arXiv subjects

Meng Liu

Publications and source records attributed to Meng Liu.

At least 145 records · Page 8Linked to original sources

arXiv2022

Automatic detection of low surface brightness galaxies from SDSS images

Low surface brightness (LSB) galaxies are galaxies with central surface brightness fainter than the night sky. Due to the faint nature of LSB galaxies and the comparable sky background, it is difficult to search LSB galaxies automatically and efficiently from large sky survey. In this study, we established the Low Surface Brightness Galaxies Auto Detect model (LSBG-AD), which is a data-driven model for end-to-end detection of LSB galaxies from Sloan Digital Sky Survey (SDSS) images. Object detection techniques based on deep learning are applied to the SDSS field images to identify LSB galaxies and estimate their coordinates at the same time. Applying LSBG-AD to 1120 SDSS images, we detected 1197 LSB galaxy candidates, of which 1081 samples are already known and 116 samples are newly found candidates. The B-band central surface brightness of the candidates searched by the model ranges from 22 mag arcsec $^ {- 2} $ to 24 mag arcsec $^ {- 2} $, quite consistent with the surface brightness distribution of the standard sample. 96.46\% of LSB galaxy candidates have an axis ratio ($b/a$) greater than 0.3, and 92.04\% of them have $fracDev\_r$\textless 0.4, which is also consistent with the standard sample. The results show that the LSBG-AD model learns the features of LSB galaxies of the training samples well, and can be used to search LSB galaxies without using photometric parameters. Next, this method will be used to develop efficient algorithms to detect LSB galaxies from massive images of the next generation observatories.

astro-ph.IM↗

arXiv2022

Neighbor2Seq: Deep Learning on Massive Graphs by Transforming Neighbors to Sequences

Modern graph neural networks (GNNs) use a message passing scheme and have achieved great success in many fields. However, this recursive design inherently leads to excessive computation and memory requirements, making it not applicable to massive real-world graphs. In this work, we propose the Neighbor2Seq to transform the hierarchical neighborhood of each node into a sequence. This novel transformation enables the subsequent mini-batch training for general deep learning operations, such as convolution and attention, that are designed for grid-like data and are shown to be powerful in various domains. Therefore, our Neighbor2Seq naturally endows GNNs with the efficiency and advantages of deep learning operations on grid-like data by precomputing the Neighbor2Seq transformations. We evaluate our method on a massive graph, with more than 111 million nodes and 1.6 billion edges, as well as several medium-scale graphs. Results show that our proposed method is scalable to massive graphs and achieves superior performance across massive and medium-scale graphs. Our code is available at https://github.com/divelab/Neighbor2Seq.

cs.LG↗

arXiv2022

Performance Analysis and Power Allocation of Joint Communication and Sensing Towards Future Communication Networks

To mitigate the radar and communication frequency overlapping caused by massive devices access, we propose a novel joint communication and sensing (JCS) system in this paper, where a micro base station (MiBS) can realize target sensing and cooperative communication simultaneously. Concretely, the MiBS, as the sensing equipment, can also serve as a full-duplex (FD) decode-and-forward (DF) relay to assist the end-to-end communication. To further improve the spectrum utilization, non-orthogonal multiple access (NOMA) is adopted such that the communication between the macro base station (MaBS) and the Internet-of-Things (IoT) devices. To facilitate the performance evaluation, the exact and asymptotic outage probabilities, ergodic rates, sensing probability of the system are characterized. Subsequently, two optimal power allocation (OPA) problems of maximizing the received signal-to-interference-plus-noise ratio of sensing signal and maximizing the sum rate for communication are designed that are solved by means of the Lagrangian method and function monotonicity. The simulation results demonstrate that: 1) the proposed JCS NOMA system can accomplish both communication enhancement and sensing function under the premise of the same power consumption as non-cooperative NOMA; 2) the proposed OPA schemes manifest superiorities over a random power allocation scheme.

cs.IT↗

arXiv2021

Non-Local Graph Neural Networks

Modern graph neural networks (GNNs) learn node embeddings through multilayer local aggregation and achieve great success in applications on assortative graphs. However, tasks on disassortative graphs usually require non-local aggregation. In addition, we find that local aggregation is even harmful for some disassortative graphs. In this work, we propose a simple yet effective non-local aggregation framework with an efficient attention-guided sorting for GNNs. Based on it, we develop various non-local GNNs. We perform thorough experiments to analyze disassortative graph datasets and evaluate our non-local GNNs. Experimental results demonstrate that our non-local GNNs significantly outperform previous state-of-the-art methods on seven benchmark datasets of disassortative graphs, in terms of both model performance and efficiency.

