Fast Federated Edge Learning with Overlapped Communication and Computation and Channel-Aware Fair Client Scheduling

We consider federated edge learning (FEEL) over wireless fading channels taking into account the downlink and uplink channel latencies, and the random computation delays at the clients. We speed up the training process by overlapping the communication with computation. With fountain coded transmission of the global model update, clients receive the global model asynchronously, and start performing local computations right away. Then, we propose a dynamic client scheduling policy, called MRTP, for uploading local model updates to the parameter server (PS), which, at any time, schedules the client with the minimum remaining upload time. However, MRTP can lead to biased participation of clients in the update process, resulting in performance degradation in non-iid data scenarios. To overcome this, we propose two alternative schemes with fairness considerations, termed as age-aware MRTP (A-MRTP), and opportunistically fair MRTP (OF-MRTP). In A-MRTP, the remaining clients are scheduled according to the ratio between their remaining transmission time and the update age, while in OF-MRTP, the selection mechanism utilizes the long term average channel rate of the clients to further reduce the latency while ensuring fair participation of the clients. It is shown through numerical simulations that OF-MRTP provides significant reduction in latency without sacrificing test accuracy.

Revealing Distributional Vulnerability of Explicit Discriminators by Implicit Generators

An explicit discriminator trained on observable in-distribution (ID) samples can make high-confidence prediction on out-of-distribution (OOD) samples due to its distributional vulnerability. This is primarily caused by the limited ID samples observable for training discriminators when OOD samples are unavailable. To address this issue, the state-of-the-art methods train the discriminator with OOD samples generated by general assumptions without considering the data and network characteristics. However, different network architectures and training ID datasets may cause diverse vulnerabilities, and the generated OOD samples thus usually misaddress the specific distributional vulnerability of the explicit discriminator. To reveal and patch the distributional vulnerabilities, we propose a novel method of textit{fine-tuning explicit discriminators by implicit generators} (FIG). According to the Shannon entropy, an explicit discriminator can construct its corresponding implicit generator to generate specific OOD samples without extra training costs. A Langevin Dynamic sampler then draws high-quality OOD samples from the generator to reveal the vulnerability. Finally, a regularizer, constructed according to the design principle of the implicit generator, patches the distributional vulnerability by encouraging those generated OOD samples with high entropy. Our experiments on four networks, four ID datasets and seven OOD datasets demonstrate that FIG achieves state-of-the-art OOD detection performance and maintains a competitive classification capability.

LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation

Camera and 3D LiDAR sensors have become indispensable devices in modern autonomous driving vehicles, where the camera provides the fine-grained texture, color information in 2D space and LiDAR captures more precise and farther-away distance measurements of the surrounding environments. The complementary information from these two sensors makes the two-modality fusion be a desired option. However, two major issues of the fusion between camera and LiDAR hinder its performance, ie, how to effectively fuse these two modalities and how to precisely align them (suffering from the weak spatiotemporal synchronization problem). In this paper, we propose a coarse-to-fine LiDAR and camera fusion-based network (termed as LIF-Seg) for LiDAR segmentation. For the first issue, unlike these previous works fusing the point cloud and image information in a one-to-one manner, the proposed method fully utilizes the contextual information of images and introduces a simple but effective early-fusion strategy. Second, due to the weak spatiotemporal synchronization problem, an offset rectification approach is designed to align these two-modality features. The cooperation of these two components leads to the success of the effective camera-LiDAR fusion. Experimental results on the nuScenes dataset show the superiority of the proposed LIF-Seg over existing methods with a large margin. Ablation studies and analyses demonstrate that our proposed LIF-Seg can effectively tackle the weak spatiotemporal synchronization problem.

