Searcharxiv⌕ Search

arXiv subjects

Bin Liu

Publications and source records attributed to Bin Liu.

At least 271 records · Page 15Linked to original sources
arXiv2023

Robust Dynamic Operating Envelopes for DER Integration in Unbalanced Distribution Networks

Dynamic operating envelopes (DOEs) have been introduced in recent years as a means to manage the operation of distributed energy resources (DERs) within the network operational constraints. DOEs can be used by network operators to communicate DER dispatchable capacity to aggregators without further consideration of network constraints and are thus viewed as a key enabler for demand-side participation in future electricity markets and for ensuring the integrity of distribution networks. While a number of approaches have been developed to calculate OEs, uncertainties in system data are typically ignored, which can lead to unreliable results and introduce security risks in network operations. This paper presents a deterministic procedure to calculate robust DOEs (RDOEs) explicitly hedged against uncertainty and variability in customers' loads and generations. The approach is based on a geometric construction strictly included within the feasible region of a linear unbalanced three-phase optimal power flow problem that specifies the network operational constraints. The paper analyses and rigorously shows that the proposed approach also delivers proportional fairness in capacity allocations, and demonstrates how the RDOEs can be enlarged by (i) exploiting the knowledge of customer operational statuses, and (ii) by optimising customers' controllable reactive powers. Two case studies based on an illustrative distribution network and an Australian representative low-voltage distribution network illustrate the efficiency and compliance of the proposed approach.

math.OC↗
arXiv2023

Symmetry-group-protected microfluidics for multiplexed stress-free manipulations

Modern micromanipulation techniques typically involve trapping using electromagnetic, acoustic or flow fields that produce stresses on the trapped particles thereby precluding stress-free manipulations. Here, we show that by employing polyhedral symmetries in a multichannel microfluidic design, we can separate the tasks of displacing and trapping a particle into two distinct sets of flow operations, each characterized and protected by their unique groups of symmetries. By combining only the displacing uniform flow modes to entrain and move targeted particles in arbitrary directions, we were able to realize symmetry-protected, stress-free micromanipulation in 3D. Furthermore, we engineered complex, microscale paths by programming and controlling the flow within each channel in real-time, resulting in multiple particles simultaneously following desired paths in the absence of any supervision or feedback. Our work therefore provides a general symmetry-group-based framework for understanding and engineering microfluidics and a novel platform for 3D stress-free manipulations.

physics.flu-dyn↗
arXiv2023

Video Captioning with Aggregated Features Based on Dual Graphs and Gated Fusion

The application of video captioning models aims at translating the content of videos by using accurate natural language. Due to the complex nature inbetween object interaction in the video, the comprehensive understanding of spatio-temporal relations of objects remains a challenging task. Existing methods often fail in generating sufficient feature representations of video content. In this paper, we propose a video captioning model based on dual graphs and gated fusion: we adapt two types of graphs to generate feature representations of video content and utilize gated fusion to further understand these different levels of information. Using a dual-graphs model to generate appearance features and motion features respectively can utilize the content correlation in frames to generate various features from multiple perspectives. Among them, dual-graphs reasoning can enhance the content correlation in frame sequences to generate advanced semantic features; The gated fusion, on the other hand, aggregates the information in multiple feature representations for comprehensive video content understanding. The experiments conducted on worldly used datasets MSVD and MSR-VTT demonstrate state-of-the-art performance of our proposed approach.

cs.CV↗
arXiv2023

MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition

Dynamic facial expression recognition (DFER) is essential to the development of intelligent and empathetic machines. Prior efforts in this field mainly fall into supervised learning paradigm, which is severely restricted by the limited labeled data in existing datasets. Inspired by recent unprecedented success of masked autoencoders (e.g., VideoMAE), this paper proposes MAE-DFER, a novel self-supervised method which leverages large-scale self-supervised pre-training on abundant unlabeled data to largely advance the development of DFER. Since the vanilla Vision Transformer (ViT) employed in VideoMAE requires substantial computation during fine-tuning, MAE-DFER develops an efficient local-global interaction Transformer (LGI-Former) as the encoder. Moreover, in addition to the standalone appearance content reconstruction in VideoMAE, MAE-DFER also introduces explicit temporal facial motion modeling to encourage LGI-Former to excavate both static appearance and dynamic motion information. Extensive experiments on six datasets show that MAE-DFER consistently outperforms state-of-the-art supervised methods by significant margins (e.g., +6.30\% UAR on DFEW and +8.34\% UAR on MAFW), verifying that it can learn powerful dynamic facial representations via large-scale self-supervised pre-training. Besides, it has comparable or even better performance than VideoMAE, while largely reducing the computational cost (about 38\% FLOPs). We believe MAE-DFER has paved a new way for the advancement of DFER and can inspire more relevant research in this field and even other related tasks. Codes and models are publicly available at https://github.com/sunlicai/MAE-DFER.

