Showing papers by "Shanghai Jiao Tong University published in 2018"

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

Abstract: Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. $10^4$ GPU hours) makes it difficult to \emph{directly} search the architectures on large-scale tasks (e.g. ImageNet). Differentiable NAS can reduce the cost of GPU hours via a continuous representation of network architecture but suffers from the high GPU memory consumption issue (grow linearly w.r.t. candidate set size). As a result, they need to utilize~\emph{proxy} tasks, such as training on a smaller dataset, or learning with only a few blocks, or training just for a few epochs. These architectures optimized on proxy tasks are not guaranteed to be optimal on the target task. In this paper, we present \emph{ProxylessNAS} that can \emph{directly} learn the architectures for large-scale target tasks and target hardware platforms. We address the high memory consumption issue of differentiable NAS and reduce the computational cost (GPU hours and GPU memory) to the same level of regular training while still allowing a large candidate set. Experiments on CIFAR-10 and ImageNet demonstrate the effectiveness of directness and specialization. On CIFAR-10, our model achieves 2.08\% test error with only 5.7M parameters, better than the previous state-of-the-art architecture AmoebaNet-B, while using 6$\times$ fewer parameters. On ImageNet, our model achieves 3.1\% better top-1 accuracy than MobileNetV2, while being 1.2$\times$ faster with measured GPU latency. We also apply ProxylessNAS to specialize neural architectures for hardware with direct hardware metrics (e.g. latency) and provide insights for efficient CNN architecture design.

Gut bacteria selectively promoted by dietary fibers alleviate type 2 diabetes

Abstract: The gut microbiota benefits humans via short-chain fatty acid (SCFA) production from carbohydrate fermentation, and deficiency in SCFA production is associated with type 2 diabetes mellitus (T2DM). We conducted a randomized clinical study of specifically designed isoenergetic diets, together with fecal shotgun metagenomics, to show that a select group of SCFA-producing strains was promoted by dietary fibers and that most other potential producers were either diminished or unchanged in patients with T2DM. When the fiber-promoted SCFA producers were present in greater diversity and abundance, participants had better improvement in hemoglobin A1c levels, partly via increased glucagon-like peptide-1 production. Promotion of these positive responders diminished producers of metabolically detrimental compounds such as indole and hydrogen sulfide. Targeted restoration of these SCFA producers may present a novel ecological approach for managing T2DM.

Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

Abstract: Gliomas are the most common primary brain malignancies, with different degrees of aggressiveness, variable prognosis and various heterogeneous histologic sub-regions, i.e., peritumoral edematous/invaded tissue, necrotic core, active and non-enhancing core. This intrinsic heterogeneity is also portrayed in their radio-phenotype, as their sub-regions are depicted by varying intensity profiles disseminated across multi-parametric magnetic resonance imaging (mpMRI) scans, reflecting varying biological properties. Their heterogeneous shape, extent, and location are some of the factors that make these tumors difficult to resect, and in some cases inoperable. The amount of resected tumoris a factor also considered in longitudinal scans, when evaluating the apparent tumor for potential diagnosis of progression. Furthermore, there is mounting evidence that accurate segmentation of the various tumor sub-regions can offer the basis for quantitative image analysis towards prediction of patient overall survival. This study assesses thestate-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018. Specifically, we focus on i) evaluating segmentations of the various glioma sub-regions in pre-operative mpMRI scans, ii) assessing potential tumor progression by virtue of longitudinal growth of tumor sub-regions, beyond use of the RECIST/RANO criteria, and iii) predicting the overall survival from pre-operative mpMRI scans of patients that underwent gross tota lresection. Finally, we investigate the challenge of identifying the best ML algorithms for each of these tasks, considering that apart from being diverse on each instance of the challenge, the multi-institutional mpMRI BraTS dataset has also been a continuously evolving/growing dataset.

