arXiv subjects

Qiang Liu

Publications and source records attributed to Qiang Liu.

At least 181 records · Page 10Linked to original sources

arXiv2024

Taurus Database: How to be Fast, Available, and Frugal in the Cloud

Using cloud Database as a Service (DBaaS) offerings instead of on-premise deployments is increasingly common. Key advantages include improved availability and scalability at a lower cost than on-premise alternatives. In this paper, we describe the design of Taurus, a new multi-tenant cloud database system. Taurus separates the compute and storage layers in a similar manner to Amazon Aurora and Microsoft Socrates and provides similar benefits, such as read replica support, low network utilization, hardware sharing and scalability. However, the Taurus architecture has several unique advantages. Taurus offers novel replication and recovery algorithms providing better availability than existing approaches using the same or fewer replicas. Also, Taurus is highly optimized for performance, using no more than one network hop on critical paths and exclusively using append-only storage, delivering faster writes, reduced device wear, and constant-time snapshots. This paper describes Taurus and provides a detailed description and analysis of the storage node architecture, which has not been previously available from the published literature.

cs.DB↗

arXiv2024

Rectified Flow For Structure Based Drug Design

Deep generative models have achieved tremendous success in structure-based drug design in recent years, especially for generating 3D ligand molecules that bind to specific protein pocket. Notably, diffusion models have transformed ligand generation by providing exceptional quality and creativity. However, traditional diffusion models are restricted by their conventional learning objectives, which limit their broader applicability. In this work, we propose a new framework FlowSBDD, which is based on rectified flow model, allows us to flexibly incorporate additional loss to optimize specific target and introduce additional condition either as an extra input condition or replacing the initial Gaussian distribution. Extensive experiments on CrossDocked2020 show that our approach could achieve state-of-the-art performance on generating high-affinity molecules while maintaining proper molecular properties without specifically designing binding site, with up to -8.50 Avg. Vina Dock score and 75.0% Diversity.

cs.LG↗

arXiv2024

InsightEdit: Towards Better Instruction Following for Image Editing

In this paper, we focus on the task of instruction-based image editing. Previous works like InstructPix2Pix, InstructDiffusion, and SmartEdit have explored end-to-end editing. However, two limitations still remain: First, existing datasets suffer from low resolution, poor background consistency, and overly simplistic instructions. Second, current approaches mainly condition on the text while the rich image information is underexplored, therefore inferior in complex instruction following and maintaining background consistency. Targeting these issues, we first curated the AdvancedEdit dataset using a novel data construction pipeline, formulating a large-scale dataset with high visual quality, complex instructions, and good background consistency. Then, to further inject the rich image information, we introduce a two-stream bridging mechanism utilizing both the textual and visual features reasoned by the powerful Multimodal Large Language Models (MLLM) to guide the image editing process more precisely. Extensive results demonstrate that our approach, InsightEdit, achieves state-of-the-art performance, excelling in complex instruction following and maintaining high background consistency with the original image.

cs.CV↗

arXiv2024

A rotational ellipsoid model for solid Earth tide with high precision

Solid Earth tide represents the response of solid Earth to the lunar (solar) gravitational force. The yielding solid Earth due to the force has been thought to be a prolate ellipsoid since the time of Lord Kelvin, yet the ellipsoid's geometry such as major semi-axis's length, minor semi-axis's length, and flattening remains unresolved. Additionally, the tidal displacement of reference point is conventionally resolved through a combination of expanded potential equations and given Earth model. Here we present a geometric model in which both the ellipsoid's geometry and the tidal displacement of reference point can be resolved through a rotating ellipse with respect to the Moon (Sun). We test the geometric model using 23-year gravity data from 22 superconducting gravimeter (SG) stations and compare it with the current model recommended by the IERS (International Earth Rotation System) conventions (2010), the average Root Mean Square (RMS) deviation of the gravity change yielded by the geometric model against observation is 6.47 μGal (equivalent to 2.07 cm), while that yielded by the current model is 30.77 μGal (equivalent to 9.85 cm). The geometric model will greatly contribute to many application fields such as geodesy, geophysics, astronomy, and oceanography.

