Searcharxiv⌕ Search

arXiv subjects

Yong Li

Publications and source records attributed to Yong Li.

At least 595 records · Page 33Linked to original sources
arXiv2023

Road Planning for Slums via Deep Reinforcement Learning

Millions of slum dwellers suffer from poor accessibility to urban services due to inadequate road infrastructure within slums, and road planning for slums is critical to the sustainable development of cities. Existing re-blocking or heuristic methods are either time-consuming which cannot generalize to different slums, or yield sub-optimal road plans in terms of accessibility and construction costs. In this paper, we present a deep reinforcement learning based approach to automatically layout roads for slums. We propose a generic graph model to capture the topological structure of a slum, and devise a novel graph neural network to select locations for the planned roads. Through masked policy optimization, our model can generate road plans that connect places in a slum at minimal construction costs. Extensive experiments on real-world slums in different countries verify the effectiveness of our model, which can significantly improve accessibility by 14.3% against existing baseline methods. Further investigations on transferring across different tasks demonstrate that our model can master road planning skills in simple scenarios and adapt them to much more complicated ones, indicating the potential of applying our model in real-world slum upgrading. The code and data are available at https://github.com/tsinghua-fib-lab/road-planning-for-slums.

cs.AI↗
arXiv2023

Carbon emissions and sustainability of launching 5G mobile networks in China

Since 2021, China has deployed more than 2.1 million 5G base stations to increase the network capacity and provide ubiquitous digital connectivity for mobile terminals. However, the launch of 5G networks also exacerbates the misalignment between cellular traffic and energy consumption, which reduces carbon efficiency - the amount of network traffic that can be delivered for each unit of carbon emission. In this study, we develop a large-scale data-driven framework to estimate the carbon emissions induced by mobile networks. We show that the decline in carbon efficiency leads to a carbon efficiency trap, estimated to cause additional carbon emissions of 23.82 +- 1.07 megatons in China. To mitigate the misalignment and improve energy efficiency, we propose DeepEnergy, an energy-saving method leveraging collaborative deep reinforcement learning and graph neural networks. DeepEnergy models complex collaboration among cells, making it possible to effectively coordinate the working state of tens of thousands of cells, which could help over 71% of Chinese provinces avoid carbon efficiency traps. In addition, applying DeepEnergy is estimated to reduce 20.90 +- 0.98 megatons of carbon emissions at the national level in 2023. We further assess the effects of adopting renewable energy and discover that the mobile network could accomplish more than 50% of its net-zero goal by integrating DeepEnergy and solar energy systems. Our study provides insight into carbon emission mitigation in 5G network infrastructure launching in China and overworld, paving the way towards achieving sustainable development goals and future net-zero mobile networks.

eess.SY↗
arXiv2023

Legion: Automatically Pushing the Envelope of Multi-GPU System for Billion-Scale GNN Training

Graph neural network(GNN) has been widely applied in real-world applications, such as product recommendation in e-commerce platforms and risk control in financial management systems. Several cache-based GNN systems have been built to accelerate GNN training in a single machine with multiple GPUs. However, these systems fail to train billion-scale graphs efficiently, which is a common challenge in the industry. In this work, we propose Legion, a system that automatically pushes the envelope of multi-GPU systems for accelerating billion-scale GNN training. First, we design a hierarchical graph partitioning mechanism that significantly improves the multi-GPU cache performance. Second, we build a unified multi-GPU cache that helps to minimize the PCIe traffic incurred by caching both graph topology and features with the highest hotness. Third, we develop an automatic caching management mechanism that adapts the multi-GPU cache plan according to the hardware specifications and various graphs to maximize the overall training throughput. Evaluations on various GNN models and multiple datasets show that Legion supports training billion-scale GNNs in a single machine and significantly outperforms the state-of-the-art cache-based systems on small graphs.

cs.DC↗
arXiv2023

Global Weinstein Type Theorem on Multiple Rotating Periodic Solutions for Hamiltonian Systems

