arXiv subjects

Bowen Zhao

Publications and source records attributed to Bowen Zhao.

At least 55 records · Page 3Linked to original sources

arXiv2023

Delving into Identify-Emphasize Paradigm for Combating Unknown Bias

Dataset biases are notoriously detrimental to model robustness and generalization. The identify-emphasize paradigm appears to be effective in dealing with unknown biases. However, we discover that it is still plagued by two challenges: A, the quality of the identified bias-conflicting samples is far from satisfactory; B, the emphasizing strategies only produce suboptimal performance. In this paper, for challenge A, we propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy, along with two practical strategies -- peer-picking and epoch-ensemble. For challenge B, we point out that the gradient contribution statistics can be a reliable indicator to inspect whether the optimization is dominated by bias-aligned samples. Then, we propose gradient alignment (GA), which employs gradient statistics to balance the contributions of the mined bias-aligned and bias-conflicting samples dynamically throughout the learning process, forcing models to leverage intrinsic features to make fair decisions. Furthermore, we incorporate self-supervised (SS) pretext tasks into training, which enable models to exploit richer features rather than the simple shortcuts, resulting in more robust models. Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases and achieve state-of-the-art performance.

cs.LG↗

arXiv2023

DELTA: degradation-free fully test-time adaptation

Fully test-time adaptation aims at adapting a pre-trained model to the test stream during real-time inference, which is urgently required when the test distribution differs from the training distribution. Several efforts have been devoted to improving adaptation performance. However, we find that two unfavorable defects are concealed in the prevalent adaptation methodologies like test-time batch normalization (BN) and self-learning. First, we reveal that the normalization statistics in test-time BN are completely affected by the currently received test samples, resulting in inaccurate estimates. Second, we show that during test-time adaptation, the parameter update is biased towards some dominant classes. In addition to the extensively studied test stream with independent and class-balanced samples, we further observe that the defects can be exacerbated in more complicated test environments, such as (time) dependent or class-imbalanced data. We observe that previous approaches work well in certain scenarios while show performance degradation in others due to their faults. In this paper, we provide a plug-in solution called DELTA for Degradation-freE fuLly Test-time Adaptation, which consists of two components: (i) Test-time Batch Renormalization (TBR), introduced to improve the estimated normalization statistics. (ii) Dynamic Online re-weighTing (DOT), designed to address the class bias within optimization. We investigate various test-time adaptation methods on three commonly used datasets with four scenarios, and a newly introduced real-world dataset. DELTA can help them deal with all scenarios simultaneously, leading to SOTA performance.

cs.LG↗

arXiv2022

Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment

Models notoriously suffer from dataset biases which are detrimental to robustness and generalization. The identify-emphasize paradigm shows a promising effect in dealing with unknown biases. However, we find that it is still plagued by two challenges: A, the quality of the identified bias-conflicting samples is far from satisfactory; B, the emphasizing strategies just yield suboptimal performance. In this work, for challenge A, we propose an effective bias-conflicting scoring method to boost the identification accuracy with two practical strategies -- peer-picking and epoch-ensemble. For challenge B, we point out that the gradient contribution statistics can be a reliable indicator to inspect whether the optimization is dominated by bias-aligned samples. Then, we propose gradient alignment, which employs gradient statistics to balance the contributions of the mined bias-aligned and bias-conflicting samples dynamically throughout the learning process, forcing models to leverage intrinsic features to make fair decisions. Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can alleviate the impact of unknown biases and achieve state-of-the-art performance.

cs.LG↗

arXiv2022

EDUKG: a Heterogeneous Sustainable K-12 Educational Knowledge Graph

Web and artificial intelligence technologies, especially semantic web and knowledge graph (KG), have recently raised significant attention in educational scenarios. Nevertheless, subject-specific KGs for K-12 education still lack sufficiency and sustainability from knowledge and data perspectives. To tackle these issues, we propose EDUKG, a heterogeneous sustainable K-12 Educational Knowledge Graph. We first design an interdisciplinary and fine-grained ontology for uniformly modeling knowledge and resource in K-12 education, where we define 635 classes, 445 object properties, and 1314 datatype properties in total. Guided by this ontology, we propose a flexible methodology for interactively extracting factual knowledge from textbooks. Furthermore, we establish a general mechanism based on our proposed generalized entity linking system for EDUKG's sustainable maintenance, which can dynamically index numerous heterogeneous resources and data with knowledge topics in EDUKG. We further evaluate EDUKG to illustrate its sufficiency, richness, and variability. We publish EDUKG with more than 252 million entities and 3.86 billion triplets. Our code and data repository is now available at https://github.com/THU-KEG/EDUKG.