Solar-driven interfacial evaporation

Abstract: As a ubiquitous solar-thermal energy conversion process, solar-driven evaporation has attracted tremendous research attention owing to its high conversion efficiency of solar energy and transformative industrial potential. In recent years, solar-driven interfacial evaporation by localization of solar-thermal energy conversion to the air/liquid interface has been proposed as a promising alternative to conventional bulk heating-based evaporation, potentially reducing thermal losses and improving energy conversion efficiency. In this Review, we discuss the development of the key components for achieving high-performance evaporation, including solar absorbers, evaporation structures, thermal insulators and thermal concentrators, and discuss how they improve the performance of the solar-driven interfacial evaporation system. We describe the possibilities for applying this efficient solar-driven interfacial evaporation process for energy conversion applications. The exciting opportunities and challenges in both fundamental research and practical implementation of the solar-driven interfacial evaporation process are also discussed. The thermal properties of solar energy can be exploited for many applications, including evaporation. Tao et al. review recent developments in the field of solar-driven interfacial evaporation, which have enabled higher-performance structures by localizing energy conversion to the air/liquid interface.

Learning Discriminative Features with Multiple Granularities for Person Re-Identification

Abstract: The combination of global and partial features has been an essential solution to improve discriminative performances in person re-identification (Re-ID) tasks. Previous part-based methods mainly focus on locating regions with specific pre-defined semantics to learn local representations, which increases learning difficulty but not efficient or robust to scenarios with large variances. In this paper, we propose an end-to-end feature learning strategy integrating discriminative information with various granularities. We carefully design the Multiple Granularity Network (MGN), a multi-branch deep network architecture consisting of one branch for global feature representations and two branches for local feature representations. Instead of learning on semantic regions, we uniformly partition the images into several stripes, and vary the number of parts in different local branches to obtain local feature representations with multiple granularities. Comprehensive experiments implemented on the mainstream evaluation datasets including Market-1501, DukeMTMC-reid and CUHK03 indicate that our method robustly achieves state-of-the-art performances and outperforms any existing approaches by a large margin. For example, on Market-1501 dataset in single query mode, we obtain a top result of Rank-1/mAP=96.6%/94.2% with this method after re-ranking.

TVM: an automated end-to-end optimizing compiler for deep learning

Abstract: There is an increasing need to bring machine learning to a wide diversity of hardware devices. Current frameworks rely on vendor-specific operator libraries and optimize for a narrow range of server-class GPUs. Deploying workloads to new platforms - such as mobile phones, embedded devices, and accelerators (e.g., FPGAs, ASICs) - requires significant manual effort. We propose TVM, a compiler that exposes graph-level and operator-level optimizations to provide performance portability to deep learning workloads across diverse hardware back-ends. TVM solves optimization challenges specific to deep learning, such as high-level operator fusion, mapping to arbitrary hardware primitives, and memory latency hiding. It also automates optimization of low-level programs to hardware characteristics by employing a novel, learning-based cost modeling method for rapid exploration of code optimizations. Experimental results show that TVM delivers performance across hardware back-ends that are competitive with state-of-the-art, hand-tuned libraries for low-power CPU, mobile GPU, and server-class GPUs. We also demonstrate TVM's ability to target new accelerator back-ends, such as the FPGA-based generic deep learning accelerator. The system is open sourced and in production use inside several major companies.

Bile acid-microbiota crosstalk in gastrointestinal inflammation and carcinogenesis.

Abstract: Emerging evidence points to a strong association between the gut microbiota and the risk, development and progression of gastrointestinal cancers such as colorectal cancer (CRC) and hepatocellular carcinoma (HCC). Bile acids, produced in the liver, are metabolized by enzymes derived from intestinal bacteria and are critically important for maintaining a healthy gut microbiota, balanced lipid and carbohydrate metabolism, insulin sensitivity and innate immunity. Given the complexity of bile acid signalling and the direct biochemical interactions between the gut microbiota and the host, a systems biology perspective is required to understand the liver-bile acid-microbiota axis and its role in gastrointestinal carcinogenesis to reverse the microbiota-mediated alterations in bile acid metabolism that occur in disease states. An examination of recent research progress in this area is urgently needed. In this Review, we discuss the mechanistic links between bile acids and gastrointestinal carcinogenesis in CRC and HCC, which involve two major bile acid-sensing receptors, farnesoid X receptor (FXR) and G protein-coupled bile acid receptor 1 (TGR5). We also highlight the strategies and cutting-edge technologies to target gut-microbiota-dependent alterations in bile acid metabolism in the context of cancer therapy.