This paper concerns the existence of multiple rotating periodic solutions for $2n$ dimensional convex Hamiltonian systems. For the symplectic orthogonal matrix $Q$, the rotating periodic solution has the form of $z(t+T)=Qz(t)$, which might be periodic, anti-periodic, subharmonic or quasi-periodic according to the structure of $Q$. It is proved that there exist at least $n$ geometrically distinct rotating periodic solutions on a given $Q$ invariant convex energy surface under a pinching condition. As a result, it is proved that if the symmetric energy surface admits a nonsymmetric periodic solution, it has infinitely many periodic orbits. In order to prove the result, we introduce a new index on rotating periodic orbits.

math.DS↗
arXiv2023

Complexity-aware Large Scale Origin-Destination Network Generation via Diffusion Model

The Origin-Destination~(OD) networks provide an estimation of the flow of people from every region to others in the city, which is an important research topic in transportation, urban simulation, etc. Given structural regional urban features, generating the OD network has become increasingly appealing to many researchers from diverse domains. However, existing works are limited in independent generation of each OD pair, i.e., flow of people from one region to another, overlooking the relations within the overall network. In this paper, we instead propose to generate the OD network, and design a graph denoising diffusion method to learn the conditional joint probability distribution of the nodes and edges within the OD network given city characteristics at region level. To overcome the learning difficulty of the OD networks covering over thousands of regions, we decompose the original one-shot generative modeling of the diffusion model into two cascaded stages, corresponding to the generation of network topology and the weights of edges, respectively. To further reproduce important network properties contained in the city-wide OD network, we design an elaborated graph denoising network structure including a node property augmentation module and a graph transformer backbone. Empirical experiments on data collected in three large US cities have verified that our method can generate OD matrices for new cities with network statistics remarkably similar with the ground truth, further achieving superior outperformance over competitive baselines in terms of the generation realism.

cs.LG↗
arXiv2023

Vanadium-Based Superconductivity in a Breathing Kagome Compound Ta2V3.1Si0.9

Superconductivity in V-based kagome metals has recently raised great interest as they exhibit the competing ground states associated with the flat bands and topological electronic structures. Here we report the discovery of superconductivity in Ta2V3.1Si0.9 with a superconducting transition temperature Tc of 7.5 K, much higher than those in previously reported kagome metals at ambient pressure. While the V ions form a two-dimensional breathing kagome structure, the length difference between two different V-V bonds is just 0.04, making it very close to the perfect kagome structure. Our results show that Ta2V3.1Si0.9 is a moderate-coupled superconductor with a large upper critical field that is close to the Pauli limit. DFT calculations give a van-Hove-singularity band located at Fermi energy, which may explain the relatively high Tc observed in this material.

cond-mat.supr-con↗
arXiv2023

Origin-Destination Network Generation via Gravity-Guided GAN

Origin-destination (OD) flow, which contains valuable population mobility information including direction and volume, is critical in many urban applications, such as urban planning, transportation management, etc. However, OD data is not always easy to access due to high costs or privacy concerns. Therefore, we must consider generating OD through mathematical models. Existing works utilize physics laws or machine learning (ML) models to build the association between urban structures and OD flows while these two kinds of methods suffer from the limitation of over-simplicity and poor generalization ability, respectively. In this paper, we propose to adopt physics-informed ML paradigm, which couple the physics scientific knowledge and data-driven ML methods, to construct a model named Origin-Destination Generation Networks (ODGN) for better population mobility modeling by leveraging the complementary strengths of combining physics and ML methods. Specifically, we first build a Multi-view Graph Attention Networks (MGAT) to capture the urban features of every region and then use a gravity-guided predictor to obtain OD flow between every two regions. Furthermore, we use a conditional GAN training strategy and design a sequence-based discriminator to consider the overall topological features of OD as a network. Extensive experiments on real-world datasets have been done to demonstrate the superiority of our proposed method compared with baselines.

cs.LG↗
arXiv2023

Decay dynamics of a giant atom in a structured bath with broken time-reversal symmetry