cs.LG↗

arXiv2021

DIG: A Turnkey Library for Diving into Graph Deep Learning Research

Although there exist several libraries for deep learning on graphs, they are aiming at implementing basic operations for graph deep learning. In the research community, implementing and benchmarking various advanced tasks are still painful and time-consuming with existing libraries. To facilitate graph deep learning research, we introduce DIG: Dive into Graphs, a turnkey library that provides a unified testbed for higher level, research-oriented graph deep learning tasks. Currently, we consider graph generation, self-supervised learning on graphs, explainability of graph neural networks, and deep learning on 3D graphs. For each direction, we provide unified implementations of data interfaces, common algorithms, and evaluation metrics. Altogether, DIG is an extensible, open-source, and turnkey library for researchers to develop new methods and effortlessly compare with common baselines using widely used datasets and evaluation metrics. Source code is available at https://github.com/divelab/DIG.

cs.LG↗

arXiv2021

Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphs

Graph neural networks are emerging as promising methods for modeling molecular graphs, in which nodes and edges correspond to atoms and chemical bonds, respectively. Recent studies show that when 3D molecular geometries, such as bond lengths and angles, are available, molecular property prediction tasks can be made more accurate. However, computing of 3D molecular geometries requires quantum calculations that are computationally prohibitive. For example, accurate calculation of 3D geometries of a small molecule requires hours of computing time using density functional theory (DFT). Here, we propose to predict the ground-state 3D geometries from molecular graphs using machine learning methods. To make this feasible, we develop a benchmark, known as Molecule3D, that includes a dataset with precise ground-state geometries of approximately 4 million molecules derived from DFT. We also provide a set of software tools for data processing, splitting, training, and evaluation, etc. Specifically, we propose to assess the error and validity of predicted geometries using four metrics. We implement two baseline methods that either predict the pairwise distance between atoms or atom coordinates in 3D space. Experimental results show that, compared with generating 3D geometries with RDKit, our method can achieve comparable prediction accuracy but with much smaller computational costs. Our Molecule3D is available as a module of the MoleculeX software library (https://github.com/divelab/MoleculeX).

cs.LG↗

arXiv2021

A Novel Patch Convolutional Neural Network for View-based 3D Model Retrieval

Recently, many view-based 3D model retrieval methods have been proposed and have achieved state-of-the-art performance. Most of these methods focus on extracting more discriminative view-level features and effectively aggregating the multi-view images of a 3D model, but the latent relationship among these multi-view images is not fully explored. Thus, we tackle this problem from the perspective of exploiting the relationships between patch features to capture long-range associations among multi-view images. To capture associations among views, in this work, we propose a novel patch convolutional neural network (PCNN) for view-based 3D model retrieval. Specifically, we first employ a CNN to extract patch features of each view image separately. Secondly, a novel neural network module named PatchConv is designed to exploit intrinsic relationships between neighboring patches in the feature space to capture long-range associations among multi-view images. Then, an adaptive weighted view layer is further embedded into PCNN to automatically assign a weight to each view according to the similarity between each view feature and the view-pooling feature. Finally, a discrimination loss function is employed to extract the discriminative 3D model feature, which consists of softmax loss values generated by the fusion lassifier and the specific classifier. Extensive experimental results on two public 3D model retrieval benchmarks, namely, the ModelNet40, and ModelNet10, demonstrate that our proposed PCNN can outperform state-of-the-art approaches, with mAP alues of 93.67%, and 96.23%, respectively.

cs.CV↗

arXiv2021

Multigranular Visual-Semantic Embedding for Cloth-Changing Person Re-identification

