arXiv subjects

Jie Wang

Publications and source records attributed to Jie Wang.

At least 469 records · Page 26Linked to original sources

arXiv2022

Rethinking Graph Convolutional Networks in Knowledge Graph Completion

Graph convolutional networks (GCNs) -- which are effective in modeling graph structures -- have been increasingly popular in knowledge graph completion (KGC). GCN-based KGC models first use GCNs to generate expressive entity representations and then use knowledge graph embedding (KGE) models to capture the interactions among entities and relations. However, many GCN-based KGC models fail to outperform state-of-the-art KGE models though introducing additional computational complexity. This phenomenon motivates us to explore the real effect of GCNs in KGC. Therefore, in this paper, we build upon representative GCN-based KGC models and introduce variants to find which factor of GCNs is critical in KGC. Surprisingly, we observe from experiments that the graph structure modeling in GCNs does not have a significant impact on the performance of KGC models, which is in contrast to the common belief. Instead, the transformations for entity representations are responsible for the performance improvements. Based on the observation, we propose a simple yet effective framework named LTE-KGE, which equips existing KGE models with linearly transformed entity embeddings. Experiments demonstrate that LTE-KGE models lead to similar performance improvements with GCN-based KGC methods, while being more computationally efficient. These results suggest that existing GCNs are unnecessary for KGC, and novel GCN-based KGC models should count on more ablation studies to validate their effectiveness. The code of all the experiments is available on GitHub at https://github.com/MIRALab-USTC/GCN4KGC.

cs.AI↗

arXiv2022

Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems

Adversarial Examples (AEs) can deceive Deep Neural Networks (DNNs) and have received a lot of attention recently. However, majority of the research on AEs is in the digital domain and the adversarial patches are static, which is very different from many real-world DNN applications such as Traffic Sign Recognition (TSR) systems in autonomous vehicles. In TSR systems, object detectors use DNNs to process streaming video in real time. From the view of object detectors, the traffic sign`s position and quality of the video are continuously changing, rendering the digital AEs ineffective in the physical world. In this paper, we propose a systematic pipeline to generate robust physical AEs against real-world object detectors. Robustness is achieved in three ways. First, we simulate the in-vehicle cameras by extending the distribution of image transformations with the blur transformation and the resolution transformation. Second, we design the single and multiple bounding boxes filters to improve the efficiency of the perturbation training. Third, we consider four representative attack vectors, namely Hiding Attack, Appearance Attack, Non-Target Attack and Target Attack. We perform a comprehensive set of experiments under a variety of environmental conditions, and considering illuminations in sunny and cloudy weather as well as at night. The experimental results show that the physical AEs generated from our pipeline are effective and robust when attacking the YOLO v5 based TSR system. The attacks have good transferability and can deceive other state-of-the-art object detectors. We launched HA and NTA on a brand-new 2021 model vehicle. Both attacks are successful in fooling the TSR system, which could be a life-threatening case for autonomous vehicles. Finally, we discuss three defense mechanisms based on image preprocessing, AEs detection, and model enhancing.

cs.CV↗

arXiv2022

An Improved Reinforcement Learning Algorithm for Learning to Branch

Most combinatorial optimization problems can be formulated as mixed integer linear programming (MILP), in which branch-and-bound (B\&B) is a general and widely used method. Recently, learning to branch has become a hot research topic in the intersection of machine learning and combinatorial optimization. In this paper, we propose a novel reinforcement learning-based B\&B algorithm. Similar to offline reinforcement learning, we initially train on the demonstration data to accelerate learning massively. With the improvement of the training effect, the agent starts to interact with the environment with its learned policy gradually. It is critical to improve the performance of the algorithm by determining the mixing ratio between demonstration and self-generated data. Thus, we propose a prioritized storage mechanism to control this ratio automatically. In order to improve the robustness of the training process, a superior network is additionally introduced based on Double DQN, which always serves as a Q-network with competitive performance. We evaluate the performance of the proposed algorithm over three public research benchmarks and compare it against strong baselines, including three classical heuristics and one state-of-the-art imitation learning-based branching algorithm. The results show that the proposed algorithm achieves the best performance among compared algorithms and possesses the potential to improve B\&B algorithm performance continuously.

