arXiv subjects

Lei Chen

Publications and source records attributed to Lei Chen.

At least 325 records · Page 18Linked to original sources

arXiv2024

A Tale of Two Paths: Toward a Hybrid Data Plane for Efficient Far-Memory Applications

With rapid advances in network hardware, far memory has gained a great deal of traction due to its ability to break the memory capacity wall. Existing far memory systems fall into one of two data paths: one that uses the kernel's paging system to transparently access far memory at the page granularity, and a second that bypasses the kernel, fetching data at the object granularity. While it is generally believed that object fetching outperforms paging due to its fine-grained access, it requires significantly more compute resources to run object-level LRU and eviction. We built Atlas, a hybrid data plane enabled by a runtime-kernel co-design that simultaneously enables accesses via these two data paths to provide high efficiency for real-world applications. Atlas uses always-on profiling to continuously measure page locality. For workloads already with good locality, paging is used to fetch data, whereas for those without, object fetching is employed. Object fetching moves objects that are accessed close in time to contiguous local space, dynamically improving locality and making the execution increasingly amenable to paging, which is much more resource-efficient. Our evaluation shows that Atlas improves the throughput (e.g., by 1.5x and 3.2x) and reduces the tail latency (e.g., by one and two orders of magnitude) when using remote memory, compared with AIFM and Fastswap, the state-of-the-art techniques respectively in the two categories.

cs.DC↗

arXiv2024

Are Large Language Models a Good Replacement of Taxonomies?

Large language models (LLMs) demonstrate an impressive ability to internalize knowledge and answer natural language questions. Although previous studies validate that LLMs perform well on general knowledge while presenting poor performance on long-tail nuanced knowledge, the community is still doubtful about whether the traditional knowledge graphs should be replaced by LLMs. In this paper, we ask if the schema of knowledge graph (i.e., taxonomy) is made obsolete by LLMs. Intuitively, LLMs should perform well on common taxonomies and at taxonomy levels that are common to people. Unfortunately, there lacks a comprehensive benchmark that evaluates the LLMs over a wide range of taxonomies from common to specialized domains and at levels from root to leaf so that we can draw a confident conclusion. To narrow the research gap, we constructed a novel taxonomy hierarchical structure discovery benchmark named TaxoGlimpse to evaluate the performance of LLMs over taxonomies. TaxoGlimpse covers ten representative taxonomies from common to specialized domains with in-depth experiments of different levels of entities in this taxonomy from root to leaf. Our comprehensive experiments of eighteen state-of-the-art LLMs under three prompting settings validate that LLMs can still not well capture the knowledge of specialized taxonomies and leaf-level entities.

cs.CL↗

arXiv2024

Learning from Emergence: A Study on Proactively Inhibiting the Monosemantic Neurons of Artificial Neural Networks

Recently, emergence has received widespread attention from the research community along with the success of large-scale models. Different from the literature, we hypothesize a key factor that promotes the performance during the increase of scale: the reduction of monosemantic neurons that can only form one-to-one correlations with specific features. Monosemantic neurons tend to be sparser and have negative impacts on the performance in large models. Inspired by this insight, we propose an intuitive idea to identify monosemantic neurons and inhibit them. However, achieving this goal is a non-trivial task as there is no unified quantitative evaluation metric and simply banning monosemantic neurons does not promote polysemanticity in neural networks. Therefore, we first propose a new metric to measure the monosemanticity of neurons with the guarantee of efficiency for online computation, then introduce a theoretically supported method to suppress monosemantic neurons and proactively promote the ratios of polysemantic neurons in training neural networks. We validate our conjecture that monosemanticity brings about performance change at different model scales on a variety of neural networks and benchmark datasets in different areas, including language, image, and physics simulation tasks. Further experiments validate our analysis and theory regarding the inhibition of monosemanticity.

cs.LG↗

arXiv2024

Confidence interval estimation of mixed oil length with conditional diffusion model