physics.geo-ph↗

arXiv2024

Investigating the Behavior and Spatiotemporal Variations of Green Line Emission in the Solar Corona

Understanding coronal structure and dynamics can be facilitated by analyzing green-line emission, which enables the investigation of diverse coronal structures such as coronal loops, streamers, coronal holes, and various eruptions in the solar atmosphere. In this study, we investigated the spatiotemporal behaviors of green-line emissions in both low and high latitudes across nine solar cycles, ranging from cycle 17 to the current cycle 25, using the Modified Homogeneous Data Set (MHDS). We employed methodologies such as cross-correlation, power spectral density (PSD), and wavelet transform techniques for this analysis. We found distinct behaviors in green line energy across various latitudinal distributions in the solar atmosphere. The trends observed at higher latitudes differ from those at lower latitudes. The emission behaviors show a close association with other solar phenomena like solar flares, sunspots, and coronal mass ejections (CMEs) throughout the solar cycles. The observed variations exhibit harmonic periods. The emission activity is significantly higher in the low latitudes, accounting for over 70 percent of the emissions, while the higher latitudes contribute less than 30 percent. The emissions exhibit asymmetric behavior between the northern and southern hemispheres, leading to a 44-year cycle of solar hemispheric dominance shifts. Various factors, such as Alfvén waves, solar magnetic fields, sunspots, differential rotation, and reconnection events, influence the observed differences in behavior between lower and higher latitudes, suggesting the existence of potential underlying phenomena contributing to deviations in properties, intensity, temporal dynamics, and spatiotemporal lifetime.

astro-ph.SR↗

arXiv2024

AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies

Diffusion-based imitation learning improves Behavioral Cloning (BC) on multi-modal decision-making, but comes at the cost of significantly slower inference due to the recursion in the diffusion process. It urges us to design efficient policy generators while keeping the ability to generate diverse actions. To address this challenge, we propose AdaFlow, an imitation learning framework based on flow-based generative modeling. AdaFlow represents the policy with state-conditioned ordinary differential equations (ODEs), which are known as probability flows. We reveal an intriguing connection between the conditional variance of their training loss and the discretization error of the ODEs. With this insight, we propose a variance-adaptive ODE solver that can adjust its step size in the inference stage, making AdaFlow an adaptive decision-maker, offering rapid inference without sacrificing diversity. Interestingly, it automatically reduces to a one-step generator when the action distribution is uni-modal. Our comprehensive empirical evaluation shows that AdaFlow achieves high performance with fast inference speed.

cs.LG↗

arXiv2024

A Multi-Server Information-Sharing Environment for Cross-Party Collaboration on A Private Cloud

Interoperability remains the key problem in multi-discipline collaboration based on building information modeling (BIM). Although various methods have been proposed to solve the technical issues of interoperability, such as data sharing and data consistency; organizational issues, including data ownership and data privacy, remain unresolved to date. These organizational issues prevent different stakeholders from sharing their data due to concerns regarding losing control of the data. This study proposes a multi-server information-sharing approach on a private cloud after analyzing the requirements for cross-party collaboration to address the aforementioned issues and prepare for massive data handling in the near future. This approach adopts a global controller to track the location, ownership and privacy of the data, which are stored in different servers that are controlled by different parties. Furthermore, data consistency conventions, parallel sub-model extraction, and sub-model integration with model verification are investigated in depth to support information sharing in a distributed environment and to maintain data consistency. Thus, with this approach, the ownership and privacy of the data can be controlled by its owner while still enabling certain required data to be shared with other parties. Application of the multi-server approach for information interoperability and cross-party collaboration is illustrated using a real construction project of an airport terminal. Validation shows that the proposed approach is feasible for maintaining the ownership and privacy of the data while supporting cross-party data sharing and collaboration at the same time, thus avoiding possible legal problems regarding data copyrights or other legal issues.

