arXiv subjects

Junfeng Liu

Publications and source records attributed to Junfeng Liu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Aster: Enhancing LSM-structures for Scalable Graph Database

There is a proliferation of applications requiring the management of large-scale, evolving graphs under workloads with intensive graph updates and lookups. Driven by this challenge, we introduce Poly-LSM, a high-performance key-value storage engine for graphs with the following novel techniques: (1) Poly-LSM is embedded with a new design of graph-oriented LSM-tree structure that features a hybrid storage model for concisely and effectively storing graph data. (2) Poly-LSM utilizes an adaptive mechanism to handle edge insertions and deletions on graphs with optimized I/O efficiency. (3) Poly-LSM exploits the skewness of graph data to encode the key-value entries. Building upon this foundation, we further implement Aster, a robust and versatile graph database that supports Gremlin query language facilitating various graph applications. In our experiments, we compared Aster against several mainstream real-world graph databases. The results demonstrate that Aster outperforms all baseline graph databases, especially on large-scale graphs. Notably, on the billion-scale Twitter graph dataset, Aster achieves up to 17x throughput improvement compared to the best-performing baseline graph system.

cs.DB↗

arXiv2024

OpenLS-DGF: An Adaptive Open-Source Dataset Generation Framework for Machine Learning Tasks in Logic Synthesis

This paper introduces OpenLS-DGF, an adaptive logic synthesis dataset generation framework, to enhance machine learning~(ML) applications within the logic synthesis process. Previous dataset generation flows were tailored for specific tasks or lacked integrated machine learning capabilities. While OpenLS-DGF supports various machine learning tasks by encapsulating the three fundamental steps of logic synthesis: Boolean representation, logic optimization, and technology mapping. It preserves the original information in both Verilog and machine-learning-friendly GraphML formats. The verilog files offer semi-customizable capabilities, enabling researchers to insert additional steps and incrementally refine the generated dataset. Furthermore, OpenLS-DGF includes an adaptive circuit engine that facilitates the final dataset management and downstream tasks. The generated OpenLS-D-v1 dataset comprises 46 combinational designs from established benchmarks, totaling over 966,000 Boolean circuits. OpenLS-D-v1 supports integrating new data features, making it more versatile for new challenges. This paper demonstrates the versatility of OpenLS-D-v1 through four distinct downstream tasks: circuit classification, circuit ranking, quality of results (QoR) prediction, and probability prediction. Each task is chosen to represent essential steps of logic synthesis, and the experimental results show the generated dataset from OpenLS-DGF achieves prominent diversity and applicability. The source code and datasets are available at https://github.com/Logic-Factory/ACE/blob/master/OpenLS-DGF/readme.md.

cs.AI↗

arXiv2024

Generalization Gap in Data Augmentation: Insights from Illumination

In the field of computer vision, data augmentation is widely used to enrich the feature complexity of training datasets with deep learning techniques. However, regarding the generalization capabilities of models, the difference in artificial features generated by data augmentation and natural visual features has not been fully revealed. This study introduces the concept of "visual representation variables" to define the possible visual variations in a task as a joint distribution of these variables. We focus on the visual representation variable "illumination", by simulating its distribution degradation and examining how data augmentation techniques enhance model performance on a classification task. Our goal is to investigate the differences in generalization between models trained with augmented data and those trained under real-world illumination conditions. Results indicate that after applying various data augmentation methods, model performance has significantly improved. Yet, a noticeable generalization gap still exists after utilizing various data augmentation methods, emphasizing the critical role of feature diversity in the training set for enhancing model generalization.

cs.CV↗

arXiv2024

Non-perturbative dynamics of flat-band systems with correlated disorder

We develop a numerical method for the time evolution of Gaussian wave packets on flat-band lattices in the presence of correlated disorder. To achieve this, we introduce a method to generate random on-site energies with prescribed correlations. We verify this method with a one-dimensional (1D) cross-stitch model, and find good agreement with analytical results obtained from the disorder-dressed evolution equations. This allows us to reproduce previous findings, that disorder can mobilize 1D flat-band states which would otherwise remain localized. As explained by the corresponding disorder-dressed evolution equations, such mobilization requires an asymmetric disorder-induced coupling to dispersive bands, a condition that is generically not fulfilled when the flat-band is resonant with the dispersive bands at a Dirac point-like crossing. We exemplify this with the 1D Lieb lattice. While analytical expressions are not available for the two-dimensional (2D) system due to its complexity, we extend the numerical method to the 2D $α-T_3$ model, and find that the initial flat-band wave packet preserves its localization when $α= 0$, regardless of disorder and intersections. However, when $α\neq 0$, the wave packet shifts in real space. We interpret this as a Berry phase controlled, disorder-induced wave-packet mobilization. In addition, we present density functional theory calculations of candidate materials, specifically $\rm Hg_{1-x}Cd_xTe$. The flat-band emerges near the $Γ$ point ($\bf{k}=$0) in the Brillouin zone.