Accurately estimating the mixed oil length plays a big role in the economic benefit for oil pipeline network. While various proposed methods have tried to predict the mixed oil length, they often exhibit an extremely high probability (around 50\%) of underestimating it. This is attributed to their failure to consider the statistical variability inherent in the estimated length of mixed oil. To address such issues, we propose to use the conditional diffusion model to learn the distribution of the mixed oil length given pipeline features. Subsequently, we design a confidence interval estimation for the length of the mixed oil based on the pseudo-samples generated by the learned diffusion model. To our knowledge, we are the first to present an estimation scheme for confidence interval of the oil-mixing length that considers statistical variability, thereby reducing the possibility of underestimating it. When employing the upper bound of the interval as a reference for excluding the mixed oil, the probability of underestimation can be as minimal as 5\%, a substantial reduction compared to 50\%. Furthermore, utilizing the mean of the generated pseudo samples as the estimator for the mixed oil length enhances prediction accuracy by at least 10\% compared to commonly used methods.

stat.AP↗

arXiv2024

The Effectiveness of a Simplified Model Structure for Crowd Counting

In the field of crowd counting research, many recent deep learning based methods have demonstrated robust capabilities for accurately estimating crowd sizes. However, the enhancement in their performance often arises from an increase in the complexity of the model structure. This paper discusses how to construct high-performance crowd counting models using only simple structures. We proposes the Fuss-Free Network (FFNet) that is characterized by its simple and efficieny structure, consisting of only a backbone network and a multi-scale feature fusion structure. The multi-scale feature fusion structure is a simple structure consisting of three branches, each only equipped with a focus transition module, and combines the features from these branches through the concatenation operation. Our proposed crowd counting model is trained and evaluated on four widely used public datasets, and it achieves accuracy that is comparable to that of existing complex models. Furthermore, we conduct a comprehensive evaluation by replacing the existing backbones of various models such as FFNet and CCTrans with different networks, including MobileNet-v3, ConvNeXt-Tiny, and Swin-Transformer-Small. The experimental results further indicate that excellent crowd counting performance can be achieved with the simplied structure proposed by us.

cs.CV↗

arXiv2024

A simple model of global cascades on random hypergraphs

This study introduces a comprehensive framework that situates information cascades within the domain of higher-order interactions, utilizing a double-threshold hypergraph model. We propose that individuals (nodes) gain awareness of information through each communication channel (hyperedge) once the number of information adopters surpasses a threshold $ϕ_m$. However, actual adoption of the information only occurs when the cumulative influence across all communication channels exceeds a second threshold, $ϕ_k$. We analytically derive the cascade condition for both the case of a single seed node using percolation methods and the case of any seed size employing mean-field approximation. Our findings underscore that when considering the fractional seed size, $r_0 \in (0,1]$, the connectivity pattern of the random hypergraph, characterized by the hyperdegree, $k$, and cardinality, $m$, distributions, exerts an asymmetric impact on the global cascade boundary. This asymmetry manifests in the observed differences in the boundaries of the global cascade within the $(ϕ_m, \langle m \rangle)$ and $(ϕ_k, \langle k \rangle)$ planes. However, as $r_0 \to 0$, this asymmetric effect gradually diminishes. Overall, by elucidating the mechanisms driving information cascades within a broader context of higher-order interactions, our research contributes to theoretical advancements in complex systems theory.

physics.soc-ph↗

arXiv2024

Massive Dirac Fermions and Strong Shubnikov-de Haas Oscillations in Topological Insulator Sm,Fe:Bi2Se3 Single Crystals

Topological insulators (TIs) are emergent materials with unique band structure, which allow the study of quantum effect in solids, as well as contribute to high performance quantum devices. To achieve the better performance of TI, here we present a co-doping strategy using synergistic rare-earth Sm and transition-metal Fe dopants in Bi2Se3 single crystals, which combine the advantages of both transition metal doped TI (high ferromagnetic ordering temperature and observed QAHE), and rare-earth doped TI (large magnetic moments and significant spin orbit coupling). In the as-grown single crystals, clear evidences of ferromagnetic ordering were observed. The angle resolve photoemission spectroscopy indicate the ferromagnetism opens a 44 meV band gap at surface Dirac point. Moreover, the carrier mobility at 3 K is ~ 7400 cm2/Vs, and we thus observed an ultra-strong Shubnikov-de Haas oscillation in the longitudinal resistivity, as well as the Hall steps in transverse resistivity below 14 T. Our transport and angular resolved photoemission spectroscopy results suggest that the rare-earth and transition metal co-doping in Bi2Se3 system is a promising avenue implement the quantum anomalous Hall effect, as well as harnessing the massive Dirac fermion in electrical devices.