cs.CR↗

arXiv2024

Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media

With the rapid development of social media, the wide dissemination of fake news on social media is increasingly threatening both individuals and society. One of the unique challenges for fake news detection on social media is how to detect fake news on future events. Recently, numerous fake news detection models that utilize textual information and the propagation structure of posts have been proposed. Unfortunately, most of the existing approaches can hardly handle this challenge since they rely heavily on event-specific features for prediction and cannot generalize to unseen events. To address this, we introduce \textbf{F}uture \textbf{AD}aptive \textbf{E}vent-based Fake news Detection (FADE) framework. Specifically, we train a target predictor through an adaptive augmentation strategy and graph contrastive learning to obtain higher-quality features and make more accurate overall predictions. Simultaneously, we independently train an event-only predictor to obtain biased predictions. We further mitigate event bias by subtracting the event-only predictor's output from the target predictor's output to obtain the final prediction. Encouraging results from experiments designed to emulate real-world social media conditions validate the effectiveness of our method in comparison to existing state-of-the-art approaches.

cs.SI↗

arXiv2024

Is the annualized compounded return of Medallion over 35%?

It is a challenge to estimate fund performance by compounded returns. Arguably, it is incorrect to use yearly returns directly for compounding, with reported annualized return of above 60% for Medallion for the 31 years up to 2018. We propose an estimation based on fund sizes and trading profits and obtain a compounded return of 31.8% before fees. Alternatively, we suggest using the manager's wealth as a proxy and arriving at a compounded growth rate of 25.6% for Simons for the 33 years up to 2020. We conclude that the annualized compounded return of Medallion before fees is probably under 35%. Our findings have implications for correctly estimating fund performance.

q-fin.PM↗

arXiv2024

Risk-neutral valuation of options under arithmetic Brownian motions

On April 22, 2020, the CME Group switched to Bachelier pricing for a group of oil futures options. The Bachelier model, or more generally the arithmetic Brownian motion (ABM), is not so widely used in finance, though. This paper provides the first comprehensive survey of options pricing under ABM. Using the risk-neutral valuation, we derive formulas for European options for three underlying types, namely an underlying that does not pay dividends, an underlying that pays a continuous dividend yield, and futures. Further, we derive Black-Scholes-Merton-like partial differential equations, which can in principle be utilized to price American options numerically via finite difference.

q-fin.PR↗

arXiv2024

Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction

Molecular property prediction (MPP) is integral to drug discovery and material science, but often faces the challenge of data scarcity in real-world scenarios. Addressing this, few-shot molecular property prediction (FSMPP) has been developed. Unlike other few-shot tasks, FSMPP typically employs a pre-trained molecular encoder and a context-aware classifier, benefiting from molecular pre-training and molecular context information. Despite these advancements, existing methods struggle with the ineffective fine-tuning of pre-trained encoders. We attribute this issue to the imbalance between the abundance of tunable parameters and the scarcity of labeled molecules, and the lack of contextual perceptiveness in the encoders. To overcome this hurdle, we propose a parameter-efficient in-context tuning method, named Pin-Tuning. Specifically, we propose a lightweight adapter for pre-trained message passing layers (MP-Adapter) and Bayesian weight consolidation for pre-trained atom/bond embedding layers (Emb-BWC), to achieve parameter-efficient tuning while preventing over-fitting and catastrophic forgetting. Additionally, we enhance the MP-Adapters with contextual perceptiveness. This innovation allows for in-context tuning of the pre-trained encoder, thereby improving its adaptability for specific FSMPP tasks. When evaluated on public datasets, our method demonstrates superior tuning with fewer trainable parameters, improving few-shot predictive performance.