Measurement of Muon-induced Neutron Production at China Jinping Underground Laboratory

Solar-, geo-, and supernova neutrino experiments are subject to muon-induced radioactive background. China Jinping Underground Laboratory (CJPL), with its unique advantage of 2400 m rock coverage and distance from nuclear power plants, is ideal for MeV-scale neutrino experiments. Using a 1-ton prototype detector of the Jinping Neutrino Experiment (JNE), we detected 343 high-energy cosmic-ray muons and (6.24$ pm $3.66) muon-induced neutrons from an 820.28-day dataset at the first phase of CJPL (CJPL-I). Based on the muon induced neutrons, we measured the corresponding neutron yield in liquid scintillator to be $(3.13 pm 1.84_{rm stat.}pm 0.70_{rm syst.})times 10^{-4}mu ^{-1}rm g^{-1}cm^{2}$ at an average muon energy of 340 GeV. This study provides the first measurement for this kind of neutron background at CJPL. A global fit including this measurement shows a power-law coefficient of (0.75$ pm $0.02) for the dependence of the neutron yield at liquid scintillator on muon energy.

Learning Graphon Autoencoders for Generative Graph Modeling

Graphon is a nonparametric model that generates graphs with arbitrary sizes and can be induced from graphs easily. Based on this model, we propose a novel algorithmic framework called textit{graphon autoencoder} to build an interpretable and scalable graph generative model. This framework treats observed graphs as induced graphons in functional space and derives their latent representations by an encoder that aggregates Chebshev graphon filters. A linear graphon factorization model works as a decoder, leveraging the latent representations to reconstruct the induced graphons (and the corresponding observed graphs). We develop an efficient learning algorithm to learn the encoder and the decoder, minimizing the Wasserstein distance between the model and data distributions. This algorithm takes the KL divergence of the graph distributions conditioned on different graphons as the underlying distance and leads to a reward-augmented maximum likelihood estimation. The graphon autoencoder provides a new paradigm to represent and generate graphs, which has good generalizability and transferability.

PTR: Prompt Tuning with Rules for Text Classification

Fine-tuned pre-trained language models (PLMs) have achieved awesome performance on almost all NLP tasks. By using additional prompts to fine-tune PLMs, we can further stimulate the rich knowledge distributed in PLMs to better serve downstream tasks. Prompt tuning has achieved promising results on some few-class classification tasks such as sentiment classification and natural language inference. However, manually designing lots of language prompts is cumbersome and fallible. For those auto-generated prompts, it is also expensive and time-consuming to verify their effectiveness in non-few-shot scenarios. Hence, it is still challenging for prompt tuning to address many-class classification tasks. To this end, we propose prompt tuning with rules (PTR) for many-class text classification and apply logic rules to construct prompts with several sub-prompts. In this way, PTR is able to encode prior knowledge of each class into prompt tuning. We conduct experiments on relation classification, a typical and complicated many-class classification task, and the results show that PTR can significantly and consistently outperform existing state-of-the-art baselines. This indicates that PTR is a promising approach to take advantage of both human prior knowledge and PLMs for those complicated classification tasks.

Sparse online relative similarity learning

For many data mining and machine learning tasks, the quality of a similarity measure is the key for their performance. To automatically find a good similarity measure from datasets, metric learning and similarity learning are proposed and studied extensively. Metric learning will learn a Mahalanobis distance based on positive semi-definite (PSD) matrix, to measure the distances between objectives, while similarity learning aims to directly learn a similarity function without PSD constraint so that it is more attractive. Most of the existing similarity learning algorithms are online similarity learning method, since online learning is more scalable than offline learning. However, most existing online similarity learning algorithms learn a full matrix with d 2 parameters, where d is the dimension of the instances. This is clearly inefficient for high dimensional tasks due to its high memory and computational complexity. To solve this issue, we introduce several Sparse Online Relative Similarity (SORS) learning algorithms, which learn a sparse model during the learning process, so that the memory and computational cost can be significantly reduced. We theoretically analyze the proposed algorithms, and evaluate them on some real-world high dimensional datasets. Encouraging empirical results demonstrate the advantages of our approach in terms of efficiency and efficacy.