We study in this paper the decay dynamics of a two-level giant atom, which is coupled to a quasi-one-dimensional sawtooth lattice exposed to uniform synthetic magnetic fluxes. In the case where the two sublattices have a large detuning, the giant atom is effectively coupled to a single-band structured bath with flux-controlled energy band and time-reversal symmetry. This feature significantly affects the decay dynamics of the giant atom as well as the propagation of the emitted photon. In particular, the giant atom can exhibit chiral spontaneous emission and allow for nonreciprocal delayed light, which are however unattainable by coupling a small atom to this lattice. Giant atoms with different frequencies can be designed to emit photons towards different directions and with different group velocities. Our results pave the way towards engineering quantum networks and manipulating giant-atom interference effects.

quant-ph↗
arXiv2023

How Graph Convolutions Amplify Popularity Bias for Recommendation?

Graph convolutional networks (GCNs) have become prevalent in recommender system (RS) due to their superiority in modeling collaborative patterns. Although improving the overall accuracy, GCNs unfortunately amplify popularity bias -- tail items are less likely to be recommended. This effect prevents the GCN-based RS from making precise and fair recommendations, decreasing the effectiveness of recommender systems in the long run. In this paper, we investigate how graph convolutions amplify the popularity bias in RS. Through theoretical analyses, we identify two fundamental factors: (1) with graph convolution (\textit{i.e.,} neighborhood aggregation), popular items exert larger influence than tail items on neighbor users, making the users move towards popular items in the representation space; (2) after multiple times of graph convolution, popular items would affect more high-order neighbors and become more influential. The two points make popular items get closer to almost users and thus being recommended more frequently. To rectify this, we propose to estimate the amplified effect of popular nodes on each node's representation, and intervene the effect after each graph convolution. Specifically, we adopt clustering to discover highly-influential nodes and estimate the amplification effect of each node, then remove the effect from the node embeddings at each graph convolution layer. Our method is simple and generic -- it can be used in the inference stage to correct existing models rather than training a new model from scratch, and can be applied to various GCN models. We demonstrate our method on two representative GCN backbones LightGCN and UltraGCN, verifying its ability in improving the recommendations of tail items without sacrificing the performance of popular items. Codes are open-sourced \footnote{https://github.com/MEICRS/DAP}.

cs.IR↗
arXiv2023

Singly Exponential Translation of Alternating Weak Büchi Automata to Unambiguous Büchi Automata

We introduce a method for translating an alternating weak Büchi automaton (AWA), which corresponds to a Linear Dynamic Logic (LDL) formula, to an unambiguous Büchi automaton (UBA). Our translations generalise constructions for Linear Temporal Logic (LTL), a less expressive specification language than LDL. In classical constructions, LTL formulas are first translated to alternating \emph{very weak} automata (AVAs) -- automata that have only singleton strongly connected components (SCCs); the AVAs are then handled by efficient disambiguation procedures. However, general AWAs can have larger SCCs, which complicates disambiguation. Currently, the only available disambiguation procedure has to go through an intermediate construction of nondeterministic Büchi automata (NBAs), which would incur an exponential blow-up of its own. We introduce a translation from \emph{general} AWAs to UBAs with a \emph{singly} exponential blow-up, which also immediately provides a singly exponential translation from LDL to UBAs. Interestingly, the complexity of our translation is \emph{smaller} than the best known disambiguation algorithm for NBAs (broadly $(0.53n)^n$ vs. $(0.76n)^n$), while the input of our construction can be exponentially more succinct.