cs.LG↗

arXiv2024

Bi-Level Graph Structure Learning for Next POI Recommendation

Next point-of-interest (POI) recommendation aims to predict a user's next destination based on sequential check-in history and a set of POI candidates. Graph neural networks (GNNs) have demonstrated a remarkable capability in this endeavor by exploiting the extensive global collaborative signals present among POIs. However, most of the existing graph-based approaches construct graph structures based on pre-defined heuristics, failing to consider inherent hierarchical structures of POI features such as geographical locations and visiting peaks, or suffering from noisy and incomplete structures in graphs. To address the aforementioned issues, this paper presents a novel Bi-level Graph Structure Learning (BiGSL) for next POI recommendation. BiGSL first learns a hierarchical graph structure to capture the fine-to-coarse connectivity between POIs and prototypes, and then uses a pairwise learning module to dynamically infer relationships between POI pairs and prototype pairs. Based on the learned bi-level graphs, our model then employs a multi-relational graph network that considers both POI- and prototype-level neighbors, resulting in improved POI representations. Our bi-level structure learning scheme is more robust to data noise and incompleteness, and improves the exploration ability for recommendation by alleviating sparsity issues. Experimental results on three real-world datasets demonstrate the superiority of our model over existing state-of-the-art methods, with a significant improvement in recommendation accuracy and exploration performance.

cs.LG↗

arXiv2024

VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark

Recently, knowledge editing on large language models (LLMs) has received considerable attention. Compared to this, editing Large Vision-Language Models (LVLMs) faces extra challenges from diverse data modalities and complicated model components, and data for LVLMs editing are limited. The existing LVLM editing benchmark, which comprises three metrics (Reliability, Locality, and Generality), falls short in the quality of synthesized evaluation images and cannot assess whether models apply edited knowledge in relevant content. Therefore, we employ more reliable data collection methods to construct a new Large $\textbf{V}$ision-$\textbf{L}$anguage Model $\textbf{K}$nowledge $\textbf{E}$diting $\textbf{B}$enchmark, $\textbf{VLKEB}$, and extend the Portability metric for more comprehensive evaluation. Leveraging a multi-modal knowledge graph, our image data are bound with knowledge entities. This can be further used to extract entity-related knowledge, which constitutes the base of editing data. We conduct experiments of different editing methods on five LVLMs, and thoroughly analyze how do they impact the models. The results reveal strengths and deficiencies of these methods and hopefully provide insights for future research. The codes and dataset are available at: https://github.com/VLKEB/VLKEB.

cs.CL↗

arXiv2024

Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery and Algebraic Equilibrium Proof

Adversarial inverse reinforcement learning (AIRL) stands as a cornerstone approach in imitation learning, yet it faces criticisms from prior studies. In this paper, we rethink AIRL and respond to these criticisms. Criticism 1 lies in Inadequate Policy Imitation. We show that substituting the built-in algorithm with soft actor-critic (SAC) during policy updating (requires multi-iterations) significantly enhances the efficiency of policy imitation. Criticism 2 lies in Limited Performance in Transferable Reward Recovery Despite SAC Integration. While we find that SAC indeed exhibits a significant improvement in policy imitation, it introduces drawbacks to transferable reward recovery. We prove that the SAC algorithm itself is not feasible to disentangle the reward function comprehensively during the AIRL training process, and propose a hybrid framework, PPO-AIRL + SAC, for a satisfactory transfer effect. Criticism 3 lies in Unsatisfactory Proof from the Perspective of Potential Equilibrium. We reanalyze it from an algebraic theory perspective.

cs.LG↗

arXiv2024

CoRA: Collaborative Information Perception by Large Language Model's Weights for Recommendation

Involving collaborative information in Large Language Models (LLMs) is a promising technique for adapting LLMs for recommendation. Existing methods achieve this by concatenating collaborative features with text tokens into a unified sequence input and then fine-tuning to align these features with LLM's input space. Although effective, in this work, we identify two limitations when adapting LLMs to recommendation tasks, which hinder the integration of general knowledge and collaborative information, resulting in sub-optimal recommendation performance. (1) Fine-tuning LLM with recommendation data can undermine its inherent world knowledge and fundamental competencies, which are crucial for interpreting and inferring recommendation text. (2) Incorporating collaborative features into textual prompts disrupts the semantics of the original prompts, preventing LLM from generating appropriate outputs. In this paper, we propose a new paradigm, \textbf{Co}llaborative \textbf{Lo}RA (CoRA), with a collaborative query generator. Rather than input space alignment, this method aligns collaborative information with LLM's parameter space, representing them as incremental weights to update LLM's output. This way, LLM perceives collaborative information without altering its general knowledge and text inference capabilities. Specifically, we employ a collaborative filtering model to extract user and item embeddings and inject them into a set number of learnable queries. We then convert collaborative queries into collaborative weights with low-rank properties and merge the collaborative weights into LLM's weights, enabling LLM to perceive the collaborative signals and generate personalized recommendations without fine-tuning or extra collaborative tokens in prompts. Extensive experiments confirm that CoRA effectively integrates collaborative information into LLM, enhancing recommendation performance.

