arXiv subjects

Yingjie Li

Publications and source records attributed to Yingjie Li.

At least 55 records · Page 3Linked to original sources

arXiv2024

A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution

Based on Pre-trained Language Models (PLMs), event coreference resolution (ECR) systems have demonstrated outstanding performance in clustering coreferential events across documents. However, the existing system exhibits an excessive reliance on the `triggers lexical matching' spurious pattern in the input mention pair text. We formalize the decision-making process of the baseline ECR system using a Structural Causal Model (SCM), aiming to identify spurious and causal associations (i.e., rationales) within the ECR task. Leveraging the debiasing capability of counterfactual data augmentation, we develop a rationale-centric counterfactual data augmentation method with LLM-in-the-loop. This method is specialized for pairwise input in the ECR system, where we conduct direct interventions on triggers and context to mitigate the spurious association while emphasizing the causation. Our approach achieves state-of-the-art performance on three popular cross-document ECR benchmarks and demonstrates robustness in out-of-domain scenarios.

cs.CL↗

arXiv2024

VLBI with SKA: Possible Arrays and Astrometric Science

The next generation of very long baseline interferometry (VLBI) is stepping into the era of microarcsecond ($μ$as) astronomy, and pushing astronomy, especially astrometry, to new heights. VLBI with the Square Kilometre Array (SKA), SKA-VLBI, will increase current sensitivity by an order of magnitude, and reach astrometric precision routinely below 10 $μ$as, even challenging 1 $μ$as. This advancement allows precise parallax and proper motion measurements of various celestial objects. Such improvements can be used to study objects (including isolated objects, and binary or multiple systems) in different stellar stages (such as star formation, main-sequence stars, asymptotic giant branch stars, pulsars, black holes, white dwarfs, etc.), unveil the structure and evolution of complex systems (such as the Milky Way), benchmark the international celestial reference frame, and reveal cosmic expansion. Furthermore, the theory of general relativity can also be tested with SKA-VLBI using precise measurements of light deflection under the gravitational fields of different solar system objects and the perihelion precession of solar system objects.

astro-ph.GA↗

arXiv2024

BoolGebra: Attributed Graph-learning for Boolean Algebraic Manipulation

Boolean algebraic manipulation is at the core of logic synthesis in Electronic Design Automation (EDA) design flow. Existing methods struggle to fully exploit optimization opportunities, and often suffer from an explosive search space and limited scalability efficiency. This work presents BoolGebra, a novel attributed graph-learning approach for Boolean algebraic manipulation that aims to improve fundamental logic synthesis. BoolGebra incorporates Graph Neural Networks (GNNs) and takes initial feature embeddings from both structural and functional information as inputs. A fully connected neural network is employed as the predictor for direct optimization result predictions, significantly reducing the search space and efficiently locating the optimization space. The experiments involve training the BoolGebra model w.r.t design-specific and cross-design inferences using the trained model, where BoolGebra demonstrates generalizability for cross-design inference and its potential to scale from small, simple training datasets to large, complex inference datasets. Finally, BoolGebra is integrated with existing synthesis tool ABC to perform end-to-end logic minimization evaluation w.r.t SOTA baselines.

cs.AR↗

arXiv2023

Verilog-to-PyG -- A Framework for Graph Learning and Augmentation on RTL Designs

The complexity of modern hardware designs necessitates advanced methodologies for optimizing and analyzing modern digital systems. In recent times, machine learning (ML) methodologies have emerged as potent instruments for assessing design quality-of-results at the Register-Transfer Level (RTL) or Boolean level, aiming to expedite design exploration of advanced RTL configurations. In this presentation, we introduce an innovative open-source framework that translates RTL designs into graph representation foundations, which can be seamlessly integrated with the PyTorch Geometric graph learning platform. Furthermore, the Verilog-to-PyG (V2PYG) framework is compatible with the open-source Electronic Design Automation (EDA) toolchain OpenROAD, facilitating the collection of labeled datasets in an utterly open-source manner. Additionally, we will present novel RTL data augmentation methods (incorporated in our framework) that enable functional equivalent design augmentation for the construction of an extensive graph-based RTL design database. Lastly, we will showcase several using cases of V2PYG with detailed scripting examples. V2PYG can be found at \url{https://yu-maryland.github.io/Verilog-to-PyG/}.