cs.CV↗
arXiv2023

Debiased Pairwise Learning from Positive-Unlabeled Implicit Feedback

Learning contrastive representations from pairwise comparisons has achieved remarkable success in various fields, such as natural language processing, computer vision, and information retrieval. Collaborative filtering algorithms based on pairwise learning also rooted in this paradigm. A significant concern is the absence of labels for negative instances in implicit feedback data, which often results in the random selected negative instances contains false negatives and inevitably, biased embeddings. To address this issue, we introduce a novel correction method for sampling bias that yields a modified loss for pairwise learning called debiased pairwise loss (DPL). The key idea underlying DPL is to correct the biased probability estimates that result from false negatives, thereby correcting the gradients to approximate those of fully supervised data. The implementation of DPL only requires a small modification of the codes. Experimental studies on five public datasets validate the effectiveness of proposed learning method.

cs.IR↗
arXiv2023

Two-dimensional anisotropic vortex quantum droplets in dipolar Bose-Einstein condensates

Creation of stable intrinsically anisotropic self-bound states with embedded vorticity is a challenging issue. Previously, no such states in Bose-Einstein condensates (BECs) or other physical settings were known. Dipolar BEC suggests a unique possibility to predict stable anisotropic vortex quantum droplets (AVQDs). We demonstrate that they can be created with the vortex' axis oriented \emph{perpendicular} to the polarization of dipoles. The stability area and characteristics of the AVQDs in the parameter space are revealed by means of analytical and numerical methods. Further, the rotation of the polarizing magnetic field is considered, and the largest angular velocities, up to which spinning AVQDs can follow the rotation in clockwise and anti-clockwise directions, are found. Collisions between moving AVQDs are studied too, demonstrating formation of bound states with a vortex-antivortex-vortex structure. A stability domain for such stationary bound states is identified. Unstable dipolar states, that can be readily implemented by means of phase imprinting, quickly transform into robust AVQDs, which suggests a straightforward possibility for the creation of these states in the experiment.

cond-mat.quant-gas↗
arXiv2023

ClickINC: In-network Computing as a Service in Heterogeneous Programmable Data-center Networks

In-Network Computing (INC) has found many applications for performance boosts or cost reduction. However, given heterogeneous devices, diverse applications, and multi-path network typologies, it is cumbersome and error-prone for application developers to effectively utilize the available network resources and gain predictable benefits without impeding normal network functions. Previous work is oriented to network operators more than application developers. We develop ClickINC to streamline the INC programming and deployment using a unified and automated workflow. ClickINC provides INC developers a modular programming abstractions, without concerning to the states of the devices and the network topology. We describe the ClickINC framework, model, language, workflow, and corresponding algorithms. Experiments on both an emulator and a prototype system demonstrate its feasibility and benefits.

cs.NI↗
arXiv2023

Unveiling the Potential of Knowledge-Prompted ChatGPT for Enhancing Drug Trafficking Detection on Social Media

Social media platforms such as Instagram and Twitter have emerged as critical channels for drug marketing and illegal sale. Detecting and labeling online illicit drug trafficking activities becomes important in addressing this issue. However, the effectiveness of conventional supervised learning methods in detecting drug trafficking heavily relies on having access to substantial amounts of labeled data, while data annotation is time-consuming and resource-intensive. Furthermore, these models often face challenges in accurately identifying trafficking activities when drug dealers use deceptive language and euphemisms to avoid detection. To overcome this limitation, we conduct the first systematic study on leveraging large language models (LLMs), such as ChatGPT, to detect illicit drug trafficking activities on social media. We propose an analytical framework to compose \emph{knowledge-informed prompts}, which serve as the interface that humans can interact with and use LLMs to perform the detection task. Additionally, we design a Monte Carlo dropout based prompt optimization method to further to improve performance and interpretability. Our experimental findings demonstrate that the proposed framework outperforms other baseline language models in terms of drug trafficking detection accuracy, showing a remarkable improvement of nearly 12\%. By integrating prior knowledge and the proposed prompts, ChatGPT can effectively identify and label drug trafficking activities on social networks, even in the presence of deceptive language and euphemisms used by drug dealers to evade detection. The implications of our research extend to social networks, emphasizing the importance of incorporating prior knowledge and scenario-based prompts into analytical tools to improve online security and public safety.