cond-mat.mtrl-sci↗

arXiv2024

Popularity-Aware Alignment and Contrast for Mitigating Popularity Bias

Collaborative Filtering (CF) typically suffers from the significant challenge of popularity bias due to the uneven distribution of items in real-world datasets. This bias leads to a significant accuracy gap between popular and unpopular items. It not only hinders accurate user preference understanding but also exacerbates the Matthew effect in recommendation systems. To alleviate popularity bias, existing efforts focus on emphasizing unpopular items or separating the correlation between item representations and their popularity. Despite the effectiveness, existing works still face two persistent challenges: (1) how to extract common supervision signals from popular items to improve the unpopular item representations, and (2) how to alleviate the representation separation caused by popularity bias. In this work, we conduct an empirical analysis of popularity bias and propose Popularity-Aware Alignment and Contrast (PAAC) to address two challenges. Specifically, we use the common supervisory signals modeled in popular item representations and propose a novel popularity-aware supervised alignment module to learn unpopular item representations. Additionally, we suggest re-weighting the contrastive learning loss to mitigate the representation separation from a popularity-centric perspective. Finally, we validate the effectiveness and rationale of PAAC in mitigating popularity bias through extensive experiments on three real-world datasets. Our code is available at https://github.com/miaomiao-cai2/KDD2024-PAAC.

cs.IR↗

arXiv2024

Cross-domain-aware Worker Selection with Training for Crowdsourced Annotation

Annotation through crowdsourcing draws incremental attention, which relies on an effective selection scheme given a pool of workers. Existing methods propose to select workers based on their performance on tasks with ground truth, while two important points are missed. 1) The historical performances of workers in other tasks. In real-world scenarios, workers need to solve a new task whose correlation with previous tasks is not well-known before the training, which is called cross-domain. 2) The dynamic worker performance as workers will learn from the ground truth. In this paper, we consider both factors in designing an allocation scheme named cross-domain-aware worker selection with training approach. Our approach proposes two estimation modules to both statistically analyze the cross-domain correlation and simulate the learning gain of workers dynamically. A framework with a theoretical analysis of the worker elimination process is given. To validate the effectiveness of our methods, we collect two novel real-world datasets and generate synthetic datasets. The experiment results show that our method outperforms the baselines on both real-world and synthetic datasets.

cs.LG↗

arXiv2024

Symmetry constraints and spectral crossing in a Mott insulator with Green's function zeros

Lattice symmetries are central to the characterization of electronic topology. Recently, it was shown that Green's function eigenvectors form a representation of the space group. This formulation has allowed the identification of gapless topological states even when quasiparticles are absent. Here we demonstrate the profundity of the framework in the extreme case, when interactions lead to a Mott insulator, through a solvable model with long-range interactions. We find that both Mott poles and zeros are subject to the symmetry constraints, and relate the symmetry-enforced spectral crossings to degeneracies of the original non-interacting eigenstates. Our results lead to new understandings of topological quantum materials and highlight the utility of interacting Green's functions toward their symmetry-based design.

cond-mat.str-el↗

arXiv2024

Logic Synthesis with Generative Deep Neural Networks

While deep learning has achieved significant success in various domains, its application to logic circuit design has been limited due to complex constraints and strict feasibility requirement. However, a recent generative deep neural model, "Circuit Transformer", has shown promise in this area by enabling equivalence-preserving circuit transformation on a small scale. In this paper, we introduce a logic synthesis rewriting operator based on the Circuit Transformer model, named "ctrw" (Circuit Transformer Rewriting), which incorporates the following techniques: (1) a two-stage training scheme for the Circuit Transformer tailored for logic synthesis, with iterative improvement of optimality through self-improvement training; (2) integration of the Circuit Transformer with state-of-the-art rewriting techniques to address scalability issues, allowing for guided DAG-aware rewriting. Experimental results on the IWLS 2023 contest benchmark demonstrate the effectiveness of our proposed rewriting methods.