Genomic variation in 3,010 diverse accessions of Asian cultivated rice

Abstract: Here we analyse genetic variation, population structure and diversity among 3,010 diverse Asian cultivated rice (Oryza sativa L.) genomes from the 3,000 Rice Genomes Project. Our results are consistent with the five major groups previously recognized, but also suggest several unreported subpopulations that correlate with geographic location. We identified 29 million single nucleotide polymorphisms, 2.4 million small indels and over 90,000 structural variations that contribute to within- and between-population variation. Using pan-genome analyses, we identified more than 10,000 novel full-length protein-coding genes and a high number of presence-absence variations. The complex patterns of introgression observed in domestication genes are consistent with multiple independent rice domestication events. The public availability of data from the 3,000 Rice Genomes Project provides a resource for rice genomics research and breeding.

Accelerated Hydrogen Evolution Kinetics on NiFe-Layered Double Hydroxide Electrocatalysts by Tailoring Water Dissociation Active Sites.

Abstract: Owing to its earth abundance, low kinetic overpotential, and superior stability, NiFe-layered double hydroxide (NiFe-LDH) has emerged as a promising electrocatalyst for catalyzing water splitting, especially oxygen evolution reaction (OER), in alkaline solutions. Unfortunately, as a result of extremely sluggish water dissociation kinetics (Volmer step), hydrogen evolution reaction (HER) activity of the NiFe-LDH is rather poor in alkaline environment. Here a novel strategy is demonstrated for substantially accelerating the hydrogen evolution kinetics of the NiFe-LDH by partially substituting Fe atoms with Ru. In a 1 m KOH solution, the as-synthesized Ru-doped NiFe-LDH nanosheets (NiFeRu-LDH) exhibit excellent HER performance with an overpotential of 29 mV at 10 mA cm-2 , which is much lower than those of noble metal Pt/C and reported electrocatalysts. Both experimental and theoretical results reveal that the introduction of Ru atoms into NiFe-LDH can efficiently reduce energy barrier of the Volmer step, eventually accelerating its HER kinetics. Benefitting from its outstanding HER activity and remained excellent OER activity, the NiFeRu-LDH steadily drives an alkaline electrolyzer with a current density of 10 mA cm-2 at a cell voltage of 1.52 V, which is much lower than the values for Pt/C-Ir/C couple and state-of-the-art overall water-splitting electrocatalysts.

Immunoregulatory mechanisms of mesenchymal stem and stromal cells in inflammatory diseases.

Abstract: Mesenchymal stem cells (MSCs; also referred to as mesenchymal stromal cells) have attracted much attention for their ability to regulate inflammatory processes. Their therapeutic potential is currently being investigated in various degenerative and inflammatory disorders such as Crohn’s disease, graft-versus-host disease, diabetic nephropathy and organ fibrosis. The mechanisms by which MSCs exert their therapeutic effects are multifaceted, but in general, these cells are thought to enable damaged tissues to form a balanced inflammatory and regenerative microenvironment in the presence of vigorous inflammation. Studies over the past few years have demonstrated that when exposed to an inflammatory environment, MSCs can orchestrate local and systemic innate and adaptive immune responses through the release of various mediators, including immunosuppressive molecules, growth factors, exosomes, chemokines, complement components and various metabolites. Interestingly, even nonviable MSCs can exert beneficial effects, with apoptotic MSCs showing immunosuppressive functions in vivo. Because the immunomodulatory capabilities of MSCs are not constitutive but rather are licensed by inflammatory cytokines, the net outcomes of MSC activation might vary depending on the levels and the types of inflammation within the residing tissues. Here, we review current understanding of the immunomodulatory mechanisms of MSCs and the issues related to their therapeutic applications.

Ultralow-loading platinum-cobalt fuel cell catalysts derived from imidazolate frameworks.

Abstract: Achieving high catalytic performance with the lowest amount of platinum is critical in fuel cell cost reduction. We describe a method of preparing highly active yet stable electrocatalysts containing ultralow Pt content using Co or Co/Zn zeolitic imidazolate frameworks as precursors. Synergistic catalysis between strained Pt-Co core-shell nanoparticles over a platinum-group-metal-free (PGM-free) catalytic substrate led to excellent fuel cell performance under 1 atmosphere of O 2 or air at both high voltage and high current domains. Two catalysts achieved the oxygen reduction reaction (ORR) mass activities of 1.08 A mg Pt −1 /1.77 A mg Pt −1 and retained 64%/15% of initial values after 30,000 voltage cycles in fuel cell. Computational modeling reveals that the interaction between Pt-Co and PGM-free sites improves ORR activity and durability.