The Diverse Morphology, Stellar Population, and Black Hole Scaling Relations of the Host Galaxies of Nearby Quasars

We present rest-frame $B$ and $I$ imaging of 35 low-redshift ($z < 0.5$) Palomar-Green quasars using the Hubble Space Telescope Wide Field Camera 3. We perform multi-component two-dimensional image decomposition to separate the host galaxy from its bright active nucleus, characterize its morphology, and measure its photometric properties. Special care is devoted to quantifying the structural parameters of the galaxy bulge, determine its $B-I$ color, and estimate its stellar mass. Roughly half of the sample, comprising the less luminous ($L_{5100} lesssim 10^{45},mathrm{erg,s^{-1}}$) but most high Eddington ratio quasars, reside in disk galaxies that are often barred and possess pseudo bulges. The large stellar masses, large effective radii, and faint surface brightnesses suggest that the host galaxies of the most luminous quasars are mostly ellipticals. Major mergers constitute only a minority ($lesssim 20%$) of our sample. Our quasar sample roughly obeys the scaling relations between black hole mass and host galaxy (bulge, core, total) stellar mass. Hosts with black holes more massive than $sim 10^8,M_odot$ behave similarly to classical bulges and early-type galaxies, while those with less massive black holes, particular the narrow-line Seyfert 1s, are consistent with pseudo bulges in late-type galaxies. The host galaxy bulges, irrespective of whether they are classical or pseudo, follow the relatively tight inverse relation between effective radius and mean effective surface brightness of inactive classical bulges and ellipticals. We argue that pseudo bulges experience recent or ongoing nuclear star formation.

A new type-II lepidocrocite-type TiO2/GaSe heterostructure: Electronic and optical properties, bandgap engineering, interaction with ultrafast laser pulses

Recently, van der Waals heterostructure has attracted interest both theoretically and experimentally for their potential applications in photoelectronic devices, photovoltaic devices, plasmonic devices and photocatalysis. Inspired by this, we design a lepidocrocite-type TiO2/GaSe heterostructure. Via first-principles simulations, we show that such a heterostructure is a direct bandgap semiconductor with a strong and broad optical absorption, ranging from visible light to UV region, exhibiting its potential application in photoelectronic and photovoltaic devices. With the planar-averaged electron density difference and Bader charge analysis, the heterostructure shows a strong capacity of enhancing the charge redistribution especially at the interface, prolonging the lifetime of excitons, and hence improving photocatalytic performance. By applying biaxial strain and interlayer coupling, the heterostructure exhibits a direct-indirect bandgap transition and shows a potential for mechanical sensors due to the smooth and linear variation of bandgaps. Furthermore, our result indicates that a lower interlayer distance leads to a stronger charge redistribution. The calculation of irradiating ultrafast on the heterostructure further reveals a semiconductor-metal transition for the heterostructure. Moreover, we find an enhanced induced plasmonic current in the heterostructure under both x-polarized and z-polarized laser, which is beneficial to plasmonic devices designs. Our research provides valuable insight in applying the lepidocrocite-type TiO2/GaSe heterostructure in photoelectronic, photovoltaic, photocatalytic, mechanical sensing and plasmonic realms.

Deep Learning-based Forgery Attack on Document Images

With the ongoing popularization of online services, the digital document images have been used in various applications. Meanwhile, there have emerged some deep learning-based text editing algorithms which alter the textual information of an image . In this work, we present a document forgery algorithm to edit practical document images. To achieve this goal, the limitations of existing text editing algorithms towards complicated characters and complex background are addressed by a set of network design strategies. First, the unnecessary confusion in the supervision data is avoided by disentangling the textual and background information in the source images. Second, to capture the structure of some complicated components, the text skeleton is provided as auxiliary information and the continuity in texture is considered explicitly in the loss function. Third, the forgery traces induced by the text editing operation are mitigated by some post-processing operations which consider the distortions from the print-and-scan channel. Quantitative comparisons of the proposed method and the exiting approach have shown the advantages of our design by reducing the about 2/3 reconstruction error measured in MSE, improving reconstruction quality measured in PSNR and in SSIM by 4 dB and 0.21, respectively. Qualitative experiments have confirmed that the reconstruction results of the proposed method are visually better than the existing approach. More importantly, we have demonstrated the performance of the proposed document forgery algorithm under a practical scenario where an attacker is able to alter the textual information in an identity document using only one sample in the target domain. The forged-and-recaptured samples created by the proposed text editing attack and recapturing operation have successfully fooled some existing document authentication systems.