arXiv subjects
Publications and source records attributed to Jie Han.
We show that for $ η>0 $ and sufficiently large $ n $, every 5-graph on $ n $ vertices with $δ_{2}(H)\ge (91/216+η)\binom{n}{3}$ contains a Hamilton 2-cycle. This minimum 2-degree condition is asymptotically best possible. Moreover, we give some related results on Hamilton $ \ell $-cycles with $ d $-degree for $\ell\le d \le k-1$ and $1\le \ell < k/2$.
Foundational models have emerged as powerful tools for addressing various tasks in clinical settings. However, their potential development to breast ultrasound analysis remains untapped. In this paper, we present BUSGen, the first foundational generative model specifically designed for breast ultrasound image analysis. Pretrained on over 3.5 million breast ultrasound images, BUSGen has acquired extensive knowledge of breast structures, pathological features, and clinical variations. With few-shot adaptation, BUSGen can generate repositories of realistic and informative task-specific data, facilitating the development of models for a wide range of downstream tasks. Extensive experiments highlight BUSGen's exceptional adaptability, significantly exceeding real-data-trained foundational models in breast cancer screening, diagnosis, and prognosis. In breast cancer early diagnosis, our approach outperformed all board-certified radiologists (n=9), achieving an average sensitivity improvement of 16.5% (P-value<0.0001). Additionally, we characterized the scaling effect of using generated data which was as effective as the collected real-world data for training diagnostic models. Moreover, extensive experiments demonstrated that our approach improved the generalization ability of downstream models. Importantly, BUSGen protected patient privacy by enabling fully de-identified data sharing, making progress forward in secure medical data utilization. An online demo of BUSGen is available at https://aibus.bio.
An $n$-vertex $k$-uniform hypergraph $G$ is $(d,α)$-degenerate if $m_1(G)\le{d}$ and there exists a constant $\varepsilon >0$ such that for every subset $U\subseteq{V(G)}$ with size $2\le|U|\le{\varepsilon n}$, we have $e\left(G[U]\right)\le{d\left(|U|-1\right)-α}$. These hypergraphs include many natural graph classes, such as the degenerate hypergraphs, the planar graphs, and the power of cycles. In this paper, we consider the threshold of the emergence of a $(d,α)$-degenerate hypergraph with bounded maximum degree in the Erdős-Rényi model. We show that its threshold is at most $n^{-1/d}$, improving previous results of Riordan and Kelly-Müyesser-Pokrovskiy.
Ramsey--Turán theory considers Turán type questions in Ramsey-context, asking for the existence of a small subgraph in a graph $G$ where the complement $\overline{G}$ lacks an appropriate subgraph $F$, such as a clique of linear size. Similarly, one can consider Dirac-type questions in Ramsey context, asking for the existence of a spanning subgraph $H$ in a graph $G$ where the complement $\overline{G}$ lacks an appropriate subgraph $F$, which we call a Ramsey--Dirac theory question. When $H$ is a connected spanning subgraph, the disjoint union $K_{n/2}\cup K_{n/2}$ of two large cliques shows that it is natural to consider complete bipartite graphs $F$. Indeed, Han, Hu, Ping, Wang, Wang and Yang in 2024 proved that if $G$ is an $n$-vertex graph with $δ(G)=Ω(n)$ where the complement $\overline{G}$ does not contain any complete bipartite graph $K_{m,m}$ with $m=Ω(n)$, then $G$ contains every $n$-vertex bounded degree tree $T$ as a subgraph. Extending this result to the Ramsey--Dirac theory for hypertrees, we prove that if $G$ is an $n$-vertex $r$-uniform hypergraph with $δ(G)=Ω(n^{r-1})$ where the complement $\overline{G}$ does not contain any complete $r$-partite hypergraph $K_{m,m,\dots, m}$ with $m=Ω(n)$, then $G$ contains every $n$-vertex bounded degree hypertree $T$ as a subgraph. We also prove the existence of matchings and loose Hamilton cycles in the same setting, which extends the result of Mcdiarmid and Yolov into hypergraphs. This result generalizes the universality result on randomly perturbed graphs by Böttcher, Han, Kohayakawa, Montgomery, Parczyk and Person in 2019 into hypergraphs and also strengthen the results on quasirandom hypergraphs by Lenz, Mubayi and Mycroft in 2016 and Lenz and Mubayi in 2016 into hypergraphs satisfying a much weaker pseudorandomness condition.