cs.CL↗
arXiv2023

Open-loop and closed-loop solvabilities for discrete-time mean-field stochastic linear quadratic optimal control problems

This paper discusses the discrete-time mean-field stochastic linear quadratic optimal control problems, whose weighting matrices in the cost functional are not assumed to be definite. The open-loop solvability is characterized by the existence of the solution to a mean-field forward-backward stochastic difference equations with a convexity condition and a stationary condition. The closed-loop solvability is presented by virtue of the existences of the regular solution to the generalized Riccati equations and the solution to the linear recursive equation, which is also shown by the uniform convexity of the cost functional. Moreover, based on a family of uniformly convex cost functionals, the finiteness of the problem is characterized. Also, it turns out that a minimizing sequence, whose convergence is equivalent to the open-loop solvability of the problem. Finally, some examples are given to illustrate the theory developed.

math.OC↗
arXiv2023

Experimental observation of non-Hermitian higher-order skin interface states in topological electric circuits

The study of topological states has developed rapidly in electric circuits, which permits flexible fabrications of non-Hermitian systems by introducing non-Hermitian terms. Here, nonreciprocal coupling terms are realized by utilizing a voltage follower module in non-Hermitian topological electric circuits. We report the experimental realization of one- and two- dimensional non-Hermitian skin interface states in electric circuits, where interface states induced by non-Hermitian skin effects are localized at the interface of different domains carrying different winding numbers. Our electric circuit system provides a readily accessible platform to explore non-Hermitian-induced topological phases, and paves a new road for device applications.

cond-mat.mes-hall↗
arXiv2023

EVOPOSE: A Recursive Transformer For 3D Human Pose Estimation With Kinematic Structure Priors

Transformer is popular in recent 3D human pose estimation, which utilizes long-term modeling to lift 2D keypoints into the 3D space. However, current transformer-based methods do not fully exploit the prior knowledge of the human skeleton provided by the kinematic structure. In this paper, we propose a novel transformer-based model EvoPose to introduce the human body prior knowledge for 3D human pose estimation effectively. Specifically, a Structural Priors Representation (SPR) module represents human priors as structural features carrying rich body patterns, e.g. joint relationships. The structural features are interacted with 2D pose sequences and help the model to achieve more informative spatiotemporal features. Moreover, a Recursive Refinement (RR) module is applied to refine the 3D pose outputs by utilizing estimated results and further injects human priors simultaneously. Extensive experiments demonstrate the effectiveness of EvoPose which achieves a new state of the art on two most popular benchmarks, Human3.6M and MPI-INF-3DHP.

cs.CV↗
arXiv2023

A Boosted Model Ensembling Approach to Ball Action Spotting in Videos: The Runner-Up Solution to CVPR'23 SoccerNet Challenge

This technical report presents our solution to Ball Action Spotting in videos. Our method reached second place in the CVPR'23 SoccerNet Challenge. Details of this challenge can be found at https://www.soccer-net.org/tasks/ball-action-spotting. Our approach is developed based on a baseline model termed E2E-Spot, which was provided by the organizer of this competition. We first generated several variants of the E2E-Spot model, resulting in a candidate model set. We then proposed a strategy for selecting appropriate model members from this set and assigning an appropriate weight to each model. The aim of this strategy is to boost the performance of the resulting model ensemble. Therefore, we call our approach Boosted Model Ensembling (BME). Our code is available at https://github.com/ZJLAB-AMMI/E2E-Spot-MBS.

cs.CV↗
arXiv2023

EmotionNAS: Two-stream Neural Architecture Search for Speech Emotion Recognition

Speech emotion recognition (SER) is an important research topic in human-computer interaction. Existing works mainly rely on human expertise to design models. Despite their success, different datasets often require distinct structures and hyperparameters. Searching for an optimal model for each dataset is time-consuming and labor-intensive. To address this problem, we propose a two-stream neural architecture search (NAS) based framework, called \enquote{EmotionNAS}. Specifically, we take two-stream features (i.e., handcrafted and deep features) as the inputs, followed by NAS to search for the optimal structure for each stream. Furthermore, we incorporate complementary information in different streams through an efficient information supplement module. Experimental results demonstrate that our method outperforms existing manually-designed and NAS-based models, setting the new state-of-the-art record.

eess.AS↗
arXiv2023

Reducing Popularity Bias in Recommender Systems through AUC-Optimal Negative Sampling

