Molecular similarity search has been widely used in drug discovery to identify structurally similar compounds from large molecular databases rapidly. With the increasing size of chemical libraries, there is growing interest in the efficient accelerat
ion of large-scale similarity search. Existing works mainly focus on CPU and GPU to accelerate the computation of the Tanimoto coefficient in measuring the pairwise similarity between different molecular fingerprints. In this paper, we propose and optimize an FPGA-based accelerator design on exhaustive and approximate search algorithms. On exhaustive search using BitBound & folding, we analyze the similarity cutoff and folding level relationship with search speedup and accuracy, and propose a scalable on-the-fly query engine on FPGAs to reduce the resource utilization and pipeline interval. We achieve a 450 million compounds-per-second processing throughput for a single query engine. On approximate search using hierarchical navigable small world (HNSW), a popular algorithm with high recall and query speed. We propose an FPGA-based graph traversal engine to utilize a high throughput register array based priority queue and fine-grained distance calculation engine to increase the processing capability. Experimental results show that the proposed FPGA-based HNSW implementation has a 103385 query per second (QPS) on the Chembl database with 0.92 recall and achieves a 35x speedup than the existing CPU implementation on average. To the best of our knowledge, our FPGA-based implementation is the first attempt to accelerate molecular similarity search algorithms on FPGA and has the highest performance among existing approaches.
We report a $5sigma$ detection of the pairwise kinematic Sunyaev-Zeldovich (kSZ) effect, combining galaxy clusters in DESI imaging surveys and the Planck temperature maps. The detection is facilitated by both improvements in the data and in the analy
sis method. For the data, we adopt the recently released galaxy group catalog (Y20: cite{yang2020extended}) with $sim 10^6$ robustly-identified groups, and construct various galaxy cluster samples for the kSZ measurement. The Y20 catalogue also provides estimation of halo mass, which further improves the kSZ measurement by $sim 10%$. For the analysis method, we derive an optimal estimator of pairwise kSZ through the maximum likelihood analysis. It also handles potential systematic errors self-consistently. The baseline cluster sample, containing the $1.2times 10^5$ richest galaxy clusters of typical mass ~$ 10^{14} M_{odot}/h$ at typical redshift $0.2$-$0.5$, rules out the null hypothesis at $5sigma$. When fitting with a pairwise kSZ template from simulations, the signal is detected at $4.7sigma$ and the average optical depth is constrained as $bar{tau}_e=(1.66pm 0.35)times 10^{-4}$. We perform various internal checks, with different cluster selection criteria, different sky coverage and redshift range, different CMB maps, different filter sizes, different treatments of potential systematics and the covariance matrix. The kSZ effect is consistently detected with $2.5leq $S/N$leq 5.6$ and acceptable $chi^2_{rm min}$, across a variety of cluster samples. The S/N is limited by both the Planck resolution and the photo-z accuracy, and therefore can be significant improved with DESI spectroscopic redshift information and with other CMB experiments.
A novel photonic approach to the time-frequency analysis of microwave signals is proposed based on the stimulated Brillouin scattering (SBS)-assisted frequency-to-time mapping (FTTM). Two types of time-frequency analysis links, namely parallel SBS li
nk and time-division SBS link are proposed. The parallel SBS link can be utilized to perform real-time time-frequency analysis of microwave signal, which provides a promising solution for real-time time-frequency analysis, especially when it is combined with the photonic integration technique. A simulation is made to verify its feasibility by analyzing signals in multiple formats. The time-division SBS link has a simpler and reconfigurable structure, which can realize an ultra-high-resolution time-frequency analysis for periodic signals using the time segmentation and accumulation technique. An experiment is performed for the time-division SBS link. The multi-dimensional reconfigurability of the system is experimentally studied. An analysis bandwidth of 3.9 GHz, an analysis frequency up to 20 GHz, and a frequency resolution of 15 MHz are demonstrated, respectively.
A photonics-based digital and analog self-interference cancellation approach for in-band full-duplex communication systems and frequency-modulated continuous-wave radar systems is reported. One dual-drive Mach-Zehnder modulator is used to implement t
he analog self-interference cancellation by pre-adjusting the delay and amplitude of the reference signal applied to the dual-drive Mach-Zehnder modulator in the digital domain. The amplitude is determined via the received signal power, while the delay is searched by the cross-correlation and bisection methods. Furthermore, recursive least squared or normalized least mean square algorithms are used to suppress the residual self-interference in the digital domain. Quadrature phase-shift keying modulated signals and linearly frequency-modulated signals are used to experimentally verify the proposed method. The analog cancellation depth is around 20 dB, and the total cancellation depth is more than 36 dB for the 2-Gbaud quadrature phase-shift keying modulated signals. For the linearly frequency-modulated signals, the analog and total cancellation depths are around 19 dB and 34 dB, respectively.