Person reidentification (ReID) is a very hot research topic in machine learning and computer vision, and many person ReID approaches have been proposed; however, most of these methods assume that the same person has the same clothes within a short time interval, and thus their visual appearance must be similar. However, in an actual surveillance environment, a given person has a great probability of changing clothes after a long time span, and they also often take different personal belongings with them. When the existing person ReID methods are applied in this type of case, almost all of them fail. To date, only a few works have focused on the cloth-changing person ReID task, but since it is very difficult to extract generalized and robust features for representing people with different clothes, their performances need to be improved. Moreover, visual-semantic information is often ignored. To solve these issues, in this work, a novel multigranular visual-semantic embedding algorithm (MVSE) is proposed for cloth-changing person ReID, where visual semantic information and human attributes are embedded into the network, and the generalized features of human appearance can be well learned to effectively solve the problem of clothing changes. Specifically, to fully represent a person with clothing changes, a multigranular feature representation scheme (MGR) is employed to focus on the unchanged part of the human, and then a cloth desensitization network (CDN) is designed to improve the feature robustness of the approach for the person with different clothing, where different high-level human attributes are fully utilized. Moreover, to further solve the issue of pose changes and occlusion under different camera perspectives, a partially semantically aligned network (PSA) is proposed to obtain the visual-semantic information that is used to align the human attributes.

cs.CV↗

arXiv2021

Frame-wise Cross-modal Matching for Video Moment Retrieval

Video moment retrieval targets at retrieving a moment in a video for a given language query. The challenges of this task include 1) the requirement of localizing the relevant moment in an untrimmed video, and 2) bridging the semantic gap between textual query and video contents. To tackle those problems, early approaches adopt the sliding window or uniform sampling to collect video clips first and then match each clip with the query. Obviously, these strategies are time-consuming and often lead to unsatisfied accuracy in localization due to the unpredictable length of the golden moment. To avoid the limitations, researchers recently attempt to directly predict the relevant moment boundaries without the requirement to generate video clips first. One mainstream approach is to generate a multimodal feature vector for the target query and video frames (e.g., concatenation) and then use a regression approach upon the multimodal feature vector for boundary detection. Although some progress has been achieved by this approach, we argue that those methods have not well captured the cross-modal interactions between the query and video frames. In this paper, we propose an Attentive Cross-modal Relevance Matching (ACRM) model which predicts the temporal boundaries based on an interaction modeling. In addition, an attention module is introduced to assign higher weights to query words with richer semantic cues, which are considered to be more important for finding relevant video contents. Another contribution is that we propose an additional predictor to utilize the internal frames in the model training to improve the localization accuracy. Extensive experiments on two datasets TACoS and Charades-STA demonstrate the superiority of our method over several state-of-the-art methods. Ablation studies have been also conducted to examine the effectiveness of different modules in our ACRM model.

cs.CV↗

arXiv2021

Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery

Properties of molecules are indicative of their functions and thus are useful in many applications. With the advances of deep learning methods, computational approaches for predicting molecular properties are gaining increasing momentum. However, there lacks customized and advanced methods and comprehensive tools for this task currently. Here we develop a suite of comprehensive machine learning methods and tools spanning different computational models, molecular representations, and loss functions for molecular property prediction and drug discovery. Specifically, we represent molecules as both graphs and sequences. Built on these representations, we develop novel deep models for learning from molecular graphs and sequences. In order to learn effectively from highly imbalanced datasets, we develop advanced loss functions that optimize areas under precision-recall curves. Altogether, our work not only serves as a comprehensive tool, but also contributes towards developing novel and advanced graph and sequence learning methodologies. Results on both online and offline antibiotics discovery and molecular property prediction tasks show that our methods achieve consistent improvements over prior methods. In particular, our methods achieve #1 ranking in terms of both ROC-AUC and PRC-AUC on the AI Cures Open Challenge for drug discovery related to COVID-19. Our software is released as part of the MoleculeX library under AdvProp.

q-bio.QM↗

arXiv2021

Lift force acting on an intruder in dense, granular shear flows

We report a new lift force model for intruders in dense, granular shear flows. Our derivation is based on the thermal buoyancy model of Trujillo & Hermann[L. Trujillo and H. J. Herrmann, Physica A 330, 519 (2003).], but takes into account both granular temperature and pressure differences in the derivation of the net buoyancy force acting on the intruder. In a second step the model is extended to take into account also density differences between the intruder and the bed particles. The model predicts very well the rising and sinking of intruders, the lift force acting on intruders as determined by discrete element model (DEM) simulations and the neutral-buoyancy limit of intruders in shear flows. Phenomenologically, we observe a cooling upon the introduction of an intruder into the system. This cooling effect increases with intruder size and explains the sinking of large intruders. On the other hand, the introduction of small to mid-sized intruders, i.e. up to 4 times the bed particle size, leads to a reduction in the granular pressure compared to the hydrostatic pressure, which in turn causes the rising of small to mid-sized intruders.