Popularity bias is a persistent issue associated with recommendation systems, posing challenges to both fairness and efficiency. Existing literature widely acknowledges that reducing popularity bias often requires sacrificing recommendation accuracy. In this paper, we challenge this commonly held belief. Our analysis under general bias-variance decomposition framework shows that reducing bias can actually lead to improved model performance under certain conditions. To achieve this win-win situation, we propose to intervene in model training through negative sampling thereby modifying model predictions. Specifically, we provide an optimal negative sampling rule that maximizes partial AUC to preserve the accuracy of any given model, while correcting sample information and prior information to reduce popularity bias in a flexible and principled way. Our experimental results on real-world datasets demonstrate the superiority of our approach in improving recommendation performance and reducing popularity bias.

cs.IR↗
arXiv2023

PFGE: Parsimonious Fast Geometric Ensembling of DNNs

Ensemble methods are commonly used to enhance the generalization performance of machine learning models. However, they present a challenge in deep learning systems due to the high computational overhead required to train an ensemble of deep neural networks (DNNs). Recent advancements such as fast geometric ensembling (FGE) and snapshot ensembles have addressed this issue by training model ensembles in the same time as a single model. Nonetheless, these techniques still require additional memory for test-time inference compared to single-model-based methods. In this paper, we propose a new method called parsimonious FGE (PFGE), which employs a lightweight ensemble of higher-performing DNNs generated through successive stochastic weight averaging procedures. Our experimental results on CIFAR-{10,100} and ImageNet datasets across various modern DNN architectures demonstrate that PFGE achieves 5x memory efficiency compared to previous methods, without compromising on generalization performance. For those interested, our code is available at https://github.com/ZJLAB-AMMI/PFGE.

cs.LG↗
arXiv2023

Adversarial Ensemble Training by Jointly Learning Label Dependencies and Member Models

Training an ensemble of diverse sub-models has been empirically demonstrated as an effective strategy for improving the adversarial robustness of deep neural networks. However, current ensemble training methods for image recognition typically encode image labels using one-hot vectors, which overlook dependency relationships between the labels. In this paper, we propose a novel adversarial en-semble training approach that jointly learns the label dependencies and member models. Our approach adaptively exploits the learned label dependencies to pro-mote diversity among the member models. We evaluate our approach on widely used datasets including MNIST, FashionMNIST, and CIFAR-10, and show that it achieves superior robustness against black-box attacks compared to state-of-the-art methods. Our code is available at https://github.com/ZJLAB-AMMI/LSD.

cs.LG↗
arXiv2023

On Context Distribution Shift in Task Representation Learning for Offline Meta RL

Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks. Context-based Reinforcement Learning (RL) adopts a context encoder to expediently adapt the agent to new tasks by inferring the task representation, and then adjusting the policy based on this inferred representation. In this work, we focus on context-based OMRL, specifically on the challenge of learning task representation for OMRL. We conduct experiments that demonstrate that the context encoder trained on offline datasets might encounter distribution shift between the contexts used for training and testing. To overcome this problem, we present a hard-sampling-based strategy to train a robust task context encoder. Our experimental findings on diverse continuous control tasks reveal that utilizing our approach yields more robust task representations and better testing performance in terms of accumulated returns compared to baseline methods. Our code is available at https://github.com/ZJLAB-AMMI/HS-OMRL.

cs.LG↗
arXiv2023

Efficient Multimodal Transformer with Dual-Level Feature Restoration for Robust Multimodal Sentiment Analysis

With the proliferation of user-generated online videos, Multimodal Sentiment Analysis (MSA) has attracted increasing attention recently. Despite significant progress, there are still two major challenges on the way towards robust MSA: 1) inefficiency when modeling cross-modal interactions in unaligned multimodal data; and 2) vulnerability to random modality feature missing which typically occurs in realistic settings. In this paper, we propose a generic and unified framework to address them, named Efficient Multimodal Transformer with Dual-Level Feature Restoration (EMT-DLFR). Concretely, EMT employs utterance-level representations from each modality as the global multimodal context to interact with local unimodal features and mutually promote each other. It not only avoids the quadratic scaling cost of previous local-local cross-modal interaction methods but also leads to better performance. To improve model robustness in the incomplete modality setting, on the one hand, DLFR performs low-level feature reconstruction to implicitly encourage the model to learn semantic information from incomplete data. On the other hand, it innovatively regards complete and incomplete data as two different views of one sample and utilizes siamese representation learning to explicitly attract their high-level representations. Comprehensive experiments on three popular datasets demonstrate that our method achieves superior performance in both complete and incomplete modality settings.

cs.LG↗