce answers based on the execution results. Second, we use a hierarchy of LLM assistants, which attempts to answer the query with weaker, cheaper LLMs before backing off to stronger, expensive ones. Third, we retrieve solutions from past successful queries as in-context demonstrations to help subsequent queries. Empirically, we show that EcoAssistant offers distinct advantages for affordability and accuracy, surpassing GPT-4 by 10 points of success rate with less than 50% of GPT-4's cost.

cs.SE↗

arXiv2023

Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference

Large Language Models (LLMs) have sparked significant interest in their generative capabilities, leading to the development of various commercial applications. The high cost of using the models drives application builders to maximize the value of generation under a limited inference budget. This paper presents a study of optimizing inference hyperparameters such as the number of responses, temperature and max tokens, which significantly affects the utility/cost of text generation. We design a framework named EcoOptiGen which leverages economical hyperparameter optimization and cost-based pruning. Experiments with the GPT-3.5/GPT-4 models on a variety of tasks verify its effectiveness. EcoOptiGen is implemented in the `autogen' package of the FLAML library: \url{https://aka.ms/autogen}.

cs.CL↗

arXiv2023

HyperTime: Hyperparameter Optimization for Combating Temporal Distribution Shifts

In this work, we propose a hyperparameter optimization method named \emph{HyperTime} to find hyperparameters robust to potential temporal distribution shifts in the unseen test data. Our work is motivated by an important observation that it is, in many cases, possible to achieve temporally robust predictive performance via hyperparameter optimization. Based on this observation, we leverage the `worst-case-oriented' philosophy from the robust optimization literature to help find such robust hyperparameter configurations. HyperTime imposes a lexicographic priority order on average validation loss and worst-case validation loss over chronological validation sets. We perform a theoretical analysis on the upper bound of the expected test loss, which reveals the unique advantages of our approach. We also demonstrate the strong empirical performance of the proposed method on multiple machine learning tasks with temporal distribution shifts.

cs.LG↗

arXiv2023

Towards Lightweight and Automated Representation Learning System for Networks

We propose LIGHTNE 2.0, a cost-effective, scalable, automated, and high-quality network embedding system that scales to graphs with hundreds of billions of edges on a single machine. In contrast to the mainstream belief that distributed architecture and GPUs are needed for large-scale network embedding with good quality, we prove that we can achieve higher quality, better scalability, lower cost, and faster runtime with shared-memory, CPU-only architecture. LIGHTNE 2.0 combines two theoretically grounded embedding methods NetSMF and ProNE. We introduce the following techniques to network embedding for the first time: (1) a newly proposed downsampling method to reduce the sample complexity of NetSMF while preserving its theoretical advantages; (2) a high-performance parallel graph processing stack GBBS to achieve high memory efficiency and scalability; (3) sparse parallel hash table to aggregate and maintain the matrix sparsifier in memory; (4) a fast randomized singular value decomposition (SVD) enhanced by power iteration and fast orthonormalization to improve vanilla randomized SVD in terms of both efficiency and effectiveness; (5) Intel MKL for proposed fast randomized SVD and spectral propagation; and (6) a fast and lightweight AutoML library FLAML for automated hyperparameter tuning. Experimental results show that LIGHTNE 2.0 can be up to 84X faster than GraphVite, 30X faster than PBG and 9X faster than NetSMF while delivering better performance. LIGHTNE 2.0 can embed very large graph with 1.7 billion nodes and 124 billion edges in half an hour on a CPU server, while other baselines cannot handle very large graphs of this scale.

cs.SI↗

arXiv2022

FairAutoML: Embracing Unfairness Mitigation in AutoML

In this work, we propose an Automated Machine Learning (AutoML) system to search for models not only with good prediction accuracy but also fair. We first investigate the necessity and impact of unfairness mitigation in the AutoML context. We establish the FairAutoML framework. The framework provides a novel design based on pragmatic abstractions, which makes it convenient to incorporate existing fairness definitions, unfairness mitigation techniques, and hyperparameter search methods into the model search and evaluation process. Following this framework, we develop a fair AutoML system based on an existing AutoML system. The augmented system includes a resource allocation strategy to dynamically decide when and on which models to conduct unfairness mitigation according to the prediction accuracy, fairness, and resource consumption on the fly. Extensive empirical evaluation shows that our system can achieve a good `fair accuracy' and high resource efficiency.