Enterotypes in the landscape of gut microbial community composition

Abstract: Population stratification is a useful approach for a better understanding of complex biological problems in human health and wellbeing. The proposal that such stratification applies to the human gut microbiome, in the form of distinct community composition types termed enterotypes, has been met with both excitement and controversy. In view of accumulated data and re-analyses since the original work, we revisit the concept of enterotypes, discuss different methods of dividing up the landscape of possible microbiome configurations, and put these concepts into functional, ecological and medical contexts. As enterotypes are of use in describing the gut microbial community landscape and may become relevant in clinical practice, we aim to reconcile differing views and encourage a balanced application of the concept.

RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems

Abstract: To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance. This paper considers the knowledge graph as the source of side information. To address the limitations of existing embedding-based and path-based methods for knowledge-graph-aware recommendation, we propose RippleNet, an end-to-end framework that naturally incorporates the knowledge graph into recommender systems. Similar to actual ripples propagating on the water, RippleNet stimulates the propagation of user preferences over the set of knowledge entities by automatically and iteratively extending a user's potential interests along links in the knowledge graph. The multiple "ripples" activated by a user's historically clicked items are thus superposed to form the preference distribution of the user with respect to a candidate item, which could be used for predicting the final clicking probability. Through extensive experiments on real-world datasets, we demonstrate that RippleNet achieves substantial gains in a variety of scenarios, including movie, book and news recommendation, over several state-of-the-art baselines.

Tumor-derived exosomal miR-1247-3p induces cancer-associated fibroblast activation to foster lung metastasis of liver cancer.

Abstract: The communication between tumor-derived elements and stroma in the metastatic niche has a critical role in facilitating cancer metastasis. Yet, the mechanisms tumor cells use to control metastatic niche formation are not fully understood. Here we report that in the lung metastatic niche, high-metastatic hepatocellular carcinoma (HCC) cells exhibit a greater capacity to convert normal fibroblasts to cancer-associated fibroblasts (CAFs) than low-metastatic HCC cells. We show high-metastatic HCC cells secrete exosomal miR-1247-3p that directly targets B4GALT3, leading to activation of β1-integrin–NF-κB signaling in fibroblasts. Activated CAFs further promote cancer progression by secreting pro-inflammatory cytokines, including IL-6 and IL-8. Clinical data show high serum exosomal miR-1247-3p levels correlate with lung metastasis in HCC patients. These results demonstrate intercellular crosstalk between tumor cells and fibroblasts is mediated by tumor-derived exosomes that control lung metastasis of HCC, providing potential targets for prevention and treatment of cancer metastasis.

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

Abstract: We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment. To achieve this, we design a 2D representation called UV position map which records the 3D shape of a complete face in UV space, then train a simple Convolutional Neural Network to regress it from a single 2D image. We also integrate a weight mask into the loss function during training to improve the performance of the network. Our method does not rely on any prior face model, and can reconstruct full facial geometry along with semantic meaning. Meanwhile, our network is very light-weighted and spends only 9.8 ms to process an image, which is extremely faster than previous works. Experiments on multiple challenging datasets show that our method surpasses other state-of-the-art methods on both reconstruction and alignment tasks by a large margin. Code is available at https://github.com/YadiraF/PRNet.

A Survey of Physical Layer Security Techniques for 5G Wireless Networks and Challenges Ahead

Abstract: Physical layer security which safeguards data confidentiality based on the information-theoretic approaches has received significant research interest recently. The key idea behind physical layer security is to utilize the intrinsic randomness of the transmission channel to guarantee the security in physical layer. The evolution toward 5G wireless communications poses new challenges for physical layer security research. This paper provides a latest survey of the physical layer security research on various promising 5G technologies, including physical layer security coding, massive multiple-input multiple-output, millimeter wave communications, heterogeneous networks, non-orthogonal multiple access, full duplex technology, and so on. Technical challenges which remain unresolved at the time of writing are summarized and the future trends of physical layer security in 5G and beyond are discussed.