cs.CL↗

arXiv2022

Towards a category-extended object detector with limited data

Object detectors are typically learned on fully-annotated training data with fixed predefined categories. However, categories are often required to be increased progressively. Usually, only the original training set annotated with old classes and some new training data labeled with new classes are available in such scenarios. Based on the limited datasets, a unified detector that can handle all categories is strongly needed. We propose a practical scheme to achieve it in this work. A conflict-free loss is designed to avoid label ambiguity, leading to an acceptable detector in one training round. To further improve performance, we propose a retraining phase in which Monte Carlo Dropout is employed to calculate the localization confidence to mine more accurate bounding boxes, and an overlap-weighted method is proposed for making better use of pseudo annotations during retraining. Extensive experiments demonstrate the effectiveness of our method.

cs.CV↗

arXiv2022

Rethinking Attention Mechanism in Time Series Classification

Attention-based models have been widely used in many areas, such as computer vision and natural language processing. However, relevant applications in time series classification (TSC) have not been explored deeply yet, causing a significant number of TSC algorithms still suffer from general problems of attention mechanism, like quadratic complexity. In this paper, we promote the efficiency and performance of the attention mechanism by proposing our flexible multi-head linear attention (FMLA), which enhances locality awareness by layer-wise interactions with deformable convolutional blocks and online knowledge distillation. What's more, we propose a simple but effective mask mechanism that helps reduce the noise influence in time series and decrease the redundancy of the proposed FMLA by masking some positions of each given series proportionally. To stabilize this mechanism, samples are forwarded through the model with random mask layers several times and their outputs are aggregated to teach the same model with regular mask layers. We conduct extensive experiments on 85 UCR2018 datasets to compare our algorithm with 11 well-known ones and the results show that our algorithm has comparable performance in terms of top-1 accuracy. We also compare our model with three Transformer-based models with respect to the floating-point operations per second and number of parameters and find that our algorithm achieves significantly better efficiency with lower complexity.

cs.LG↗

arXiv2022

Evolution as a Service: A Privacy-Preserving Genetic Algorithm for Combinatorial Optimization

Evolutionary algorithms (EAs), such as the genetic algorithm (GA), offer an elegant way to handle combinatorial optimization problems (COPs). However, limited by expertise and resources, most users do not have enough capability to implement EAs to solve COPs. An intuitive and promising solution is to outsource evolutionary operations to a cloud server, whilst it suffers from privacy concerns. To this end, this paper proposes a novel computing paradigm, evolution as a service (EaaS), where a cloud server renders evolutionary computation services for users without sacrificing users' privacy. Inspired by the idea of EaaS, this paper designs PEGA, a novel privacy-preserving GA for COPs. Specifically, PEGA enables users outsourcing COPs to the cloud server holding a competitive GA and approximating the optimal solution in a privacy-preserving manner. PEGA features the following characteristics. First, any user without expertise and enough resources can solve her COPs. Second, PEGA does not leak contents of optimization problems, i.e., users' privacy. Third, PEGA has the same capability as the conventional GA to approximate the optimal solution. We implements PEGA falling in a twin-server architecture and evaluates it in the traveling salesman problem (TSP, a widely known COP). Particularly, we utilize encryption cryptography to protect users' privacy and carefully design a suit of secure computing protocols to support evolutionary operators of GA on encrypted data. Privacy analysis demonstrates that PEGA does not disclose the contents of the COP to the cloud server. Experimental evaluation results on four TSP datasets show that PEGA is as effective as the conventional GA in approximating the optimal solution.

cs.NE↗

arXiv2022

On Jointly Optimizing Partial Offloading and SFC Mapping: A Cooperative Dual-agent Deep Reinforcement Learning Approach