cs.LG↗

arXiv2022

The SMILE mission

This chapter describes the SMILE (Solar wind Magnetosphere Ionosphere Link Explorer) mission, currently under development as a joint project of the European Space Agency and the Chinese Academy of Sciences. SMILE aims to study the solar wind coupling with the terrestrial magnetosphere in a very novel and global way, by imaging the Earth's magnetosheath and cusps in X-rays emitted when high charge-state solar wind ions exchange charges with exospheric neutrals. SMILE combines this with simultaneous UV imaging of the northern aurora and in-situ plasma and magnetic field measurements of the magnetosheath and solar wind while flying in a highly elliptical northern polar orbit. In this chapter, after a brief introduction to the science that SMILE is targeted to investigate, the payload and the spacecraft, and progress in their development, are described. The mission operations in space, the ground segment and the scientific preparations that will ensure the optimal exploitation of SMILE measurements are also presented. The international space plasma and planetary communities are looking forward to the step change that SMILE will provide by making visible our invisible terrestrial magnetosphere.

physics.space-ph↗

arXiv2022

ACE: Adaptive Constraint-aware Early Stopping in Hyperparameter Optimization

Deploying machine learning models requires high model quality and needs to comply with application constraints. That motivates hyperparameter optimization (HPO) to tune model configurations under deployment constraints. The constraints often require additional computation cost to evaluate, and training ineligible configurations can waste a large amount of tuning cost. In this work, we propose an Adaptive Constraint-aware Early stopping (ACE) method to incorporate constraint evaluation into trial pruning during HPO. To minimize the overall optimization cost, ACE estimates the cost-effective constraint evaluation interval based on a theoretical analysis of the expected evaluation cost. Meanwhile, we propose a stratum early stopping criterion in ACE, which considers both optimization and constraint metrics in pruning and does not require regularization hyperparameters. Our experiments demonstrate superior performance of ACE in hyperparameter tuning of classification tasks under fairness or robustness constraints.

cs.LG↗

arXiv2022

SMILE: A novel way to explore solar-terrestrial interactions

This chapter describes the scientific motivations that led to the development of the SMILE (Solar wind Magnetosphere Ionosphere Link Explorer) mission. The solar wind coupling with the terrestrial magnetosphere is a key link in Sun-Earth interactions. In-situ missions can provide detailed observations of plasma and magnetic field conditions in the solar wind and the magnetosphere, but leave us still unable to fully quantify the global effects of the drivers of Sun-Earth connections, and to monitor their evolution. This information is essential to develop a comprehensive understanding of how the Sun controls the Earth's plasma environment and space weather. SMILE offers a new approach to global monitoring of geospace by imaging the magnetosheath and cusps in X-rays emitted when high charge-state solar wind ions exchange charges with exospheric neutrals. SMILE combines this with simultaneous UV imaging of the northern aurora and in-situ plasma and magnetic field measurements in the magnetosheath and solar wind from a highly elliptical northern polar orbit. In this chapter the science that SMILE will explore and the scientific preparations that will ensure the optimal exploitation of SMILE measurements are presented.

physics.space-ph↗

arXiv2022

Whistler Waves As a Signature of Converging Magnetic Holes in Space Plasmas

Magnetic holes are plasma structures that trap a large number of particles in a magnetic field that is weaker than the field in its surroundings. The unprecedented high time-resolution observations by NASA's Magnetospheric Multi-Scale (MMS) mission enable us to study the particle dynamics in magnetic holes in the Earth's magnetosheath in great detail. We reveal the local generation mechanism of whistler waves by a combination of Landau-resonant and cyclotron-resonant wave-particle interactions of electrons in response to the large-scale evolution of a magnetic hole. As the magnetic hole converges, a pair of counter-streaming electron beams form near the hole's center as a consequence of the combined action of betatron and Fermi effects. The beams trigger the generation of slightly-oblique whistler waves. Our conceptual prediction is supported by a remarkable agreement between our observations and numerical predictions from the Arbitrary Linear Plasma Solver (ALPS). Our study shows that wave-particle interactions are fundamental to the evolution of magnetic holes in space and astrophysical plasmas.

physics.plasm-ph↗

arXiv2022

Multivariate Sparse Group Lasso Joint Model for Radiogenomics Data

Radiogenomics is an emerging field in cancer research that combines medical imaging data with genomic data to predict patients clinical outcomes. In this paper, we propose a multivariate sparse group lasso joint model to integrate imaging and genomic data for building prediction models. Specifically, we jointly consider two models, one regresses imaging features on genomic features, and the other regresses patients clinical outcomes on genomic features. The regularization penalties through sparse group lasso allow incorporation of intrinsic group information, e.g. biological pathway and imaging category, to select both important intrinsic groups and important features within a group. To integrate information from the two models, in each model, we introduce a weight in the penalty term of each individual genomic feature, where the weight is inversely correlated with the model coefficient of that feature in the other model. This weight allows a feature to have a higher chance of selection by one model if it is selected by the other model. Our model is applicable to both continuous and time to event outcomes. It also allows the use of two separate datasets to fit the two models, addressing a practical challenge that many genomic datasets do not have imaging data available. Simulations and real data analyses demonstrate that our method outperforms existing methods in the literature.