cs.LO↗

arXiv2024

SpanGNN: Towards Memory-Efficient Graph Neural Networks via Spanning Subgraph Training

Graph Neural Networks (GNNs) have superior capability in learning graph data. Full-graph GNN training generally has high accuracy, however, it suffers from large peak memory usage and encounters the Out-of-Memory problem when handling large graphs. To address this memory problem, a popular solution is mini-batch GNN training. However, mini-batch GNN training increases the training variance and sacrifices the model accuracy. In this paper, we propose a new memory-efficient GNN training method using spanning subgraph, called SpanGNN. SpanGNN trains GNN models over a sequence of spanning subgraphs, which are constructed from empty structure. To overcome the excessive peak memory consumption problem, SpanGNN selects a set of edges from the original graph to incrementally update the spanning subgraph between every epoch. To ensure the model accuracy, we introduce two types of edge sampling strategies (i.e., variance-reduced and noise-reduced), and help SpanGNN select high-quality edges for the GNN learning. We conduct experiments with SpanGNN on widely used datasets, demonstrating SpanGNN's advantages in the model performance and low peak memory usage.

cs.LG↗

arXiv2024

Wide-bandgap semiconductor of three-dimensional unconventional stoichiometric NaCl2 crystal

The expanding applications call for novel new-generation wide-bandgap semiconductors. Here, we show that a compound only composed of the ordinary elements Na and Cl, namely three-dimensional NaCl2 crystal, is a wide-bandgap semiconductor. This finding benefits from the breaking of conventional stoichiometry frameworks in the theoretical design, leading to the discovery of three-dimensional XY2 (X = Na, Li, K; Y = Cl, F, Br, I) crystals, with covalent bonds of Y pairs inducing the wide bandgap from 2.24 to 4.45 eV. Crucially, such an unexpected NaCl2 crystal was successfully synthesized under ambient conditions. The unconventional stoichiometric strategy with other chemical elements potentially yields more wide-bandgap semiconductors, offering the capability for bandgap tuning. These unconventional stoichiometric materials may also exhibit superconductivity, transparent inorganic electrides, high-energy-density, and beyond.

cond-mat.mtrl-sci↗

arXiv2024

KGLink: A column type annotation method that combines knowledge graph and pre-trained language model

The semantic annotation of tabular data plays a crucial role in various downstream tasks. Previous research has proposed knowledge graph (KG)-based and deep learning-based methods, each with its inherent limitations. KG-based methods encounter difficulties annotating columns when there is no match for column cells in the KG. Moreover, KG-based methods can provide multiple predictions for one column, making it challenging to determine the semantic type with the most suitable granularity for the dataset. This type granularity issue limits their scalability. On the other hand, deep learning-based methods face challenges related to the valuable context missing issue. This occurs when the information within the table is insufficient for determining the correct column type. This paper presents KGLink, a method that combines WikiData KG information with a pre-trained deep learning language model for table column annotation, effectively addressing both type granularity and valuable context missing issues. Through comprehensive experiments on widely used tabular datasets encompassing numeric and string columns with varying type granularity, we showcase the effectiveness and efficiency of KGLink. By leveraging the strengths of KGLink, we successfully surmount challenges related to type granularity and valuable context issues, establishing it as a robust solution for the semantic annotation of tabular data.

cs.LG↗

arXiv2024

Emergent flat band and topological Kondo semimetal driven by orbital-selective correlations

Flat electronic bands are expected to show proportionally enhanced electron correlations, which may generate a plethora of novel quantum phases and unusual low-energy excitations. They are increasingly being pursued in $d$-electron-based systems with crystalline lattices that feature destructive electronic interference, where they are often topological. Such flat bands, though, are generically located far away from the Fermi energy, which limits their capacity to partake in the low-energy physics. Here we show that electron correlations produce emergent flat bands that are pinned to the Fermi energy. We demonstrate this effect within a Hubbard model, in the regime described by Wannier orbitals where an effective Kondo description arises through orbital-selective Mott correlations. Moreover, the correlation effect cooperates with symmetry constraints to produce a topological Kondo semimetal. Our results motivate a novel design principle for Weyl Kondo semimetals in a new setting, viz. $d$-electron-based materials on suitable crystal lattices, and uncover interconnections among seemingly disparate systems that may inspire fresh understandings and realizations of correlated topological effects in quantum materials and beyond.