Multi-access edge computing (MEC) and network function virtualization (NFV) are promising technologies to support emerging IoT applications, especially those computation-intensive. In NFV-enabled MEC environment, service function chain (SFC), i.e., a set of ordered virtual network functions (VNFs), can be mapped on MEC servers. Mobile devices (MDs) can offload computation-intensive applications, which can be represented by SFCs, fully or partially to MEC servers for remote execution. This paper studies the partial offloading and SFC mapping joint optimization (POSMJO) problem in an NFV-enabled MEC system, where an incoming task can be partitioned into two parts, one for local execution and the other for remote execution. The objective is to minimize the average cost in the long term which is a combination of execution delay, MD's energy consumption, and usage charge for edge computing. This problem consists of two closely related decision-making steps, namely task partition and VNF placement, which is highly complex and quite challenging. To address this, we propose a cooperative dual-agent deep reinforcement learning (CDADRL) algorithm, where we design a framework enabling interaction between two agents. Simulation results show that the proposed algorithm outperforms three combinations of deep reinforcement learning algorithms in terms of cumulative and average episodic rewards and it overweighs a number of baseline algorithms with respect to execution delay, energy consumption, and usage charge.

cs.AI↗

arXiv2022

Evolutionary Multi-Objective Reinforcement Learning Based Trajectory Control and Task Offloading in UAV-Assisted Mobile Edge Computing

This paper studies the trajectory control and task offloading (TCTO) problem in an unmanned aerial vehicle (UAV)-assisted mobile edge computing system, where a UAV flies along a planned trajectory to collect computation tasks from smart devices (SDs). We consider a scenario that SDs are not directly connected by the base station (BS) and the UAV has two roles to play: MEC server or wireless relay. The UAV makes task offloading decisions online, in which the collected tasks can be executed locally on the UAV or offloaded to the BS for remote processing. The TCTO problem involves multi-objective optimization as its objectives are to minimize the task delay and the UAV's energy consumption, and maximize the number of tasks collected by the UAV, simultaneously. This problem is challenging because the three objectives conflict with each other. The existing reinforcement learning (RL) algorithms, either single-objective RLs or single-policy multi-objective RLs, cannot well address the problem since they cannot output multiple policies for various preferences (i.e. weights) across objectives in a single run. This paper adapts the evolutionary multi-objective RL (EMORL), a multi-policy multi-objective RL, to the TCTO problem. This algorithm can output multiple optimal policies in just one run, each optimizing a certain preference. The simulation results demonstrate that the proposed algorithm can obtain more excellent nondominated policies by striking a balance between the three objectives regarding policy quality, compared with two evolutionary and two multi-policy RL algorithms.

eess.SP↗

arXiv2021

An Efficient Federated Distillation Learning System for Multi-task Time Series Classification

This paper proposes an efficient federated distillation learning system (EFDLS) for multi-task time series classification (TSC). EFDLS consists of a central server and multiple mobile users, where different users may run different TSC tasks. EFDLS has two novel components, namely a feature-based student-teacher (FBST) framework and a distance-based weights matching (DBWM) scheme. Within each user, the FBST framework transfers knowledge from its teacher's hidden layers to its student's hidden layers via knowledge distillation, with the teacher and student having identical network structure. For each connected user, its student model's hidden layers' weights are uploaded to the EFDLS server periodically. The DBWM scheme is deployed on the server, with the least square distance used to measure the similarity between the weights of two given models. This scheme finds a partner for each connected user such that the user's and its partner's weights are the closest among all the weights uploaded. The server exchanges and sends back the user's and its partner's weights to these two users which then load the received weights to their teachers' hidden layers. Experimental results show that the proposed EFDLS achieves excellent performance on a set of selected UCR2018 datasets regarding top-1 accuracy.

cs.LG↗

arXiv2021

Emergent O(4) symmetry at the phase transition from plaquette-singlet to antiferromagnetic order in quasi-two-dimensional quantum magnets