cs.LG↗

arXiv2023

Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information

Argument structure extraction (ASE) aims to identify the discourse structure of arguments within documents. Previous research has demonstrated that contextual information is crucial for developing an effective ASE model. However, we observe that merely concatenating sentences in a contextual window does not fully utilize contextual information and can sometimes lead to excessive attention on less informative sentences. To tackle this challenge, we propose an Efficient Context-aware ASE model (ECASE) that fully exploits contextual information by enhancing modeling capacity and augmenting training data. Specifically, we introduce a sequence-attention module and distance-weighted similarity loss to aggregate contextual information and argumentative information. Additionally, we augment the training data by randomly masking discourse markers and sentences, which reduces the model's reliance on specific words or less informative sentences. Our experiments on five datasets from various domains demonstrate that our model achieves state-of-the-art performance. Furthermore, ablation studies confirm the effectiveness of each module in our model.

cs.CL↗

arXiv2023

LightRidge: An End-to-end Agile Design Framework for Diffractive Optical Neural Networks

To lower the barrier to diffractive optical neural networks (DONNs) design, exploration, and deployment, we propose LightRidge, the first end-to-end optical ML compilation framework, which consists of (1) precise and differentiable optical physics kernels that enable complete explorations of DONNs architectures, (2) optical physics computation kernel acceleration that significantly reduces the runtime cost in training, emulation, and deployment of DONNs, and (3) versatile and flexible optical system modeling and user-friendly domain-specific-language (DSL). As a result, LightRidge framework enables efficient end-to-end design and deployment of DONNs, and significantly reduces the efforts for programming, hardware-software codesign, and chip integration. Our results are experimentally conducted with physical optical systems, where we demonstrate: (1) the optical physics kernels precisely correlated to low-level physics and systems, (2) significant speedups in runtime with physics-aware emulation workloads compared to the state-of-the-art commercial system, (3) effective architectural design space exploration verified by the hardware prototype and on-chip integration case study, and (4) novel DONN design principles including successful demonstrations of advanced image classification and image segmentation task using DONNs architecture and topology.

cs.AR↗

arXiv2023

Kinematics of the Local Spiral Structure Revealed by Young Stars in \emph{Gaia}~DR3

Using young open clusters and O--B2-type stars in~\emph{Gaia}~DR3, we investigate the kinematics of the local spiral structure. In general, the young sources in the outer spiral arms may present larger peculiar motions than those in the inner spiral arms. The young open clusters appear to have smaller peculiar motions than the O--B2-type stars, and the sources in both the Perseus and Local Arms may show an inward motion toward the Galactic center and rotate slower than Galactic rotation. Meanwhile, the sources in the Carina Arm may move in the opposite direction from the Sun to the Galactic center and rotate marginally faster than Galactic rotation. In addition, using young open clusters and O--B2-type stars, we have improved the distance estimations of kinematic methods for several regions near the Sun.

astro-ph.GA↗

arXiv2023

Distributions and Physical Properties of Molecular Clouds in the Third Galactic Quadrant: $l$ = [219.75, 229.75]$^\circ$ and $b$ = [-5.25, 5.25]$^\circ$

We present the results of an unbiased $^{12}$CO/$^{13}$CO/C$^{18}$O ($J$ = 1-0) survey in a portion of the third Galactic quadrant (TGQ): $l$ = [219.75, 229.75]$^\circ$ and $b$ = [-5.25, 5.25]$^\circ$. The high-resolution and high-sensitivity data sets help to unravel the distributions and physical properties of the molecular clouds (MCs) in the mapped area. In the LSR velocity range from -1 to 85 km/s, the molecular material successfully traces the Local, Perseus, and Outer arms. In the TGQ, the Outer arm appears to be more prominent than that in the second Galactic quadrant (SGQ), but the Perseus arm is not as conspicuous as that in the SGQ. A total of 1,502 $^{12}$CO, 570 $^{13}$CO, and 53 C$^{18}$O molecular structures are identified, spanning over $\sim2$ and $\sim6$ orders of magnitude in size and mass, respectively. Tight mass-radius correlations and virial parameter-mass anticorrelations are observable. Yet, it seems that no clear correlations between velocity dispersion and effective radius can be found over the full dynamic range. The vertical distribution of the MCs renders evident pictures of the Galactic warp and flare.