DKN: Deep Knowledge-Aware Network for News Recommendation

Abstract: Online news recommender systems aim to address the information explosion of news and make personalized recommendation for users. In general, news language is highly condensed, full of knowledge entities and common sense. However, existing methods are unaware of such external knowledge and cannot fully discover latent knowledge-level connections among news. The recommended results for a user are consequently limited to simple patterns and cannot be extended reasonably. To solve the above problem, in this paper, we propose a deep knowledge-aware network (DKN) that incorporates knowledge graph representation into news recommendation. DKN is a content-based deep recommendation framework for click-through rate prediction. The key component of DKN is a multi-channel and word-entity-aligned knowledge-aware convolutional neural network (KCNN) that fuses semantic-level and knowledge-level representations of news. KCNN treats words and entities as multiple channels, and explicitly keeps their alignment relationship during convolution. In addition, to address users» diverse interests, we also design an attention module in DKN to dynamically aggregate a user»s history with respect to current candidate news. Through extensive experiments on a real online news platform, we demonstrate that DKN achieves substantial gains over state-of-the-art deep recommendation models. We also validate the efficacy of the usage of knowledge in DKN.

BSN: Boundary Sensitive Network for Temporal Action Proposal Generation

Abstract: Temporal action proposal generation is an important yet challenging problem, since temporal proposals with rich action content are indispensable for analysing real-world videos with long duration and high proportion irrelevant content. This problem requires methods not only generating proposals with precise temporal boundaries, but also retrieving proposals to cover truth action instances with high recall and high overlap using relatively fewer proposals. To address these difficulties, we introduce an effective proposal generation method, named Boundary-Sensitive Network (BSN), which adopts “local to global” fashion. Locally, BSN first locates temporal boundaries with high probabilities, then directly combines these boundaries as proposals. Globally, with Boundary-Sensitive Proposal feature, BSN retrieves proposals by evaluating the confidence of whether a proposal contains an action within its region. We conduct experiments on two challenging datasets: ActivityNet-1.3 and THUMOS14, where BSN outperforms other state-of-the-art temporal action proposal generation methods with high recall and high temporal precision. Finally, further experiments demonstrate that by combining existing action classifiers, our method significantly improves the state-of-the-art temporal action detection performance.

Author Correction: The nature of spin excitations in the one-third magnetization plateau phase of Ba3CoSb2O9.

Abstract: The original version of this Article omitted the following from the Acknowledgements: ‘J. Ma’s primary affiliation is Shanghai Jiao Tong University.’ This has been corrected in both the PDF and HTML versions of the Article.

Fluorine-Free Synthesis of High-Purity Ti3 C2 Tx (T=OH, O) via Alkali Treatment.

Abstract: MXenes, 2D compounds generated from layered bulk materials, have attracted significant attention in energy-related fields. However, most syntheses involve HF, which is highly corrosive and harmful to lithium-ion battery and supercapacitor performance. Here an alkali-assisted hydrothermal method is used to prepare a MXene Ti3 C2 Tx (T=OH, O). This route is inspired from a Bayer process used in bauxite refining. The process is free of fluorine and yields multilayer Ti3 C2 Tx with ca. 92 wt % in purity (using 27.5 m NaOH, 270 °C). Without the F terminations, the resulting Ti3 C2 Tx film electrode (ca. 52 μm in thickness, ca. 1.63 g cm-3 in density) is 314 F g-1 via gravimetric capacitance at 2 mV s-1 in 1 m H2 SO4 . This surpasses (by ca. 214 %) that of the multilayer Ti3 C2 Tx prepared via HF treatments. This fluorine-free method also provides an alkali-etching strategy for exploring new MXenes for which the interlayer amphoteric/acidic atoms from the pristine MAX phase must be removed.

Bifunctional Stabilization of All-Inorganic α-CsPbI3 Perovskite for 17% Efficiency Photovoltaics.

Abstract: The all-inorganic α-CsPbI3 perovskite with the most suitable band gap faces serious challenges of low phase stability and high moisture sensitivity. We discover that a simple phenyltrimethylammonium bromide (PTABr) post-treatment could achieve a bifunctional stabilization including both gradient Br doping (or alloying) and surface passivation. The PTABr treatment on CsPbI3 only induces less than 5 nm blue shift in UV–vis absorbance but significantly stabilize the perovskite phase with much better stability. Finally, the highly stable PTABr treated CsPbI3 based perovskite solar cells exhibit a reproducible photovoltaic performance with a champion efficiency up to 17.06% and stable output of 16.3%. Therefore, this one-step bifunctional stabilization of perovskite through gradient halide doping and surface organic cation passivation presents a novel and promising strategy to design stable and high performance all-inorganic lead halide.