cond-mat.dis-nn↗

arXiv2024

Parallel AIG Refactoring via Conflict Breaking

Algorithm parallelization to leverage multi-core platforms for improving the efficiency of Electronic Design Automation~(EDA) tools plays a significant role in enhancing the scalability of Integrated Circuit (IC) designs. Logic optimization is a key process in the EDA design flow to reduce the area and depth of the circuit graph by finding logically equivalent graphs for substitution, which is typically time-consuming. To address these challenges, in this paper, we first analyze two types of conflicts that need to be handled in the parallelization framework of refactoring And-Inverter Graph~(AIG). We then present a fine-grained parallel AIG refactoring method, which strikes a balance between the degree of parallelism and the conflicts encountered during the refactoring operations. Experiment results show that our parallel refactor is 28x averagely faster than the sequential algorithm on large benchmark tests with 64 physical CPU cores, and has comparable optimization quality.

cs.DC↗

arXiv2024

Word Order's Impacts: Insights from Reordering and Generation Analysis

Existing works have studied the impacts of the order of words within natural text. They usually analyze it by destroying the original order of words to create a scrambled sequence, and then comparing the models' performance between the original and scrambled sequences. The experimental results demonstrate marginal drops. Considering this findings, different hypothesis about word order is proposed, including ``the order of words is redundant with lexical semantics'', and ``models do not rely on word order''. In this paper, we revisit the aforementioned hypotheses by adding a order reconstruction perspective, and selecting datasets of different spectrum. Specifically, we first select four different datasets, and then design order reconstruction and continuing generation tasks. Empirical findings support that ChatGPT relies on word order to infer, but cannot support or negate the redundancy relations between word order lexical semantics.

cs.CL↗

arXiv2024

On Invariant subspace for hyponormal operators

There is a resent paper claiming that every hyponormal operator which is not a multiple of the identity (operator) has a nontrivial hyperinvariant subspace. If this claim is true, then every hyponormal operator has a nontrivial invariant subspace, and every subnormal operator which is not multiple of the identity has a nontrivial hyperinvariant subspace. But we find out that the proof of the above claim go wrong. Therefore the invariant subspace problem of the hyponormal operator and the hyperinvariant problem of subnormal operator remains unresolved. Moreover, it is well known that these are two important research topics in operator theory that have not been solved for a long time, and that a lot of people have been trying to solved the two problems. So it is very meaningful to clarify whether these two problems have been solved.

math.FA↗

arXiv2023

Adaptive Reconvergence-driven AIG Rewriting via Strategy Learning

Rewriting is a common procedure in logic synthesis aimed at improving the performance, power, and area (PPA) of circuits. The traditional reconvergence-driven And-Inverter Graph (AIG) rewriting method focuses solely on optimizing the reconvergence cone through Boolean algebra minimization. However, there exist opportunities to incorporate other node-rewriting algorithms that are better suited for specific cones. In this paper, we propose an adaptive reconvergence-driven AIG rewriting algorithm that combines two key techniques: multi-strategy-based AIG rewriting and strategy learning-based algorithm selection. The multi-strategy-based rewriting method expands upon the traditional approach by incorporating support for multi-node-rewriting algorithms, thus expanding the optimization space. Additionally, the strategy learning-based algorithm selection method determines the most suitable node-rewriting algorithm for a given cone. Experimental results demonstrate that our proposed method yields a significant average improvement of 5.567\% in size and 5.327\% in depth.

cs.AI↗

arXiv2023

Context Retrieval via Normalized Contextual Latent Interaction for Conversational Agent

Conversational agents leveraging AI, particularly deep learning, are emerging in both academic research and real-world applications. However, these applications still face challenges, including disrespecting knowledge and facts, not personalizing to user preferences, and enormous demand for computational resources during training and inference. Recent research efforts have been focused on addressing these challenges from various aspects, including supplementing various types of auxiliary information to the conversational agents. However, existing methods are still not able to effectively and efficiently exploit relevant information from these auxiliary supplements to further unleash the power of the conversational agents and the language models they use. In this paper, we present a novel method, PK-NCLI, that is able to accurately and efficiently identify relevant auxiliary information to improve the quality of conversational responses by learning the relevance among persona, chat history, and knowledge background through low-level normalized contextual latent interaction. Our experimental results indicate that PK-NCLI outperforms the state-of-the-art method, PK-FoCus, by 47.80%/30.61%/24.14% in terms of perplexity, knowledge grounding, and training efficiency, respectively, and maintained the same level of persona grounding performance. We also provide a detailed analysis of how different factors, including language model choices and trade-offs on training weights, would affect the performance of PK-NCLI.