astro-ph.GA↗

arXiv2023

Gamora: Graph Learning based Symbolic Reasoning for Large-Scale Boolean Networks

Reasoning high-level abstractions from bit-blasted Boolean networks (BNs) such as gate-level netlists can significantly benefit functional verification, logic minimization, datapath synthesis, malicious logic identification, etc. Mostly, conventional reasoning approaches leverage structural hashing and functional propagation, suffering from limited scalability and inefficient usage of modern computing power. In response, we propose a novel symbolic reasoning framework exploiting graph neural networks (GNNs) and GPU acceleration to reason high-level functional blocks from gate-level netlists, namely Gamora, which offers high reasoning performance w.r.t exact reasoning algorithms, strong scalability to BNs with over 33 million nodes, and generalization capability from simple to complex designs. To further demonstrate the capability of Gamora, we also evaluate its reasoning performance after various technology mapping options, since technology-dependent optimizations are known to make functional reasoning much more challenging. Experimental results show that (1) Gamora reaches almost 100% and over 97% reasoning accuracy for carry-save-array (CSA) and Booth-encoded multipliers, respectively, with up to six orders of magnitude speedups compared to the state-of-the-art implementation in the ABC framework; (2) Gamora maintains high reasoning accuracy (>92%) in finding functional modules after complex technology mapping, upon which we comprehensively analyze the impacts on Gamora reasoning from technology mapping.

cs.AR↗

arXiv2023

FlowTune: End-to-end Automatic Logic Optimization Exploration via Domain-specific Multi-armed Bandit

Recent years have seen increasing employment of decision intelligence in electronic design automation (EDA), which aims to reduce the manual efforts and boost the design closure process in modern toolflows. However, existing approaches either require a large number of labeled data and expensive training efforts, or are limited in practical EDA toolflow integration due to computation overhead. This paper presents a generic end-to-end sequential decision making framework FlowTune for synthesis tooflow optimization, with a novel high-performance domain-specific, multi-stage multi-armed bandit (MAB) approach. This framework addresses optimization problems on Boolean optimization problems such as a) And-Inv-Graphs (# nodes), b) Conjunction Normal Form (CNF) minimization (# clauses) for Boolean Satisfiability; logic synthesis and technology mapping problems such as c) post static timing analysis (STA) delay and area optimization for standard-cell technology mapping, and d) FPGA technology mapping for 6-in LUT architectures. Moreover, we demonstrate the high extnsibility and generalizability of the proposed domain-specific MAB approach with end-to-end FPGA design flow, evaluated at post-routing stage, with two different FPGA backend tools (OpenFPGA and VPR) and two different logic synthesis representations (AIGs and MIGs). FlowTune is fully integrated with ABC [1], Yosys [2], VTR [3], LSOracle [4], OpenFPGA [5], and industrial tools, and is released publicly. The experimental results conducted on various design stages in the flow all demonstrate that our framework outperforms both hand-crafted flows [1] and ML explored flows [6], [7] in quality of results, and is orders of magnitude faster compared to ML-based approaches.

cs.AR↗

arXiv2023

Rubik's Optical Neural Networks: Multi-task Learning with Physics-aware Rotation Architecture

Recently, there are increasing efforts on advancing optical neural networks (ONNs), which bring significant advantages for machine learning (ML) in terms of power efficiency, parallelism, and computational speed. With the considerable benefits in computation speed and energy efficiency, there are significant interests in leveraging ONNs into medical sensing, security screening, drug detection, and autonomous driving. However, due to the challenge of implementing reconfigurability, deploying multi-task learning (MTL) algorithms on ONNs requires re-building and duplicating the physical diffractive systems, which significantly degrades the energy and cost efficiency in practical application scenarios. This work presents a novel ONNs architecture, namely, \textit{RubikONNs}, which utilizes the physical properties of optical systems to encode multiple feed-forward functions by physically rotating the hardware similarly to rotating a \textit{Rubik's Cube}. To optimize MTL performance on RubikONNs, two domain-specific physics-aware training algorithms \textit{RotAgg} and \textit{RotSeq} are proposed. Our experimental results demonstrate more than 4$\times$ improvements in energy and cost efficiency with marginal accuracy degradation compared to the state-of-the-art approaches.