cs.LG↗

arXiv2022

Learning to Reformulate for Linear Programming

It has been verified that the linear programming (LP) is able to formulate many real-life optimization problems, which can obtain the optimum by resorting to corresponding solvers such as OptVerse, Gurobi and CPLEX. In the past decades, a serial of traditional operation research algorithms have been proposed to obtain the optimum of a given LP in a fewer solving time. Recently, there is a trend of using machine learning (ML) techniques to improve the performance of above solvers. However, almost no previous work takes advantage of ML techniques to improve the performance of solver from the front end, i.e., the modeling (or formulation). In this paper, we are the first to propose a reinforcement learning-based reformulation method for LP to improve the performance of solving process. Using an open-source solver COIN-OR LP (CLP) as an environment, we implement the proposed method over two public research LP datasets and one large-scale LP dataset collected from practical production planning scenario. The evaluation results suggest that the proposed method can effectively reduce both the solving iteration number ($25\%\downarrow$) and the solving time ($15\%\downarrow$) over above datasets in average, compared to directly solving the original LP instances.

math.OC↗

arXiv2022

Gradient Estimates For $Δu + a(x)u\log u + b(x)u = 0$ and its Parabolic Counterpart Under Integral Ricci Curvature Bounds

In this paper, we consider a class of important nonlinear elliptic equations $$Δu + a(x)u\log u + b(x)u = 0$$ on a collapsed complete Riemannian manifold and its parabolic counterpart under integral curvature conditions, where $a(x)$ and $b(x)$ are two $C^1$-smooth real functions. Some new local gradient estimates for positive solutions to these equations are derived by Moser's iteration provided that the integral Ricci curvature is small enough. Especially, some classical results are extended by our estimates and a few interesting corollaries are given. Furthermore, some global gradient estimates are also established under certain geometric conditions. Some estimates obtained in this paper play an important role in a recent paper by Y. Ma and B. Wang [17], which extended and improved the main results due to B. Wang [29] to the case of integral Ricci curvature bounds.

math.DG↗

arXiv2022

Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization

Fooling deep neural networks (DNNs) with the black-box optimization has become a popular adversarial attack fashion, as the structural prior knowledge of DNNs is always unknown. Nevertheless, recent black-box adversarial attacks may struggle to balance their attack ability and visual quality of the generated adversarial examples (AEs) in tackling high-resolution images. In this paper, we propose an attention-guided black-box adversarial attack based on the large-scale multiobjective evolutionary optimization, termed as LMOA. By considering the spatial semantic information of images, we firstly take advantage of the attention map to determine the perturbed pixels. Instead of attacking the entire image, reducing the perturbed pixels with the attention mechanism can help to avoid the notorious curse of dimensionality and thereby improves the performance of attacking. Secondly, a large-scale multiobjective evolutionary algorithm is employed to traverse the reduced pixels in the salient region. Benefiting from its characteristics, the generated AEs have the potential to fool target DNNs while being imperceptible by the human vision. Extensive experimental results have verified the effectiveness of the proposed LMOA on the ImageNet dataset. More importantly, it is more competitive to generate high-resolution AEs with better visual quality compared with the existing black-box adversarial attacks.

cs.CV↗

arXiv2022

Phase Diagram of Infinite-layer Nickelate Compounds from First- and Second-principles Calculations

The fundamental properties of infinite-layer rare-earth nickelates (RNiO2) are carefully revisited and compared with those of CaCuO2 and RNiO3 perovskites. Combining first-principles and finite-temperature second-principles calculations, we highlight that bulk NdNiO2 compound are far from equivalent to CaCuO2, together at the structural, electronic, and magnetic levels. Structurally, it is shown to be prone to spin-phonon coupling induced oxygen square rotation motion, which might be responsible for the intriguing upturn of the resistivity. At the electronic and magnetic levels, we point out orbital-selective Mott localization with strong out-of-plane band dispersion, which should result in the isotropic upper critical fields and weakly three-dimensional magnetic interactions with in-plane local moment and out-of-plane itinerant moment. We further demonstrate that as in RNiO3 perovskites, oxygen rotation motion and rare-earth ion controlled electronic and magnetic properties can give rise in RNiO2 compounds to a rich phase diagram and high tunability of various appealing properties. In line with that, we reveal that key ingredients of high-Tc superconductor such as orbital polarization, Fermi surface, and antiferromagnetic interactions can be deliberately controlled in NdNiO2 through epitaxial strain. Exploiting strain-orbital engineering, a crossover from three- to two-dimensional magnetic transition can be established, making then NdNiO2 thin film a true analog of high-Tc cuprates.