cs.CL↗

arXiv2023

Persona-Coded Poly-Encoder: Persona-Guided Multi-Stream Conversational Sentence Scoring

Recent advances in machine learning and deep learning have led to the widespread use of Conversational AI in many practical applications. However, it is still very challenging to leverage auxiliary information that can provide conversational context or personalized tuning to improve the quality of conversations. For example, there has only been limited research on using an individuals persona information to improve conversation quality, and even state-of-the-art conversational AI techniques are unable to effectively leverage signals from heterogeneous sources of auxiliary data, such as multi-modal interaction data, demographics, SDOH data, etc. In this paper, we present a novel Persona-Coded Poly-Encoder method that leverages persona information in a multi-stream encoding scheme to improve the quality of response generation for conversations. To show the efficacy of the proposed method, we evaluate our method on two different persona-based conversational datasets, and compared against two state-of-the-art methods. Our experimental results and analysis demonstrate that our method can improve conversation quality over the baseline method Poly-Encoder by 3.32% and 2.94% in terms of BLEU score and HR@1, respectively. More significantly, our method offers a path to better utilization of multi-modal data in conversational tasks. Lastly, our study outlines several challenges and future research directions for advancing personalized conversational AI technology.

cs.CL↗

arXiv2023

MATA: Combining Learnable Node Matching with A Algorithm for Approximate Graph Edit Distance Computation

Graph Edit Distance (GED) is a general and domain-agnostic metric to measure graph similarity, widely used in graph search or retrieving tasks. However, the exact GED computation is known to be NP-complete. For instance, the widely used A* algorithms explore the entire search space to find the optimal solution which inevitably suffers scalability issues. Learning-based methods apply graph representation techniques to learn the GED by formulating a regression task, which can not recover the edit path and lead to inaccurate GED approximation (i.e., the predicted GED is smaller than the exact). To this end, in this work, we present a data-driven hybrid approach MATA* for approximate GED computation based on Graph Neural Networks (GNNs) and A* algorithms, which models from the perspective of learning to match nodes instead of directly regressing GED. Specifically, aware of the structure-dominant operations (i.e.,node and edge insertion/deletion) property in GED computation, a structure-enhanced GNN is firstly designed to jointly learn local and high-order structural information for node embeddings for node matchings. Second, top-k candidate nodes are produced via a differentiable top-k operation to enable the training for node matchings, which is adhering to another property of GED, i.e., multiple optimal node matchings. Third, benefiting from the candidate nodes, MATA* only performs on the promising search directions, reaching the solution efficiently. Finally, extensive experiments show the superiority of MATA* as it significantly outperforms the combinatorial search-based, learning-based and hybrid methods and scales well to large-size graphs.

cs.LG↗

arXiv2023

Do as You Say: Consistency Detection of Data Practice in Program Code and Privacy Policy in Mini-App

Mini-app is an emerging form of mobile application that combines web technology with native capabilities. Its features, e.g., no need to download and no installation, have made it popular rapidly. However, privacy issues that violate the laws or regulations are breeding in the swiftly expanding mini-app ecosystem. The consistency between what the mini-app does about the data in the program code and what it declares in its privacy policy description is important. But no work has systematically investigated the privacy problem of the mini-app before. In this paper, to our best knowledge, we are the first to conduct the compliance detection of data practice and policy description in mini-apps. In this paper, we first customize a taint analysis method based on data entity dependency network to adapt to the characteristics of the JavaScript language in the mini-apps. Then, we transform data types and data operations to data practices in program codes and privacy policies, so as to finish a fine-grained consistency matching model.We crawl 100,000 mini-apps on WeChat client in the wild and extract 2,998 with a privacy policy. Among them, only 318 meet the consistency requirements, 2,680 are inconsistent, and the proportion of inconsistencies is as high as 89.4%. The inconsistency in the mini-app is very serious. Based on 6 real-world cases analyzed, in order to reduce this potential data leakage risk, we suggest that the developer should reduce the collection of irrelevant information and the straightforward use of templates, and the platform should provide data flow detection tools and privacy policy writing support.