cs.LG↗

arXiv2023

RESPECT: Reinforcement Learning based Edge Scheduling on Pipelined Coral Edge TPUs

Deep neural networks (DNNs) have substantial computational and memory requirements, and the compilation of its computational graphs has a great impact on the performance of resource-constrained (e.g., computation, I/O, and memory-bound) edge computing systems. While efficient execution of their computational graph requires an effective scheduling algorithm, generating the optimal scheduling solution is a challenging NP-hard problem. Furthermore, the complexity of scheduling DNN computational graphs will further increase on pipelined multi-core systems considering memory communication cost, as well as the increasing size of DNNs. Using the synthetic graph for the training dataset, this work presents a reinforcement learning (RL) based scheduling framework RESPECT, which learns the behaviors of optimal optimization algorithms and generates near-optimal scheduling results with short solving runtime overhead. Our framework has demonstrated up to $\sim2.5\times$ real-world on-chip inference runtime speedups over the commercial compiler with ten popular ImageNet models deployed on the physical Coral Edge TPUs system. Moreover, compared to the exact optimization methods, the proposed RL scheduling improves the scheduling optimization runtime by up to 683$\times$ speedups compared to the commercial compiler and matches the exact optimal solutions with up to 930$\times$ speedups. Finally, we perform a comprehensive generalizability test, which demonstrates RESPECT successfully imitates optimal solving behaviors from small synthetic graphs to large real-world DNNs computational graphs.

cs.AR↗

arXiv2023

Physics-aware Roughness Optimization for Diffractive Optical Neural Networks

As a representative next-generation device/circuit technology beyond CMOS, diffractive optical neural networks (DONNs) have shown promising advantages over conventional deep neural networks due to extreme fast computation speed (light speed) and low energy consumption. However, there is a mismatch, i.e., significant prediction accuracy loss, between the DONN numerical modelling and physical optical device deployment, because of the interpixel interaction within the diffractive layers. In this work, we propose a physics-aware diffractive optical neural network training framework to reduce the performance difference between numerical modeling and practical deployment. Specifically, we propose the roughness modeling regularization in the training process and integrate the physics-aware sparsification method to introduce sparsity to the phase masks to reduce sharp phase changes between adjacent pixels in diffractive layers. We further develop $2π$ periodic optimization to reduce the roughness of the phase masks to preserve the performance of DONN. Experiment results demonstrate that, compared to state-of-the-arts, our physics-aware optimization can provide $35.7\%$, $34.2\%$, $28.1\%$, and $27.3\%$ reduction in roughness with only accuracy loss on MNIST, FMNIST, KMNIST, and EMNIST, respectively.

cs.LG↗

arXiv2022

Calibrating the Cepheid Period--Wesenheit Relation in the Gaia Bands using Galactic Open Cluster Cepheids

Establishing the period--Wesenheit relation requires independent and accurate distance measurements of classical Cepheids (DCEPs). The precise distance provided by an associated open cluster independently calibrates the period--Wesenheit relation of DCEPs. 51 DCEPs associated with open clusters are compiled using the constraints of five-dimensional astrometric information. By directly using Gaia DR3 parallax, the period--Wesenheit relation in the Gaia $G$ band is calibrated as $W_G = (-3.06 \pm 0.11) \log P + (-2.96 \pm 0.10)$. Compared with the results derived by directly adopting the DCEP parallaxes or using distance moduli, the Wesenheit magnitudes based on the cluster-averaged parallaxes exhibit a tighter relation with the period. Besides, there is a systematic offset between the observed Wesenheit absolute magnitudes of distant OC-DCEPs and their fitted magnitudes. After considering the parallax zero-point correction, the systematic offset can be reduced, yielding a probably better PW relation of $W_G = (-2.94 \pm 0.12) \log P + (-2.93 \pm 0.11)$.

astro-ph.SR↗

arXiv2022

Physics-aware Differentiable Discrete Codesign for Diffractive Optical Neural Networks