Recent experiments [J. Guo et al., Phys. Rev. Lett.124,206602 (2020)] on thermodynamic properties of the frustrated layered quantum magnet SrCu$_2$(BO$_3$)$_2$ -- the Shastry-Sutherland material -- have provided strong evidence for a low-temperature phase transition between plaquette-singlet and antiferromagnetic order as a function of pressure. Further motivated by the recently discovered unusual first-order quantum phase transition with an apparent emergent O(4) symmetry of the antiferromagnetic and plaquette-singlet order parameters in a two-dimensional "checkerboard J-Q" quantum spin model [B. Zhao et al., Nat. Phys. 15, 678 (2019)], we here study the same model in the presence of weak inter-layer couplings. Our focus is on the evolution of the emergent symmetry as the system crosses over from two to three dimensions and the phase transition extends from strictly zero temperature in two dimensions up to finite temperature as expected in SrCu$_2$(BO$_3$)$_2$. Using quantum Monte Carlo simulations, we map out the phase boundaries of the plaquette-singlet and antiferromagnetic phases, with particular focus on the triple point where these two order phases meet the paramagnetic phase for given strength of the inter-layer coupling. All transitions are first-order in the neighborhood of the triple points. We show that the emergent O(4) symmetry of the coexistence state breaks down clearly when the interlayer coupling becomes sufficiently large, but for a weak coupling, of the magnitude expected experimentally, the enlarged symmetry can still be observed at the triple point up to significant length scales. Thus, it is likely that the plaquette-singlet to antiferromagnetic transition in SrCu$_2$(BO$_3$)$_2$ exhibits remnants of emergent O(4) symmetry, which should be observable due to additional weakly gapped Goldstone modes.

cond-mat.str-el↗

arXiv2021

Energy Aligning for Biased Models

Training on class-imbalanced data usually results in biased models that tend to predict samples into the majority classes, which is a common and notorious problem. From the perspective of energy-based model, we demonstrate that the free energies of categories are aligned with the label distribution theoretically, thus the energies of different classes are expected to be close to each other when aiming for ``balanced'' performance. However, we discover a severe energy-bias phenomenon in the models trained on class-imbalanced dataset. To eliminate the bias, we propose a simple and effective method named Energy Aligning by merely adding the calculated shift scalars onto the output logits during inference, which does not require to (i) modify the network architectures, (ii) intervene the standard learning paradigm, (iii) perform two-stage training. The proposed algorithm is evaluated on two class imbalance-related tasks under various settings: class incremental learning and long-tailed recognition. Experimental results show that energy aligning can effectively alleviate class imbalance issue and outperform state-of-the-art methods on several benchmarks.

cs.LG↗

arXiv2021

When Crowdsensing Meets Federated Learning: Privacy-Preserving Mobile Crowdsensing System

Mobile crowdsensing (MCS) is an emerging sensing data collection pattern with scalability, low deployment cost, and distributed characteristics. Traditional MCS systems suffer from privacy concerns and fair reward distribution. Moreover, existing privacy-preserving MCS solutions usually focus on the privacy protection of data collection rather than that of data processing. To tackle faced problems of MCS, in this paper, we integrate federated learning (FL) into MCS and propose a privacy-preserving MCS system, called \textsc{CrowdFL}. Specifically, in order to protect privacy, participants locally process sensing data via federated learning and only upload encrypted training models. Particularly, a privacy-preserving federated averaging algorithm is proposed to average encrypted training models. To reduce computation and communication overhead of restraining dropped participants, discard and retransmission strategies are designed. Besides, a privacy-preserving posted pricing incentive mechanism is designed, which tries to break the dilemma of privacy protection and data evaluation. Theoretical analysis and experimental evaluation on a practical MCS application demonstrate the proposed \textsc{CrowdFL} can effectively protect participants privacy and is feasible and efficient.

cs.CR↗

arXiv2020

Multicritical deconfined quantum-criticality and Lifshitz point of a helical valence-bond phase

The $S=1/2$ square-lattice $J$-$Q$ model hosts a deconfined quantum phase transition between antiferromagnetic and dimerized (valence-bond solid) ground states. We here study two deformations of this model -- a term projecting staggered singlets as well as a modulation of the $J$ terms forming alternating "staircases" of strong and weak couplings. The first deformation preserves all lattice symmetries. Using quantum Monte Carlo simulations, we show that it nevertheless introduces a second relevant field, likely by producing topological defects. The second deformation induces helical valence-bond order. Thus, we identify the deconfined quantum critical point as a multicritical Lifshitz point -- the end point of the helical phase and also the end point of a line of first-order transitions. The helical-antiferromagnetic transitions form a line of generic deconfined quantum-critical points. These findings extend the scope of deconfined quantum criticality and resolve a previously inconsistent critical-exponent bound from the conformal-bootstrap method.