cs.CR↗

arXiv2022

Persona-Based Conversational AI: State of the Art and Challenges

Conversational AI has become an increasingly prominent and practical application of machine learning. However, existing conversational AI techniques still suffer from various limitations. One such limitation is a lack of well-developed methods for incorporating auxiliary information that could help a model understand conversational context better. In this paper, we explore how persona-based information could help improve the quality of response generation in conversations. First, we provide a literature review focusing on the current state-of-the-art methods that utilize persona information. We evaluate two strong baseline methods, the Ranking Profile Memory Network and the Poly-Encoder, on the NeurIPS ConvAI2 benchmark dataset. Our analysis elucidates the importance of incorporating persona information into conversational systems. Additionally, our study highlights several limitations with current state-of-the-art methods and outlines challenges and future research directions for advancing personalized conversational AI technology.

cs.CL↗

arXiv2022

The Beurling-type theorem in the Bergman space $A^2_α(D)$ for any $-1<α<+\infty$

In this paper, we use a new method to solve a long-standing problem. More specifically, we show that the Beurling-type theorem holds in the Bergman space $A^2_α(D)$ for any $-1<α< +\infty$. That is, every invariant subspace $H$ for the shift operator $S$ on $A^2_α(D)$ $(-1<α< +\infty)$ has the property $H=[H\ominus zH]_{S,A^2_α\left(D\right)}$.

math.FA↗

arXiv2022

Contextualized Scene Imagination for Generative Commonsense Reasoning

Humans use natural language to compose common concepts from their environment into plausible, day-to-day scene descriptions. However, such generative commonsense reasoning (GCSR) skills are lacking in state-of-the-art text generation methods. Descriptive sentences about arbitrary concepts generated by neural text generation models (e.g., pre-trained text-to-text Transformers) are often grammatically fluent but may not correspond to human common sense, largely due to their lack of mechanisms to capture concept relations, to identify implicit concepts, and to perform generalizable reasoning about unseen concept compositions. In this paper, we propose an Imagine-and-Verbalize (I&V) method, which learns to imagine a relational scene knowledge graph (SKG) with relations between the input concepts, and leverage the SKG as a constraint when generating a plausible scene description. We collect and harmonize a set of knowledge resources from different domains and modalities, providing a rich auxiliary supervision signal for I&V. The experiments demonstrate the effectiveness of I&V in improving language models on both concept-to-sentence and concept-to-story generation tasks, while enabling the model to learn well from fewer task examples and generate SKGs that make common sense to human annotators.

cs.CL↗

arXiv2022

Generalized space-time fractional stochastic kinetic equation

In this paper, we study a class of nonlinear space-time fractional stochastic kinetic equations in $\mathbb{R}^d$ with Gaussian noise which is white in time and homogeneous in space. This type of equation constitutes an extension of the non-linear stochastic heat equation involving fractional derivative in time and fractional Laplacian in space. We give a necessary condition on the spatial covariance for the existence and uniqueness of the solution. We also study various properties of the solution: path regularity, the behavior of second moment and the stationarity in the case of linear additive noise.

math.PR↗

arXiv2021

Empirical Quantitative Analysis of COVID-19 Forecasting Models

COVID-19 has been a public health emergency of international concern since early 2020. Reliable forecasting is critical to diminish the impact of this disease. To date, a large number of different forecasting models have been proposed, mainly including statistical models, compartmental models, and deep learning models. However, due to various uncertain factors across different regions such as economics and government policy, no forecasting model appears to be the best for all scenarios. In this paper, we perform quantitative analysis of COVID-19 forecasting of confirmed cases and deaths across different regions in the United States with different forecasting horizons, and evaluate the relative impacts of the following three dimensions on the predictive performance (improvement and variation) through different evaluation metrics: model selection, hyperparameter tuning, and the length of time series required for training. We find that if a dimension brings about higher performance gains, if not well-tuned, it may also lead to harsher performance penalties. Furthermore, model selection is the dominant factor in determining the predictive performance. It is responsible for both the largest improvement and the largest variation in performance in all prediction tasks across different regions. While practitioners may perform more complicated time series analysis in practice, they should be able to achieve reasonable results if they have adequate insight into key decisions like model selection.

cs.LG↗

arXiv2021

Intersecting Surface defects and 3d Superconformal indices

We compute the 3d N = 2 superconformal indices for 3d/1d coupled systems, which arise as the worldvolume theories of intersecting surface defects engineered by Higgsing 5d N = 1 gauge theories. We generalize some known 3d dualities, including non-Abelian 3d mirror symmetry and 3d/3d correspondence, to some of the simple 3d/1d coupled systems. Finally we propose a q-Virasoro construction for the superconformal indices.

hep-th↗