cond-mat.mtrl-sci↗

arXiv2021

ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs

Query embedding (QE) -- which aims to embed entities and first-order logical (FOL) queries in low-dimensional spaces -- has shown great power in multi-hop reasoning over knowledge graphs. Recently, embedding entities and queries with geometric shapes becomes a promising direction, as geometric shapes can naturally represent answer sets of queries and logical relationships among them. However, existing geometry-based models have difficulty in modeling queries with negation, which significantly limits their applicability. To address this challenge, we propose a novel query embedding model, namely Cone Embeddings (ConE), which is the first geometry-based QE model that can handle all the FOL operations, including conjunction, disjunction, and negation. Specifically, ConE represents entities and queries as Cartesian products of two-dimensional cones, where the intersection and union of cones naturally model the conjunction and disjunction operations. By further noticing that the closure of complement of cones remains cones, we design geometric complement operators in the embedding space for the negation operations. Experiments demonstrate that ConE significantly outperforms existing state-of-the-art methods on benchmark datasets.

cs.AI↗

arXiv2021

Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization

Deep reinforcement learning algorithms can perform poorly in real-world tasks due to the discrepancy between source and target environments. This discrepancy is commonly viewed as the disturbance in transition dynamics. Many existing algorithms learn robust policies by modeling the disturbance and applying it to source environments during training, which usually requires prior knowledge about the disturbance and control of simulators. However, these algorithms can fail in scenarios where the disturbance from target environments is unknown or is intractable to model in simulators. To tackle this problem, we propose a novel model-free actor-critic algorithm -- namely, state-conservative policy optimization (SCPO) -- to learn robust policies without modeling the disturbance in advance. Specifically, SCPO reduces the disturbance in transition dynamics to that in state space and then approximates it by a simple gradient-based regularizer. The appealing features of SCPO include that it is simple to implement and does not require additional knowledge about the disturbance or specially designed simulators. Experiments in several robot control tasks demonstrate that SCPO learns robust policies against the disturbance in transition dynamics.

cs.LG↗

arXiv2021

EmotionBox: a music-element-driven emotional music generation system using Recurrent Neural Network

With the development of deep neural networks, automatic music composition has made great progress. Although emotional music can evoke listeners' different emotions and it is important for artistic expression, only few researches have focused on generating emotional music. This paper presents EmotionBox -an music-element-driven emotional music generator that is capable of composing music given a specific emotion, where this model does not require a music dataset labeled with emotions. Instead, pitch histogram and note density are extracted as features that represent mode and tempo respectively to control music emotions. The subjective listening tests show that the Emotionbox has a more competitive and balanced performance in arousing a specified emotion than the emotion-label-based method.

cs.SD↗

arXiv2021

Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic

Model-based reinforcement learning algorithms, which aim to learn a model of the environment to make decisions, are more sample efficient than their model-free counterparts. The sample efficiency of model-based approaches relies on whether the model can well approximate the environment. However, learning an accurate model is challenging, especially in complex and noisy environments. To tackle this problem, we propose the conservative model-based actor-critic (CMBAC), a novel approach that achieves high sample efficiency without the strong reliance on accurate learned models. Specifically, CMBAC learns multiple estimates of the Q-value function from a set of inaccurate models and uses the average of the bottom-k estimates -- a conservative estimate -- to optimize the policy. An appealing feature of CMBAC is that the conservative estimates effectively encourage the agent to avoid unreliable "promising actions" -- whose values are high in only a small fraction of the models. Experiments demonstrate that CMBAC significantly outperforms state-of-the-art approaches in terms of sample efficiency on several challenging tasks, and the proposed method is more robust than previous methods in noisy environments.

cs.LG↗

arXiv2021

Radio Frequency Interference Mitigation and Statistics in the Spectral Observations of FAST