stat.ME↗

arXiv2022

Mining Robust Default Configurations for Resource-constrained AutoML

Automatic machine learning (AutoML) is a key enabler of the mass deployment of the next generation of machine learning systems. A key desideratum for future ML systems is the automatic selection of models and hyperparameters. We present a novel method of selecting performant configurations for a given task by performing offline autoML and mining over a diverse set of tasks. By mining the training tasks, we can select a compact portfolio of configurations that perform well over a wide variety of tasks, as well as learn a strategy to select portfolio configurations for yet-unseen tasks. The algorithm runs in a zero-shot manner, that is without training any models online except the chosen one. In a compute- or time-constrained setting, this virtually instant selection is highly performant. Further, we show that our approach is effective for warm-starting existing autoML platforms. In both settings, we demonstrate an improvement on the state-of-the-art by testing over 62 classification and regression datasets. We also demonstrate the utility of recommending data-dependent default configurations that outperform widely used hand-crafted defaults.

cs.LG↗

arXiv2022

Active Boundary Loss for Semantic Segmentation

This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced in commonly used cross-entropy loss. Based on the predicted boundaries detected from the segmentation results using current network parameters, we formulate the boundary alignment problem as a differentiable direction vector prediction problem to guide the movement of predicted boundaries in each iteration. Our loss is model-agnostic and can be plugged in to the training of segmentation networks to improve the boundary details. Experimental results show that training with the active boundary loss can effectively improve the boundary F-score and mean Intersection-over-Union on challenging image and video object segmentation datasets.

cs.CV↗

arXiv2021

Bounding the Last Mile: Efficient Learned String Indexing

We introduce the RadixStringSpline (RSS) learned index structure for efficiently indexing strings. RSS is a tree of radix splines each indexing a fixed number of bytes. RSS approaches or exceeds the performance of traditional string indexes while using 7-70$\times$ less memory. RSS achieves this by using the minimal string prefix to sufficiently distinguish the data unlike most learned approaches which index the entire string. Additionally, the bounded-error nature of RSS accelerates the last mile search and also enables a memory-efficient hash-table lookup accelerator. We benchmark RSS on several real-world string datasets against ART and HOT. Our experiments suggest this line of research may be promising for future memory-intensive database applications.

cs.DB↗

arXiv2021

Estimating the Distribution of Ratio of Paired Event Times in Phase II Oncology Trials

With the rapid development of new anti-cancer agents which are cytostatic, new endpoints are needed to better measure treatment efficacy in phase II trials. For this purpose, Von Hoff (1998) proposed the growth modulation index (GMI), i.e. the ratio between times to progression or progression-free survival times in two successive treatment lines. An essential task in studies using GMI as an endpoint is to estimate the distribution of GMI. Traditional methods for survival data have been used for estimating the GMI distribution because censoring is common for GMI data. However, we point out that the independent censoring assumption required by traditional survival methods is always violated for GMI, which may lead to severely biased results. In this paper, we construct nonparametric estimators for the distribution of GMI, accounting for the dependent censoring of GMI. We prove that the proposed estimators are consistent and converge weakly to zero-mean Gaussian processes upon proper normalization. Extensive simulation studies show that our estimators perform well in practical situations and outperform traditional methods. A phase II clinical trial using GMI as the primary endpoint is provided for illustration.

stat.ME↗

arXiv2021

Weighted Mean Difference Statistics for Paired Data in Presence of Missing Values

Missing data is a common issue in many biomedical studies. Under a paired design, some subjects may have missing values in either one or both of the conditions due to loss of follow-up, insufficient biological samples, etc. Such partially paired data complicate statistical comparison of the distribution of the variable of interest between the two conditions. In this paper, we propose a general class of test statistics based on the difference in weighted sample means without imposing any distributional or model assumption. An optimal weight is derived for this class of tests. Simulation studies show that our proposed test with the optimal weight performs well and outperforms existing methods in practical situations. Two cancer biomarker studies are provided for illustration.

stat.ME↗