cond-mat.soft↗

arXiv2021

Fast Quantum Property Prediction via Deeper 2D and 3D Graph Networks

Molecular property prediction is gaining increasing attention due to its diverse applications. One task of particular interests and importance is to predict quantum chemical properties without 3D equilibrium structures. This is practically favorable since obtaining 3D equilibrium structures requires extremely expensive calculations. In this work, we design a deep graph neural network to predict quantum properties by directly learning from 2D molecular graphs. In addition, we propose a 3D graph neural network to learn from low-cost conformer sets, which can be obtained with open-source tools using an affordable budget. We employ our methods to participate in the 2021 KDD Cup on OGB Large-Scale Challenge (OGB-LSC), which aims to predict the HOMO-LUMO energy gap of molecules. Final evaluation results reveal that we are one of the winners with a mean absolute error of 0.1235 on the holdout test set. Our implementation is available as part of the MoleculeX package (https://github.com/divelab/MoleculeX).

cs.LG↗

arXiv2021

Exploring Deep Learning for Joint Audio-Visual Lip Biometrics

Audio-visual (AV) lip biometrics is a promising authentication technique that leverages the benefits of both the audio and visual modalities in speech communication. Previous works have demonstrated the usefulness of AV lip biometrics. However, the lack of a sizeable AV database hinders the exploration of deep-learning-based audio-visual lip biometrics. To address this problem, we compile a moderate-size database using existing public databases. Meanwhile, we establish the DeepLip AV lip biometrics system realized with a convolutional neural network (CNN) based video module, a time-delay neural network (TDNN) based audio module, and a multimodal fusion module. Our experiments show that DeepLip outperforms traditional speaker recognition models in context modeling and achieves over 50% relative improvements compared with our best single modality baseline, with an equal error rate of 0.75% and 1.11% on the test datasets, respectively.

cs.MM↗

arXiv2021

GraphEBM: Molecular Graph Generation with Energy-Based Models

We note that most existing approaches for molecular graph generation fail to guarantee the intrinsic property of permutation invariance, resulting in unexpected bias in generative models. In this work, we propose GraphEBM to generate molecular graphs using energy-based models. In particular, we parameterize the energy function in a permutation invariant manner, thus making GraphEBM permutation invariant. We apply Langevin dynamics to train the energy function by approximately maximizing likelihood and generate samples with low energies. Furthermore, to generate molecules with a desirable property, we propose a simple yet effective strategy, which pushes down energies with flexible degrees according to the properties of corresponding molecules. Finally, we explore the use of GraphEBM for generating molecules with multiple objectives in a compositional manner. Comprehensive experimental results on random, goal-directed, and compositional generation tasks demonstrate the effectiveness of our proposed method.

cs.LG↗

arXiv2021

Strongly Local Hypergraph Diffusions for Clustering and Semi-supervised Learning

Hypergraph-based machine learning methods are now widely recognized as important for modeling and using higher-order and multiway relationships between data objects. Local hypergraph clustering and semi-supervised learning specifically involve finding a well-connected set of nodes near a given set of labeled vertices. Although many methods for local clustering exist for graphs, there are relatively few for localized clustering in hypergraphs. Moreover, those that exist often lack flexibility to model a general class of hypergraph cut functions or cannot scale to large problems. To tackle these issues, this paper proposes a new diffusion-based hypergraph clustering algorithm that solves a quadratic hypergraph cut based objective akin to a hypergraph analog of Andersen-Chung-Lang personalized PageRank clustering for graphs. We prove that, for graphs with fixed maximum hyperedge size, this method is strongly local, meaning that its runtime only depends on the size of the output instead of the size of the hypergraph and is highly scalable. Moreover, our method enables us to compute with a wide variety of cardinality-based hypergraph cut functions. We also prove that the clusters found by solving the new objective function satisfy a Cheeger-like quality guarantee. We demonstrate that on large real-world hypergraphs our new method finds better clusters and runs much faster than existing approaches. Specifically, it runs in few seconds for hypergraphs with a few million hyperedges compared with minutes for flow-based technique. We furthermore show that our framework is general enough that can also be used to solve other p-norm based cut objectives on hypergraphs. Our code is available \url{github.com/MengLiuPurdue/LHQD}.