cs.FL↗
arXiv2023

Template-based eukaryotic genome editing directed by SviCas3

RNA-guided gene editing based on the CRISPR-Cas system is currently the most effective genome editing technique. Here, we report that the SviCas3 from the subtype I-B-Svi Cas system in Streptomyces virginiae IBL14 is an RNA-guided and DNA-guided DNA endonuclease suitable for the HDR-directed gene and/or base editing of eukaryotic cell genomes. The genome editing efficiency of SviCas3 guided by DNA is no less than that of SviCas3 guided by RNA. In particular, t-DNA, as a template and a guide, does not require a proto-spacer-adjacent motif, demonstrating that CRISPR, as the basis for crRNA design, is not required for the SviCas3-mediated gene and base editing. This discovery will broaden our understanding of enzyme diversity in CRISPR-Cas systems, will provide important tools for the creation and modification of living things and the treatment of human genetic diseases, and will usher in a new era of DNA-guided gene editing and base editing.

q-bio.GN↗
arXiv2023

Dynamical $N$-photon bundle emission

Engineering multiphoton resources is of importance in quantum metrology, quantum lithography, and biological sensing. Here we propose a concept of dynamical emission of $N$ strongly-correlated photons. This is realized in a circuit quantum electrodynamical system driven by two Gaussian-pulse sequences. The underlying physical mechanism relies on the stimulated Raman adiabatic passage that allows efficient and selective preparation of target multiphoton states. Assisted by the photon decay, a highly pure $N$-photon bundle emission takes place in this system. In particular, the dynamical $N$-photon bundle emission can be tuned by controlling the time interval between consecutive pulses so that the device behaves as an $N$-photon gun, which can be triggered on demand. Our work opens up a route to achieve multiphoton source devices, which have wide potential applications in quantum information processing and quantum metrology.

quant-ph↗
arXiv2023

Enantiodetection via the 2D spectroscopy: extending the methodology to general experimental conditions

Developing effective methods to measure the enantiomeric excess of the chiral mixture is one of the major topics in chiral molecular researches, yet remains challenging. Enantiodetection method via two-dimensional (2D) spectroscopy based on a four level model, containing a cyclic three-level system (CTLS), of chiral molecules was recently proposed and demonstrated, yet with a strict condition of the one-photon resonance (where three driving fields are exactly resonantly coupled to the three electric-dipole transitions, respectively) in the CTLS and narrowband probe pulse assumption. Here, we extend the 2D spectroscopy method to more general experimental conditions, with three-photon resonance (where the sum of the two smaller frequencies among the three driving fields equals to the third one) and broadband probe pulse. Our method remains effective on enantiodetection with the help of experimental techniques, such as the chop detection method, which is used to eliminate the influence of the other redundant levels existing in the real system of chiral molecules. Under these more general conditions, the enantiomeric excess of the chiral mixture is estimated by taking an easily available standard sample (usually the racemic mixture) as the reference.

physics.chem-ph↗
arXiv2023

An Infinite-dimensional KAM Theorem with Normal Degeneracy

In this paper, we consider a classical Hamiltonian normal form with degeneracy in normal direction. In previous results, one needs to assume that the perturbation satisfies certain non-degenerate conditions in order to remove the degeneracy in the normal form. In stead of that, we introduce a topological degree condition and a weak convexity condition, which are easy to be verified, and we prove the persistence of lower dimensional tori without any restriction on perturbation but only smallness and analyticity.

math.DS↗
arXiv2023

Decoupled Multimodal Distilling for Emotion Recognition

Human multimodal emotion recognition (MER) aims to perceive human emotions via language, visual and acoustic modalities. Despite the impressive performance of previous MER approaches, the inherent multimodal heterogeneities still haunt and the contribution of different modalities varies significantly. In this work, we mitigate this issue by proposing a decoupled multimodal distillation (DMD) approach that facilitates flexible and adaptive crossmodal knowledge distillation, aiming to enhance the discriminative features of each modality. Specially, the representation of each modality is decoupled into two parts, i.e., modality-irrelevant/-exclusive spaces, in a self-regression manner. DMD utilizes a graph distillation unit (GD-Unit) for each decoupled part so that each GD can be performed in a more specialized and effective manner. A GD-Unit consists of a dynamic graph where each vertice represents a modality and each edge indicates a dynamic knowledge distillation. Such GD paradigm provides a flexible knowledge transfer manner where the distillation weights can be automatically learned, thus enabling diverse crossmodal knowledge transfer patterns. Experimental results show DMD consistently obtains superior performance than state-of-the-art MER methods. Visualization results show the graph edges in DMD exhibit meaningful distributional patterns w.r.t. the modality-irrelevant/-exclusive feature spaces. Codes are released at \url{https://github.com/mdswyz/DMD}.