We show that every $(n,d,λ)$-graph contains a Hamilton cycle for sufficiently large $n$, assuming that $d\geq \log^{6}n$ and $λ\leq cd$, where $c=\frac{1}{70000}$. This significantly improves a recent result of Glock, Correia and Sudakov, who obtained a similar result for $d$ that grows polynomially with $n$. The proof is based on a new result regarding the second largest eigenvalue of the adjacency matrix of a subgraph induced by a random subset of vertices, combined with a recent result on connecting designated pairs of vertices by vertex-disjoint paths in $(n,d,λ)$-graphs. We believe that the former result is of independent interest and will have further applications.
Given a family of graphs $G_1,\dots,G_{n}$ on the same vertex set $[n]$, a rainbow Hamilton cycle is a Hamilton cycle on $[n]$ such that each $G_c$ contributes exactly one edge. We prove that if $G_1,\dots,G_{n}$ are independent samples of $G(n,p)$ on the same vertex set $[n]$, then for each $\varepsilon>0$, whp, every collection of spanning subgraphs $H_c\subseteq G_c$, with $δ(H_c)\geq(\frac{1}{2}+\varepsilon)np$, admits a rainbow Hamilton cycle. A similar result is proved for rainbow perfect matchings in a family of $n/2$ graphs on the same vertex set $[n]$.
Large recommendation models (LRMs) are fundamental to the multi-billion dollar online advertising industry, processing massive datasets of hundreds of billions of examples before transitioning to continuous online training to adapt to rapidly changing user behavior. The massive scale of data directly impacts both computational costs and the speed at which new methods can be evaluated (R&D velocity). This paper presents actionable principles and high-level frameworks to guide practitioners in optimizing training data requirements. These strategies have been successfully deployed in Google's largest Ads CTR prediction models and are broadly applicable beyond LRMs. We outline the concept of data convergence, describe methods to accelerate this convergence, and finally, detail how to optimally balance training data volume with model size.
As a potential alternative for implementing the large number of multiplications in convolutional neural networks (CNNs), approximate multipliers (AMs) promise both high hardware efficiency and accuracy. However, the characterization of accuracy and design of appropriate AMs are critical to an AM-based CNN (AM-CNN). In this work, the generation and propagation of errors in an AM-CNN are analyzed by considering the CNN architecture. Based on this analysis, a novel AM error metric is proposed to evaluate the accuracy degradation of an AM-CNN, denoted as the architectural mean error (AME). The effectiveness of the AME is assessed in VGG and ResNet on CIFAR-10, CIFAR-100, and ImageNet datasets. Experimental results show that AME exhibits a strong correlation with the accuracy of AM-CNNs, outperforming the other AM error metrics. To predict the accuracy of AM-CNNs, quadratic regression models are constructed based on the AME; the predictions show an average of 3% deviation from the ground-truth values. Compared with a GPU-based simulation, the AME-based prediction is about $10^{6}\times$ faster.
Resolving a recent problem of Bell, Frieze, and Marbach, we establish both the threshold result of Frankston--Kahn--Narayanan--Park, and its strengthening by Spiro, in the rainbow setting. This has applications to the thresholds for rainbow structures in random graphs where each edge is given a uniformly random color from a set of given colors.