cs.SI↗

arXiv2021

Pressure-enhanced interlayer exciton in WS2/MoSe2 van der Waals heterostructure

The atomic-level vdW heterostructures have been one of the most interesting quantum material systems, due to their exotic physical properties. The interlayer coupling in these systems plays a critical role to realize novel physical observation and enrich interface functionality. However, there is still lack of investigation on the tuning of interlayer coupling in a quantitative way. A prospective strategy to tune the interlayer coupling is to change the electronic structure and interlayer distance by high pressure, which is a well-established method to tune the physical properties. Here, we construct a high-quality WS2/MoSe2 heterostructure in a DAC and successfully tuned the interlayer coupling through hydrostatic pressure. Typical photoluminescence spectra of the monolayer MoSe2 (ML-MoSe2), monolayer WS2 (ML-WS2) and WS2/MoSe2 heterostructure have been observed and it's intriguing that their photoluminescence peaks shift with respect to applied pressure in a quite different way. The intralayer exciton of ML-MoSe2 and ML-WS2 show blue shift under high pressure with a coefficient of 19.8 meV/GPa and 9.3 meV/GPa, respectively, while their interlayer exciton shows relative weak pressure dependence with a coefficient of 3.4 meV/GPa. Meanwhile, external pressure helps to drive stronger interlayer interaction and results in a higher ratio of interlayer/intralayer exciton intensity, indicating the enhanced interlayer exciton behavior. The first-principles calculation reveals the stronger interlayer interaction which leads to enhanced interlayer exciton behavior in WS2/MoSe2 heterostructure under external pressure and reveals the robust peak of interlayer exciton. This work provides an effective strategy to study the interlayer interaction in vdW heterostructures, which could be of great importance for the material and device design in various similar quantum systems.

cond-mat.str-el↗

arXiv2020

Combinatorial entropy behaviour leads to range selective binding in ligand-receptor interactions

From viruses to nanoparticles, constructs functionalized with multiple ligands display peculiar binding properties that only arise from multivalent effects. Using statistical mechanical modelling, we describe here how multivalency can be exploited to achieve what we dub range selectivity, that is, binding only to targets bearing a number of receptors within a specified range. We use our model to characterise the region in parameter space where one can expect range selective targeting to occur, and provide experimental support for this phenomenon. Overall, range selectivity represents a potential path to increase the targeting selectivity of multivalent constructs.

cond-mat.soft↗

arXiv2020

Strongly local p-norm-cut algorithms for semi-supervised learning and local graph clustering

Graph based semi-supervised learning is the problem of learning a labeling function for the graph nodes given a few example nodes, often called seeds, usually under the assumption that the graph's edges indicate similarity of labels. This is closely related to the local graph clustering or community detection problem of finding a cluster or community of nodes around a given seed. For this problem, we propose a novel generalization of random walk, diffusion, or smooth function methods in the literature to a convex p-norm cut function. The need for our p-norm methods is that, in our study of existing methods, we find those principled methods based on eigenvector, spectral, random walk, or linear system often have difficulty capturing the correct boundary of a target label or target cluster. In contrast, 1-norm or maxflow-mincut based methods capture the boundary, but cannot grow from small seed set; hybrid procedures that use both have many hard to set parameters. In this paper, we propose a generalization of the objective function behind these methods involving p-norms. To solve the p-norm cut problem we give a strongly local algorithm -- one whose runtime depends on the size of the output rather than the size of the graph. Our method can be thought as a nonlinear generalization of the Anderson-Chung-Lang push procedure to approximate a personalized PageRank vector efficiently. Our procedure is general and can solve other types of nonlinear objective functions, such as p-norm variants of Huber losses. We provide a theoretical analysis of finding planted target clusters with our method and show that the p-norm cut functions improve on the standard Cheeger inequalities for random walk and spectral methods. Finally, we demonstrate the speed and accuracy of our new method in synthetic and real world datasets. Our code is available at http://github.com/MengLiuPurdue/SLQ.

cs.SI↗