cs.CV↗
arXiv2023

Robust Preference-Guided Denoising for Graph based Social Recommendation

Graph Neural Network(GNN) based social recommendation models improve the prediction accuracy of user preference by leveraging GNN in exploiting preference similarity contained in social relations. However, in terms of both effectiveness and efficiency of recommendation, a large portion of social relations can be redundant or even noisy, e.g., it is quite normal that friends share no preference in a certain domain. Existing models do not fully solve this problem of relation redundancy and noise, as they directly characterize social influence over the full social network. In this paper, we instead propose to improve graph based social recommendation by only retaining the informative social relations to ensure an efficient and effective influence diffusion, i.e., graph denoising. Our designed denoising method is preference-guided to model social relation confidence and benefits user preference learning in return by providing a denoised but more informative social graph for recommendation models. Moreover, to avoid interference of noisy social relations, it designs a self-correcting curriculum learning module and an adaptive denoising strategy, both favoring highly-confident samples. Experimental results on three public datasets demonstrate its consistent capability of improving two state-of-the-art social recommendation models by robustly removing 10-40% of original relations. We release the source code at https://github.com/tsinghua-fib-lab/Graph-Denoising-SocialRec.

cs.IR↗
arXiv2023

Advancements in Federated Learning: Models, Methods, and Privacy

Federated learning (FL) is a promising technique for addressing the rising privacy and security issues. Its main ingredient is to cooperatively learn the model among the distributed clients without uploading any sensitive data. In this paper, we conducted a thorough review of the related works, following the development context and deeply mining the key technologies behind FL from both theoretical and practical perspectives. Specifically, we first classify the existing works in FL architecture based on the network topology of FL systems with detailed analysis and summarization. Next, we abstract the current application problems, summarize the general techniques and frame the application problems into the general paradigm of FL base models. Moreover, we provide our proposed solutions for model training via FL. We have summarized and analyzed the existing FedOpt algorithms, and deeply revealed the algorithmic development principles of many first-order algorithms in depth, proposing a more generalized algorithm design framework. Based on these frameworks, we have instantiated FedOpt algorithms. As privacy and security is the fundamental requirement in FL, we provide the existing attack scenarios and the defense methods. To the best of our knowledge, we are among the first tier to review the theoretical methodology and propose our strategies since there are very few works surveying the theoretical approaches. Our survey targets motivating the development of high-performance, privacy-preserving, and secure methods to integrate FL into real-world applications.

cs.AI↗
arXiv2023

On the Power of Finite Ambiguity in Büchi Complementation

In this work, we exploit the power of \emph{finite ambiguity} for the complementation problem of Büchi automata by using reduced run directed acyclic graphs (DAGs) over infinite words, in which each vertex has at most one predecessor; these reduced run DAGs have only a finite number of infinite runs, thus obtaining the finite ambiguity in Büchi complementation. We show how to use this type of reduced run DAGs as a unified tool to optimize both rank-based and slice-based complementation constructions for Büchi automata with a finite degree of ambiguity. As a result, given a Büchi automaton with $n$ states and a finite degree of ambiguity, the number of states in the complementary Büchi automaton constructed by the classical rank-based and slice-based complementation constructions can be improved from $2^{\mathsf{O}(n \log n)}$ and $\mathsf{O}((3n)^{n})$ to $\mathsf{O}(6^{n}) \subseteq 2^{\mathsf{O}(n)}$ and $\mathsf{O}(4^{n})$, respectively. We further show how to construct such reduced run DAGs for limit deterministic Büchi automata and obtain a specialized complementation algorithm, thus demonstrating the generality of the power of finite ambiguity.

cs.FL↗