cond-mat.str-el↗

arXiv2024

UniCL: A Universal Contrastive Learning Framework for Large Time Series Models

Time-series analysis plays a pivotal role across a range of critical applications, from finance to healthcare, which involves various tasks, such as forecasting and classification. To handle the inherent complexities of time-series data, such as high dimensionality and noise, traditional supervised learning methods first annotate extensive labels for time-series data in each task, which is very costly and impractical in real-world applications. In contrast, pre-trained foundation models offer a promising alternative by leveraging unlabeled data to capture general time series patterns, which can then be fine-tuned for specific tasks. However, existing approaches to pre-training such models typically suffer from high-bias and low-generality issues due to the use of predefined and rigid augmentation operations and domain-specific data training. To overcome these limitations, this paper introduces UniCL, a universal and scalable contrastive learning framework designed for pretraining time-series foundation models across cross-domain datasets. Specifically, we propose a unified and trainable time-series augmentation operation to generate pattern-preserved, diverse, and low-bias time-series data by leveraging spectral information. Besides, we introduce a scalable augmentation algorithm capable of handling datasets with varying lengths, facilitating cross-domain pretraining. Extensive experiments on two benchmark datasets across eleven domains validate the effectiveness of UniCL, demonstrating its high generalization on time-series analysis across various fields.

cs.LG↗

arXiv2024

How Good Are Multi-dimensional Learned Indices? An Experimental Survey

Efficient indexing is fundamental for multi-dimensional data management and analytics. An emerging tendency is to directly learn the storage layout of multi-dimensional data by simple machine learning models, yielding the concept of Learned Index. Compared with the conventional indices used for decades (e.g., kd-tree and R-tree variants), learned indices are empirically shown to be both space- and time-efficient on modern architectures. However, there lacks a comprehensive evaluation of existing multi-dimensional learned indices under a unified benchmark, which makes it difficult to decide the suitable index for specific data and queries and further prevents the deployment of learned indices in real application scenarios. In this paper, we present the first in-depth empirical study to answer the question of how good multi-dimensional learned indices are. Six recently published indices are evaluated under a unified experimental configuration including index implementation, datasets, query workloads, and evaluation metrics. We thoroughly investigate the evaluation results and discuss the findings that may provide insights for future learned index design.

cs.DB↗

arXiv2024

The Dawn of AI-Native EDA: Opportunities and Challenges of Large Circuit Models

Within the Electronic Design Automation (EDA) domain, AI-driven solutions have emerged as formidable tools, yet they typically augment rather than redefine existing methodologies. These solutions often repurpose deep learning models from other domains, such as vision, text, and graph analytics, applying them to circuit design without tailoring to the unique complexities of electronic circuits. Such an AI4EDA approach falls short of achieving a holistic design synthesis and understanding, overlooking the intricate interplay of electrical, logical, and physical facets of circuit data. This paper argues for a paradigm shift from AI4EDA towards AI-native EDA, integrating AI at the core of the design process. Pivotal to this vision is the development of a multimodal circuit representation learning technique, poised to provide a comprehensive understanding by harmonizing and extracting insights from varied data sources, such as functional specifications, RTL designs, circuit netlists, and physical layouts. We champion the creation of large circuit models (LCMs) that are inherently multimodal, crafted to decode and express the rich semantics and structures of circuit data, thus fostering more resilient, efficient, and inventive design methodologies. Embracing this AI-native philosophy, we foresee a trajectory that transcends the current innovation plateau in EDA, igniting a profound shift-left in electronic design methodology. The envisioned advancements herald not just an evolution of existing EDA tools but a revolution, giving rise to novel instruments of design tools that promise to radically enhance design productivity and inaugurate a new epoch where the optimization of circuit performance, power, and area (PPA) is achieved not incrementally, but through leaps that redefine the benchmarks of electronic systems' capabilities.

cs.AR↗