In radio astronomy, radio frequency interference (RFI) becomes more and more serious for radio observational facilities. The RFI always influences the search and study of the interesting astronomical objects. Mitigating the RFI becomes an essential procedure in any survey data processing. Five-hundred-meter Aperture Spherical radio Telescope (FAST) is an extremely sensitive radio telescope. It is necessary to find out an effective and precise RFI mitigation method for FAST data processing. In this work, we introduce a method to mitigate the RFI in FAST spectral observation and make a statistics for the RFI using around 300 hours FAST data. The details are as follows. Firstly, according to the characteristics of FAST spectra, we propose to use the ArPLS algorithm for baseline fitting. Our test results show that it has a good performance. Secondly, we flag the RFI with four strategies, which are to flag extremely strong RFI, flag long-lasting RFI, flag polarized RFI, and flag beam-combined RFI, respectively. The test results show that all the RFI above a preset threshold could be flagged. Thirdly, we make a statistics for the probabilities of polarized XX and YY RFI in FAST observations. The statistical results could tell us which frequencies are relatively quiescent. With such statistical data, we are able to avoid using such frequencies in our spectral observations. Finally, based on the around 300 hours FAST data, we got an RFI table, which is the most complete database currently for FAST.

astro-ph.IM↗

arXiv2021

PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds

Fine-grained geometry, captured by aggregation of point features in local regions, is crucial for object recognition and scene understanding in point clouds. Nevertheless, existing preeminent point cloud backbones usually incorporate max/average pooling for local feature aggregation, which largely ignores points' positional distribution, leading to inadequate assembling of fine-grained structures. To mitigate this bottleneck, we present an efficient alternative to max pooling, Position Adaptive Pooling (PAPooling), that explicitly models spatial relations among local points using a novel graph representation, and aggregates features in a position adaptive manner, enabling position-sensitive representation of aggregated features. Specifically, PAPooling consists of two key steps, Graph Construction and Feature Aggregation, respectively in charge of constructing a graph with edges linking the center point with every neighboring point in a local region to map their relative positional information to channel-wise attentive weights, and adaptively aggregating local point features based on the generated weights through Graph Convolution Network (GCN). PAPooling is simple yet effective, and flexible enough to be ready to use for different popular backbones like PointNet++ and DGCNN, as a plug-andplay operator. Extensive experiments on various tasks ranging from 3D shape classification, part segmentation to scene segmentation well demonstrate that PAPooling can significantly improve predictive accuracy, while with minimal extra computational overhead. Code will be released.

cs.CV↗

arXiv2021

Search for Optimal Systolic Arrays: A Comprehensive Automated Exploration Framework and Lessons Learned

Systolic arrays have been widely used for accelerating HPC and deep learning applications. There is a plethora of previous works on the performance tuning of systolic arrays, but usually based on a number of oversimplified assumptions (e.g., only considering divisors for loop tiling, pruning based on off-chip data communication) to reduce the design space. In this paper, we present a comprehensive design space exploration tool named Odyssey for systolic array optimization. Odyssey does not rely on artificial assumptions to limit the design space, and yet it is highly efficient and scalable with a hybrid optimization technique. For example, for a 1024x1024x1024 matrix multiplication, it finds designs that reach 90% of the optimal performance in 5 seconds with a single CPU thread. Moreover, using Odyssey, we unveil and quantify the suboptimality introduced by multiple commonly used oversimplifications in prior studies for systolic array design space exploration. For example, Odyssey results show that limiting to divisors for loop tiling leads to a 39% performance loss, and pruning based on off-chip data movement results in a 45% performance loss. We applied Odyssey to explore the architecture trade-offs for matrix multiplication and convolutional neural network, providing inspiration into possible optimizations for these two applications.

cs.AR↗

arXiv2021

Jointly Learning Agent and Lane Information for Multimodal Trajectory Prediction

Predicting the plausible future trajectories of nearby agents is a core challenge for the safety of Autonomous Vehicles and it mainly depends on two external cues: the dynamic neighbor agents and static scene context. Recent approaches have made great progress in characterizing the two cues separately. However, they ignore the correlation between the two cues and most of them are difficult to achieve map-adaptive prediction. In this paper, we use lane as scene data and propose a staged network that Jointly learning Agent and Lane information for Multimodal Trajectory Prediction (JAL-MTP). JAL-MTP use a Social to Lane (S2L) module to jointly represent the static lane and the dynamic motion of the neighboring agents as instance-level lane, a Recurrent Lane Attention (RLA) mechanism for utilizing the instance-level lanes to predict the map-adaptive future trajectories and two selectors to identify the typical and reasonable trajectories. The experiments conducted on the public Argoverse dataset demonstrate that JAL-MTP significantly outperforms the existing models in both quantitative and qualitative.