cond-mat.str-el↗

arXiv2020

Consistent scaling exponents at the deconfined quantum-critical point

We report a quantum Monte Carlo study of the phase transition between antiferromagnetic and valence-bond solid ground states in the square-lattice $S=1/2$ $J$-$Q$ model. The critical correlation function of the $Q$ terms gives a scaling dimension corresponding to the value $ν= 0.455 \pm 0.002$ of the correlation-length exponent. This value agrees with previous (less precise) results from conventional methods, e.g., finite-size scaling of the near-critical order parameters. We also study the $Q$-derivatives of the Binder cumulants of the order parameters for $L^2$ lattices with $L$ up to $448$. The slope grows as $L^{1/ν}$ with a value of $ν$ consistent with the scaling dimension of the $Q$ term. There are no indications of runaway flow to a first-order phase transition. The mutually consistent estimates of $ν$ provide compelling support for a continuous deconfined quantum-critical point.

cond-mat.str-el↗

arXiv2020

Quantum phases of SrCu2(BO3)2 from high-pressure thermodynamics

We report heat capacity measurements of SrCu$_2$(BO$_3$)$_2$ under high pressure along with simulations of relevant quantum spin models and map out the $(P,T)$ phase diagram of the material. We find a first-order quantum phase transition between the low-pressure quantum dimer paramagnet and a phase with signatures of a plaquette-singlet state below T = $2$ K. At higher pressures, we observe a transition into a previously unknown antiferromagnetic state below $4$ K. Our findings can be explained within the two-dimensional Shastry-Sutherland quantum spin model supplemented by weak inter-layer couplings. The possibility to tune SrCu$_2$(BO$_3$)$_2$ between the plaquette-singlet and antiferromagnetic states opens opportunities for experimental tests of quantum field theories and lattice models involving fractionalized excitations, emergent symmetries, and gauge fluctuations.

cond-mat.str-el↗

arXiv2020

Tunable deconfined quantum criticality and interplay of different valence-bond solid phases

We use quantum Monte Carlo simulations to study a quantum $S=1/2$ spin model with competing multi-spin interactions. We find a quantum phase transition between a columnar valence-bond solid (cVBS) and a Néel antiferromagnet (AFM), as in the scenario of deconfined quantum-critical points, as well as a transition between the AFM and a staggered valence-bond solid (sVBS). By continuously varying a parameter, the sVBS--AFM and AFM--cVBS boundaries merge into a direct sVBS--cVBS transition. Unlike previous models with putative deconfined AFM--cVBS transitions, e.g., the standard $J$-$Q$ model, in our extended $J$-$Q$ model with competing cVBS and sVBS inducing terms the transition can be tuned from continuous to first-order. We find the expected emergent U(1) symmetry of the microscopically $Z_4$ symmetric cVBS order parameter when the transition is continuous. In contrast, when the transition changes to first-order the clock-like $Z_4$ fluctuations are absent and there is no emergent higher symmetry. We argue that the confined spinons in the sVBS phase are fracton-like. We also present results for an SU(3) symmetric model with a similar phase diagram. The new family of models can serve as a useful tool for further investigating open questions related to deconfined quantum criticality and its associated emergent symmetries.

cond-mat.str-el↗

arXiv2019

Maintaining Discrimination and Fairness in Class Incremental Learning

Deep neural networks (DNNs) have been applied in class incremental learning, which aims to solve common real-world problems of learning new classes continually. One drawback of standard DNNs is that they are prone to catastrophic forgetting. Knowledge distillation (KD) is a commonly used technique to alleviate this problem. In this paper, we demonstrate it can indeed help the model to output more discriminative results within old classes. However, it cannot alleviate the problem that the model tends to classify objects into new classes, causing the positive effect of KD to be hidden and limited. We observed that an important factor causing catastrophic forgetting is that the weights in the last fully connected (FC) layer are highly biased in class incremental learning. In this paper, we propose a simple and effective solution motivated by the aforementioned observations to address catastrophic forgetting. Firstly, we utilize KD to maintain the discrimination within old classes. Then, to further maintain the fairness between old classes and new classes, we propose Weight Aligning (WA) that corrects the biased weights in the FC layer after normal training process. Unlike previous work, WA does not require any extra parameters or a validation set in advance, as it utilizes the information provided by the biased weights themselves. The proposed method is evaluated on ImageNet-1000, ImageNet-100, and CIFAR-100 under various settings. Experimental results show that the proposed method can effectively alleviate catastrophic forgetting and significantly outperform state-of-the-art methods.

cs.CV↗