The rapid development of facial manipulation techniques has aroused public concerns in recent years. Following the success of deep learning, existing methods always formulate DeepFake video detection as a binary classification problem and develop fra
me-based and video-based solutions. However, little attention has been paid to capturing the spatial-temporal inconsistency in forged videos. To address this issue, we term this task as a Spatial-Temporal Inconsistency Learning (STIL) process and instantiate it into a novel STIL block, which consists of a Spatial Inconsistency Module (SIM), a Temporal Inconsistency Module (TIM), and an Information Supplement Module (ISM). Specifically, we present a novel temporal modeling paradigm in TIM by exploiting the temporal difference over adjacent frames along with both horizontal and vertical directions. And the ISM simultaneously utilizes the spatial information from SIM and temporal information from TIM to establish a more comprehensive spatial-temporal representation. Moreover, our STIL block is flexible and could be plugged into existing 2D CNNs. Extensive experiments and visualizations are presented to demonstrate the effectiveness of our method against the state-of-the-art competitors.
This is an update of the two articles [H.Y. Cheng, Int. J. Mod. Phys. A {bf 24} (Suppl. 1), 593 (2009); Front. Phys. {bf 10}, 101406 (2015)] in which charmed baryon physics around 2007 and 2015, respectively, were reviewed. In this review we emphasiz
e the experimental progress and the theoretical development since 2015.
A photonic approach for radio-frequency (RF) self-interference cancellation (SIC) incorporated in an in-band full-duplex radio-over-fiber system is proposed. A dual-polarization binary phase-shift keying modulator is used for dual-polarization multip
lexing at the central office (CO). A local oscillator signal and an intermediate-frequency signal carrying the downlink data are single-sideband modulated on the two polarization directions of the modulator, respectively. The optical signal is then transmitted to the remote unit, where the optical signals in the two polarization directions are split into two parts. One part is detected to generate the up-converted downlink RF signal, and the other part is re-modulated by the uplink RF signal and the self-interference, which is then transmitted back to the CO for the signal down-conversion and SIC via the optical domain signal adjustment and balanced detection. The functions of SIC, frequency up-conversion, down-conversion, and fiber transmission with dispersion immunity are all incorporated in the system. An experiment is performed. Cancellation depths of more than 39 dB for the single-tone signal and more than 20 dB for the 20-MBaud 16 quadrature amplitude modulation signal are achieved in the back-to-back case. The performance of the system does not have a significant decline when a section of 4.1-km optical fiber is incorporated.
Large performance degradation is often observed for speaker ver-ification systems when applied to a new domain dataset. Givenan unlabeled target-domain dataset, unsupervised domain adaptation(UDA) methods, which usually leverage adversarial training
strate-gies, are commonly used to bridge the performance gap caused bythe domain mismatch. However, such adversarial training strategyonly uses the distribution information of target domain data and cannot ensure the performance improvement on the target domain. Inthis paper, we incorporate self-supervised learning strategy to the un-supervised domain adaptation system and proposed a self-supervisedlearning based domain adaptation approach (SSDA). Compared tothe traditional UDA method, the new SSDA training strategy canfully leverage the potential label information from target domainand adapt the speaker discrimination ability from source domainsimultaneously. We evaluated the proposed approach on the Vox-Celeb (labeled source domain) and CnCeleb (unlabeled target do-main) datasets, and the best SSDA system obtains 10.2% Equal ErrorRate (EER) on the CnCeleb dataset without using any speaker labelson CnCeleb, which also can achieve the state-of-the-art results onthis corpus.
We describe a process for cross-calibrating the effective areas of X-ray telescopes that observe common targets. The targets are not assumed to be standard candles in the classic sense, in that we assume that the source fluxes have well-defined, but
{it a priori} unknown values. Using a technique developed by Chen et al. (2019, arXiv:1711.09429) that involves a statistical method called {em shrinkage estimation}, we determine effective area correction factors for each instrument that brings estimated fluxes into the best agreement, consistent with prior knowledge of their effective areas. We expand the technique to allow unique priors on systematic uncertainties in effective areas for each X-ray astronomy instrument and to allow correlations between effective areas in different energy bands. We demonstrate the method with several data sets from various X-ray telescopes.
Generating font glyphs of consistent style from one or a few reference glyphs, i.e., font completion, is an important task in topographical design. As the problem is more well-defined than general image style transfer tasks, thus it has received inte
rest from both vision and machine learning communities. Existing approaches address this problem as a direct image-to-image translation task. In this work, we innovate to explore the generation of font glyphs as 2D graphic objects with the graph as an intermediate representation, so that more intrinsic graphic properties of font styles can be captured. Specifically, we formulate a cross-modality cycled image-to-image model structure with a graph constructor between an image encoder and an image renderer. The novel graph constructor maps a glyphs latent code to its graph representation that matches expert knowledge, which is trained to help the translation task. Our model generates improved results than both image-to-image baseline and previous state-of-the-art methods for glyph completion. Furthermore, the graph representation output by our model also provides an intuitive interface for users to do local editing and manipulation. Our proposed cross-modality cycled representation learning has the potential to be applied to other domains with prior knowledge from different data modalities. Our code is available at https://github.com/VITA-Group/Font_Completion_Graph.