The conventional Cohen's distribution can't meet the requirement of additive noises jamming signals high-performance denoising under the condition of low signal-to-noise ratio, it is necessary to integrate the metaplectic transform for non-stationary signal fractional domain time-frequency analysis. In this paper, we blend time-frequency operators and coordinate operator fractionizations to formulate the definition of the metaplectic Wigner distribution, based on which we integrate the generalized metaplectic convolution to address the unified representation issue of the convolution type of metaplectic Cohen's distribution (CMCD), whose special cases and essential properties are also derived. We blend Wiener filter principle and fractional domain filter mechanism of the metaplectic transform to design the least-squares adaptive filter method in the metaplectic Wigner distribution domain, giving birth to the least-squares adaptive filter-based CMCD whose kernel function can be adjusted with the input signal automatically to achieve the minimum mean-square error (MSE) denoising in Wigner distribution domain. We discuss the optimal symplectic matrices selection strategy of the proposed adaptive CMCD through the minimum MSE minimization modeling and solving. Some examples are also carried out to demonstrate that the proposed filtering method outperforms some state-of-the-arts including Wiener filter and fixed kernel functions-based or adaptive Cohen's distribution in noise suppression.
Data-driven deep learning models have shown great capabilities to assist radiologists in breast ultrasound (US) diagnoses. However, their effectiveness is limited by the long-tail distribution of training data, which leads to inaccuracies in rare cases. In this study, we address a long-standing challenge of improving the diagnostic model performance on rare cases using long-tailed data. Specifically, we introduce a pipeline, TAILOR, that builds a knowledge-driven generative model to produce tailored synthetic data. The generative model, using 3,749 lesions as source data, can generate millions of breast-US images, especially for error-prone rare cases. The generated data can be further used to build a diagnostic model for accurate and interpretable diagnoses. In the prospective external evaluation, our diagnostic model outperforms the average performance of nine radiologists by 33.5% in specificity with the same sensitivity, improving their performance by providing predictions with an interpretable decision-making process. Moreover, on ductal carcinoma in situ (DCIS), our diagnostic model outperforms all radiologists by a large margin, with only 34 DCIS lesions in the source data. We believe that TAILOR can potentially be extended to various diseases and imaging modalities.
Many multi-dimensional (M-D) graph signals appear in the real world, such as digital images, sensor network measurements and temperature records from weather observation stations. It is a key challenge to design a transform method for processing these graph M-D signals in the linear canonical transform domain. This paper proposes the two-dimensional graph linear canonical transform based on the central discrete dilated Hermite function (2-D CDDHFs-GLCT) and the two-dimensional graph linear canonical transform based on chirp multiplication-chirp convolution-chirp multiplication decomposition (2-D CM-CC-CM-GLCT). Then, extending 2-D CDDHFs-GLCT and 2-D CM-CC-CM-GLCT to M-D CDDHFs-GLCT and M-D CM-CC-CM-GLCT. In terms of the computational complexity, additivity and reversibility, M-D CDDHFs-GLCT and M-D CM-CC-CM-GLCT are compared. Theoretical analysis shows that the computational complexity of M-D CM-CC-CM-GLCT algorithm is obviously reduced. Simulation results indicate that M-D CM-CC-CM-GLCT achieves comparable additivity to M-D CDDHFs-GLCT, while M-D CM-CC-CM-GLCT exhibits better reversibility. Finally, M-D GLCT is applied to data compression to show its application advantages. The experimental results reflect the superiority of M-D GLCT in the algorithm design and implementation of data compression.
The graph linear canonical transform (GLCT) is presented as an extension of the graph Fourier transform (GFT) and the graph fractional Fourier transform (GFrFT), offering more flexibility as an effective tool for graph signal processing. In this paper, we introduce a GLCT based on chirp multiplication-chirp convolution-chirp multiplication decomposition (CM-CC-CM-GLCT), which irrelevant to sampling periods and without oversampling operation. Various properties and special cases of the CM-CC-CM-GLCT are derived and discussed. In terms of computational complexity, additivity, and reversibility, we compare the CM-CC-CM-GLCT and the GLCT based on the central discrete dilated Hermite function (CDDHFs-GLCT). Theoretical analysis demonstrates that the computational complexity of the CM-CC-CM-GLCT is significantly reduced. Simulation results indicate that the CM-CC-CM-GLCT achieves similar additivity to the CDDHFs-GLCT. Notably, the CM-CC-CM-GLCT exhibits better reversibility.