High-efficiency small-molecule ternary solar cells with a hierarchical morphology enabled by synergizing fullerene and non-fullerene acceptors

Abstract: Using combinatory photoactive blends is a promising approach to achieve high power conversion efficiency in ternary organic photovoltaics However, the fundamental challenge of how to manipulate th

DKN: Deep Knowledge-Aware Network for News Recommendation

Abstract: Online news recommender systems aim to address the information explosion of news and make personalized recommendation for users. In general, news language is highly condensed, full of knowledge entities and common sense. However, existing methods are unaware of such external knowledge and cannot fully discover latent knowledge-level connections among news. The recommended results for a user are consequently limited to simple patterns and cannot be extended reasonably. Moreover, news recommendation also faces the challenges of high time-sensitivity of news and dynamic diversity of users' interests. To solve the above problems, in this paper, we propose a deep knowledge-aware network (DKN) that incorporates knowledge graph representation into news recommendation. DKN is a content-based deep recommendation framework for click-through rate prediction. The key component of DKN is a multi-channel and word-entity-aligned knowledge-aware convolutional neural network (KCNN) that fuses semantic-level and knowledge-level representations of news. KCNN treats words and entities as multiple channels, and explicitly keeps their alignment relationship during convolution. In addition, to address users' diverse interests, we also design an attention module in DKN to dynamically aggregate a user's history with respect to current candidate news. Through extensive experiments on a real online news platform, we demonstrate that DKN achieves substantial gains over state-of-the-art deep recommendation models. We also validate the efficacy of the usage of knowledge in DKN.

Construction and demolition waste management in China through the 3R principle

Abstract: Construction and demolition waste (CDW) accounts for 30% to 40% of the total amount of waste in China. CDW is usually randomly dumped or disposed in landfills and the average recycling rate of CDW in China is only about 5%. Considering there is big challenge in adoption of circular economy in CDW industry in China while related research is still limited, we conduct the CDW management analysis through 3R principle. Existing policies and management situations were investigated and analyzed based on the reduction, reuse and recycle principles. Results reveal that primary barriers of reducing CDW in China include lack of building design standard for reducing CDW, low cost for CDW disposal and inappropriate urban planning. Barriers to reuse CDW include lack of guidance for effective CDW collection and sorting, lack of knowledge and standard for reused CDW, and an under-developed market for reused CDW. As for recycling of CDW, key challenges are identified as ineffective management system, immature recycling technology, under-developed market for recycled CDW products and immature recycling market operation. Proposals to improve the current situation based on 3R principle are also proposed, including designing effective circular economy model, reinforcing the source control of CDW, adopting innovative technologies and market models, and implementing targeted economic incentives.

Computation Rate Maximization in UAV-Enabled Wireless-Powered Mobile-Edge Computing Systems

Abstract: Mobile-edge computing (MEC) and wireless power transfer are two promising techniques to enhance the computation capability and to prolong the operational time of low-power wireless devices that are ubiquitous in Internet of Things. However, the computation performance and the harvested energy are significantly impacted by the severe propagation loss. In order to address this issue, an unmanned aerial vehicle (UAV)-enabled MEC wireless-powered system is studied in this paper. The computation rate maximization problems in a UAV-enabled MEC wireless powered system are investigated under both partial and binary computation offloading modes, subject to the energy-harvesting causal constraint and the UAV’s speed constraint. These problems are non-convex and challenging to solve. A two-stage algorithm and a three-stage alternative algorithm are, respectively, proposed for solving the formulated problems. The closed-form expressions for the optimal central processing unit frequencies, user offloading time, and user transmit power are derived. The optimal selection scheme on whether users choose to locally compute or offload computation tasks is proposed for the binary computation offloading mode. Simulation results show that our proposed resource allocation schemes outperform other benchmark schemes. The results also demonstrate that the proposed schemes converge fast and have low computational complexity.