cs.IR↗

arXiv2024

Optical next generation reservoir computing

Artificial neural networks with internal dynamics exhibit remarkable capability in processing information. Reservoir computing (RC) is a canonical example that features rich computing expressivity and compatibility with physical implementations for enhanced efficiency. Recently, a new RC paradigm known as next generation reservoir computing (NGRC) further improves expressivity but compromises its physical openness, posing challenges for realizations in physical systems. Here we demonstrate optical NGRC with computations performed by light scattering through disordered media. In contrast to conventional optical RC implementations, we drive our optical reservoir directly with time-delayed inputs. Much like digital NGRC that relies on polynomial features of delayed inputs, our optical reservoir also implicitly generates these polynomial features for desired functionalities. By leveraging the domain knowledge of the reservoir inputs, we show that the optical NGRC not only predicts the short-term dynamics of the low-dimensional Lorenz63 and large-scale Kuramoto-Sivashinsky chaotic time series, but also replicates their long-term ergodic properties. Optical NGRC shows superiority in shorter training length, increased interpretability and fewer hyperparameters compared to conventional optical RC based on scattering media, while achieving better forecasting performance. Our optical NGRC framework may inspire the realization of NGRC in other physical RC systems, new applications beyond time-series processing, and the development of deep and parallel architectures broadly.

physics.optics↗

arXiv2024

Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining

Multimodal large language models (MLLMs) have made significant strides by integrating visual and textual modalities. A critical factor in training MLLMs is the quality of image-text pairs within multimodal pretraining datasets. However, $\textit {de facto}$ filter-based data quality enhancement paradigms often discard a substantial portion of high-quality image data due to inadequate semantic alignment between images and texts, leading to inefficiencies in data utilization and scalability. In this paper, we propose the Adaptive Image-Text Quality Enhancer (AITQE), a model that dynamically assesses and enhances the quality of image-text pairs. AITQE employs a text rewriting mechanism for low-quality pairs and incorporates a negative sample learning strategy to improve evaluative capabilities by integrating deliberately selected low-quality samples during training. Unlike prior approaches that significantly alter text distributions, our method minimally adjusts text to preserve data volume while enhancing quality. Experimental results demonstrate that AITQE surpasses existing methods on various benchmark, effectively leveraging raw data and scaling efficiently with increasing data volumes. We hope our work will inspire future works. The code and model are available at: https://github.com/hanhuang22/AITQE.

cs.CV↗

arXiv2024

Memory-Efficient Optimization with Factorized Hamiltonian Descent

Modern deep learning heavily depends on adaptive optimizers such as Adam and its variants, which are renowned for their capacity to handle model scaling and streamline hyperparameter tuning. However, these algorithms typically experience high memory overhead caused by the accumulation of optimization states, leading to a critical challenge in training large-scale network models. In this study, we introduce a novel adaptive optimizer, H-Fac, which incorporates a memory-efficient factorization approach to address this challenge. By employing a rank-1 parameterization for both momentum and scaling parameter estimators, H-Fac reduces memory costs to a sublinear level while maintaining competitive performance across a wide range of architectures. We develop our algorithms based on principles derived from Hamiltonian dynamics, providing robust theoretical underpinnings in optimization dynamics and convergence guarantees. These optimization algorithms are designed to be both straightforward and adaptable, facilitating easy implementation in diverse settings.

cs.LG↗