Let $Y_{3,2}$ be the 3-graph with two edges intersecting in two vertices. We prove that every 3-graph $ H $ on $ n $ vertices with at least $ \max \left \{ \binom{4αn}{3}, \binom{n}{3}-\binom{n-αn}{3} \right \}+o(n^3) $ edges contains a $Y_{3,2}$-tiling covering more than $ 4αn$ vertices, for sufficiently large $ n $ and $0<α< 1/4$. The bound on the number of edges is asymptotically best possible and solves a conjecture of the authors for 3-graphs that generalizes the Matching Conjecture of Erdős.
Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available. However, experience transferring as a whole usually suffers from gaps that exist among source domains and target domains. For instance, transferring domain-specific-knowledge-related experience is difficult. To tackle this problem, we propose a new method that explicitly decouples the transferring of general-semantic-representation-related experience and the domain-specific-knowledge-related experience. Specifically, for domain-specific-knowledge-related experience, we design two modules to capture intent-slot relation and slot-slot relation respectively. Extensive experiments on Snips and FewJoint datasets show that our method achieves state-of-the-art performance. The method improves the joint accuracy metric from 27.72% to 42.20% in the 1-shot setting, and from 46.54% to 60.79% in the 5-shot setting.
In this note we show the following strengthening of a multipartite version of the Hajnal--Szemerédi theorem. For an integer $r \ge 3$ and $γ> 0$, there exists a constant $C$ such that if $p\ge Cn^{-2/r}(\log n)^{1/{r \choose 2}}$ and $G$ is a balanced $r$-partite graph with each vertex class of size $n$ and $δ^\ast(G)\ge (1-1/r+γ)n$, then with high probability the random subgraph $G(p)$ of $G$ contains a $K_r$-factor. We also use it to derive corresponding transversal versions.
We investigate the occurrence of powers of tight Hamilton cycles in random hypergraphs. For every $r\ge 3$ and $k\ge 1$, we show that there exists a constant $C > 0$ such that if $p=p(n) \ge Cn^{-1/\binom{k+r-2}{r-1}}$ then asymptotically almost surely the random hypergraph $H^{(r)}(n,p)$ contains the $k$th power of a tight Hamilton cycle. This improves on a result of Parczyk and Person, who proved the same result under the assumption $p=ω\left(n^{-1/\binom{k+r-2}{r-1}}\right)$ using a second moment argument.
We study the following rainbow version of subgraph containment problems in a family of (hyper)graphs, which generalizes the classical subgraph containment problems in a single host graph. For a collection $\textbf{G}=\{G_1, G_2,\ldots, G_{m}\}$ of not necessarily distinct $k$-graphs on the same vertex set $[n]$, a (sub)graph $H$ on $[n]$ is rainbow if there exists an injection $φ: E(H)\rightarrow[m]$ such that $e\in E(G_{φ(e)})$ for each $e\in E(H)$. Note that if $|E(H)|=m$, then $φ$ is a bijection and thus $H$ contains exactly one edge from each $G_i$. Our main results focus on rainbow clique-factors in (hyper)graph systems with minimum $d$-degree conditions. Specifically, we establish the following: (1) A rainbow analogue of an asymptotical version of the Hajnal--Szemerédi theorem, namely, if $t\mid n$ and $δ(G_i)\geq(1-\frac{1}{t}+\varepsilon)n$ for each $i\in[\frac{n}{t}\binom{t}{2}]$, then $\textbf{G}$ contains a rainbow $K_t$-factor; (2) Essentially a minimum $d$-degree condition forcing a perfect matching in a $k$-graph also forces rainbow perfect matchings in $k$-graph systems for $d\in[k-1]$. The degree assumptions in both results are asymptotically best possible (although the minimum $d$-degree condition forcing a perfect matching in a $k$-graph is in general unknown). For (1) we also discuss two directed versions and a multipartite version. Finally, to establish these results, we in fact provide a general framework to attack this type of problems, which reduces it to subproblems with finitely many colors.