Diffractive optical neural networks (DONNs) have attracted lots of attention as they bring significant advantages in terms of power efficiency, parallelism, and computational speed compared with conventional deep neural networks (DNNs), which have intrinsic limitations when implemented on digital platforms. However, inversely mapping algorithm-trained physical model parameters onto real-world optical devices with discrete values is a non-trivial task as existing optical devices have non-unified discrete levels and non-monotonic properties. This work proposes a novel device-to-system hardware-software codesign framework, which enables efficient physics-aware training of DONNs w.r.t arbitrary experimental measured optical devices across layers. Specifically, Gumbel-Softmax is employed to enable differentiable discrete mapping from real-world device parameters into the forward function of DONNs, where the physical parameters in DONNs can be trained by simply minimizing the loss function of the ML task. The results have demonstrated that our proposed framework offers significant advantages over conventional quantization-based methods, especially with low-precision optical devices. Finally, the proposed algorithm is fully verified with physical experimental optical systems in low-precision settings.

cs.AI↗

arXiv2022

The Effect of Light Deflection by Solar System Objects on High-Precision SKA Astrometry

We have computed the deflection angles caused by 195 objects in the solar system, including 177 satellites and eight asteroids. Twenty-one satellites and six asteroids can bend light from distant compact extragalactic sources by more than 0.1 $μ$as, and fourteen satellites and the asteroid Ceres can deflect light by more than 1.0 $μ$as. We calculated the zones and durations of perturbations posed by the gravitational fields of five planets (excluding Earth, Jupiter, and Saturn), Pluto, and Ceres, where the perturbations would affect astrometry measured with the Squared Kilometre Array (SKA). Perturbed zones with deflection angles larger than 0.1 and 1.0 $μ$as appear as ribbons. Their widths range from dozens of degrees for Uranus, Neptune, and Venus to several degrees or less for other objects at 0.1 $μ$as, and from $\sim$ 16$^{\circ}$ for Venus to several degrees or less for other objects at 1.0 $μ$as. From the calculated perturbation durations, the influence of the gravitational fields of selected objects can be divided into four levels: hardly affect SKA astrometry (I), may have little effect (II), may have a great effect (III) on single-epoch astrometry, and may greatly affect both single- and multi-epoch astrometry (IV). The objects corresponding to these levels are Ceres (I), Pluto (II), Mercury and Mars (III), and other objects (IV).

gr-qc↗

arXiv2022

QuickSkill: Novice Skill Estimation in Online Multiplayer Games

Matchmaking systems are vital for creating fair matches in online multiplayer games, which directly affects players' satisfactions and game experience. Most of the matchmaking systems largely rely on precise estimation of players' game skills to construct equitable games. However, the skill rating of a novice is usually inaccurate, as current matchmaking rating algorithms require considerable amount of games for learning the true skill of a new player. Using these unreliable skill scores at early stages for matchmaking usually leads to disparities in terms of team performance, which causes negative game experience. This is known as the ''cold-start'' problem for matchmaking rating algorithms. To overcome this conundrum, this paper proposes QuickSKill, a deep learning based novice skill estimation framework to quickly probe abilities of new players in online multiplayer games. QuickSKill extracts sequential performance features from initial few games of a player to predict his/her future skill rating with a dedicated neural network, thus delivering accurate skill estimation at the player's early game stage. By employing QuickSKill for matchmaking, game fairness can be dramatically improved in the initial cold-start period. We conduct experiments in a popular mobile multiplayer game in both offline and online scenarios. Results obtained with two real-world anonymized gaming datasets demonstrate that proposed QuickSKill delivers precise estimation of game skills for novices, leading to significantly lower team skill disparities and better player game experience. To the best of our knowledge, proposed QuickSKill is the first framework that tackles the cold-start problem for traditional skill rating algorithms.

cs.LG↗

arXiv2022

Local Spiral Structure Traced by Red Clump Stars

Using the cross-matched data of Gaia EDR3 and the 2MASS Point Source Catalog, a sample of RC stars with parallax accuracies better than 20% is identified and used to reveal the nearby spiral pattern traced by old stars. As shown in the overdensity distribution of RC stars, there is an arc-like feature extended from $l~\sim$ 90$^\circ$ to $\sim$ 243$^\circ$, which passed close to the Sun. This feature is probably an arm segment traced by old stars, indicating the Galaxy potential in the vicinity of the Sun. By comparing to the spiral arms depicted by young objects, we found that there are considerable offsets between the two different components of Galactic spiral arms. The spiral arm traced by RC stars tends to have a larger pitch angle, hence a more loose wound pattern.

astro-ph.GA↗