cs.LG↗

arXiv2021

Charmless $B_s\to V S$ Decays in PQCD Approach

In this work, we investigate the $B_s\to V S$ decays in the perturbative QCD approach, where $V$ and $S$ denote the vector meson and scalar meson respectively. Based on the two-quark structure, considering two different scenarios for describing the scalar mesons, we calculate the branching fractions and the direct $CP$ asymmetries of all $B_s\to VS$ decays. Most branching fractions are predicted to be at $10^{-7}$ to $10^{-5}$, which could be measured in the LHCb and Belle-II experiments, especially for these color-allowed $B_s\to κ(800)(K_0^*(1430))K^*$ decays. It is found that the branching fractions of $B_s\to K_0^{*0}(1430)\bar{K}^{*0}$ and $B_s\to K_0^{*+}(1430)\bar{K}^{*-}$ are very sensitive to the scenarios, which can be used to determine whether $K_0^{*0}(1430)$ belongs to the ground state or the first excited state, if the data were available. We also note that some decays have large direct $CP$ asymmetries, some of which are also sensitive to the scenarios, such as the $B_s \to a_0^+(1450)K^{*-}$ and the $B_s\to f_0(1500) K^{*0}$ decays. Since the experimental measurements of $B_s\to VS$ decays are on the way, combined with the available data in the future, we expect the theoretical predictions will shed light on the structure of the scalar mesons.

hep-ph↗

arXiv2021

The Formation and Evolution of Massive Galaxies

The discovery of massive galaxies at high redshifts, especially the passive ones, poses a big challenge for the current standard galaxy formation models. Here we use the semi-analytic galaxy formation model developed by Henriques et al. to explore the formation and evolution of massive galaxies (MGs, stellar-mass $M_{*}> 10^{11}$ M$_{\odot}$). Different from previous works, we focus on the ones just formed (e.g. just reach $\simeq 10^{11}$ M$_{\odot}$). We find that most of the MGs are formed around $z=0.6$, with the earliest formation at $z>4$. Interestingly, although most of the MGs in the local Universe are passive, we find that only $13\%$ of the MGs are quenched at the formation time. Most of the quenched MGs at formation already hosts a very massive supermassive black hole (SMBH) which could power the very effective AGN feedback. For the star-forming MGs, the ones with more massive SMBH prefer to quench in shorter timescales; in particular, those with $M_{\textrm{SMBH}} > 10^{7.5}$ M$_{\odot}$ have a quenching timescale of $\sim 0.5$ Gyr and the characteristic $M_{\textrm{SMBH}}$ depends on the chosen stellar mass threshold in the definition of MGs as a result of their co-evolution. We also find that the "in-situ" star formation dominates the stellar mass growth of MGs until they are formed. Over the whole redshift range, we find the quiescent MGs prefer to stay in more massive dark matter halos, and have more massive SMBH and less cold gas masses. Our results provide a new angle on the whole life of the growth of MGs in the Universe.

astro-ph.GA↗

arXiv2021

Exact Landau Level Description of Geometry and Interaction in a Flatband

Flatbands appear in many condensed matter systems, such as in high magnetic fields, correlated materials and moire heterostructures. They are characterized by intrinsic geometric properties such as the Berry curvature and Fubini-Study metric. In general the band geometry is nonuniform in momentum space, making its influence on electron-electron interactions a difficult problem to understand analytically. In this work, we study this problem in a topological flatband of Chern number C=1 with the ideal properties that the Berry curvature is positive definite and fluctuates in sync with Fubini-Study metric. We derive an exact correspondence between such ideal flatbands and Landau levels by showing how the band geometry fluctuation in ideal flatbands gives raise to a new type of interaction in Landau levels which depends on the center-of-mass of two particles. We characterize such interaction by generalizing the usual Haldane pseudopotentials. This mapping gives exact zero-energy ground states for short-ranged repulsive generalized pseudopotentials in flatbands, in analogy to fractional quantum Hall systems. Driving the center-of-mass interactions beyond the repulsive regime leads to a dramatic reconstruction of the ground states towards gapless phases. The generalized pseudopotential could be a useful basis for future numerical studies.

cond-mat.mes-hall↗