arXiv subjects

Kai Yi

Publications and source records attributed to Kai Yi.

At least 37 records · Page 2Linked to original sources

arXiv2025

Sparse-ProxSkip: Accelerated Sparse-to-Sparse Training in Federated Learning

In Federated Learning (FL), both client resource constraints and communication costs pose major problems for training large models. In the centralized setting, sparse training addresses resource constraints, while in the distributed setting, local training addresses communication costs. Recent work has shown that local training provably improves communication complexity through acceleration. In this work we show that in FL, naive integration of sparse training and acceleration fails, and we provide theoretical and empirical explanations of this phenomenon. We introduce Sparse-ProxSkip, addressing the issue and implementing the efficient technique of Straight-Through Estimator pruning into sparse training. We demonstrate the performance of Sparse-ProxSkip in extensive experiments.

cs.LG↗

arXiv2025

Symmetric Pruning of Large Language Models

Popular post-training pruning methods such as Wanda and RIA are known for their simple, yet effective, designs that have shown exceptional empirical performance. Wanda optimizes performance through calibrated activations during pruning, while RIA emphasizes the relative, rather than absolute, importance of weight elements. Despite their practical success, a thorough theoretical foundation explaining these outcomes has been lacking. This paper introduces new theoretical insights that redefine the standard minimization objective for pruning, offering a deeper understanding of the factors contributing to their success. Our study extends beyond these insights by proposing complementary strategies that consider both input activations and weight significance. We validate these approaches through rigorous experiments, demonstrating substantial enhancements over existing methods. Furthermore, we introduce a novel training-free fine-tuning approach $R^2$-DSnoT that incorporates relative weight importance and a regularized decision boundary within a dynamic pruning-and-growing framework, significantly outperforming strong baselines and establishing a new state of the art.

cs.LG↗

arXiv2025

Estimating Large Global Significances with a New Monte Carlo Extrapolation Method

In particle physics, it is needed to evaluate the possibility that excesses of events in mass spectra are due to statistical fluctuations as quantified by the standards of local and global significances. Without prior knowledge of a particle's mass, it is especially critical to estimate its global significance. The usual approach is to count the number of times a significance limit is exceeded in a collection of simulated Monte Carlo (MC) 'toy experiments.' To demonstrate this conventional method for global significance, we performed simulation studies according to a recent Compact Muon Solenoid (CMS) result to show its effectiveness. However, this counting method is not practical for computing large global significances. To address this problem, we developed a new 'extrapolation' method to evaluate the global significance. We compared the global significance estimated by our new method with that of the conventional approach, and verified its feasibility and effectiveness. This method is also applicable for cases where only small toy MC samples are available. In this approach, the significance is calculated based on p-values, assuming symmetrical Gaussian distributions.

hep-ex↗

arXiv2024

MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects

We present MANTA, a visual-text anomaly detection dataset for tiny objects. The visual component comprises over 137.3K images across 38 object categories spanning five typical domains, of which 8.6K images are labeled as anomalous with pixel-level annotations. Each image is captured from five distinct viewpoints to ensure comprehensive object coverage. The text component consists of two subsets: Declarative Knowledge, including 875 words that describe common anomalies across various domains and specific categories, with detailed explanations for < what, why, how>, including causes and visual characteristics; and Constructivist Learning, providing 2K multiple-choice questions with varying levels of difficulty, each paired with images and corresponded answer explanations. We also propose a baseline for visual-text tasks and conduct extensive benchmarking experiments to evaluate advanced methods across different settings, highlighting the challenges and efficacy of our dataset.

cs.CV↗

arXiv2024

A Regressor-Guided Graph Diffusion Model for Predicting Enzyme Mutations to Enhance Turnover Number

Enzymes are biological catalysts that can accelerate chemical reactions compared to uncatalyzed reactions in aqueous environments. Their catalytic efficiency is quantified by the turnover number (kcat), a parameter in enzyme kinetics. Enhancing enzyme activity is important for optimizing slow chemical reactions, with far-reaching implications for both research and industrial applications. However, traditional wet-lab methods for measuring and optimizing enzyme activity are often resource-intensive and time-consuming. To address these limitations, we introduce kcatDiffuser, a novel regressor-guided diffusion model designed to predict and improve enzyme turnover numbers. Our approach innovatively reformulates enzyme mutation prediction as a protein inverse folding task, thereby establishing a direct link between structural prediction and functional optimization. kcatDiffuser is a graph diffusion model guided by a regressor, enabling the prediction of amino acid mutations at multiple random positions simultaneously. Evaluations on BERENDA dataset shows that kcatDiffuser can achieve a Δ log kcat of 0.209, outperforming state-of-the-art methods like ProteinMPNN, PiFold, GraDe-IF in improving enzyme turnover numbers. Additionally, kcatDiffuser maintains high structural fidelity with a recovery rate of 0.716, pLDDT score of 92.515, RMSD of 3.764, and TM-score of 0.934, demonstrating its ability to generate enzyme variants with enhanced activity while preserving essential structural properties. Overall, kcatDiffuser represents a more efficient and targeted approach to enhancing enzyme activity. The code is available at https://github.com/xz32yu/KcatDiffuser.

q-bio.QM↗

arXiv2024

Experimental Road to a Charming Family of Tetraquarks ... and Beyond

Discovery of the X(3872) meson in 2003 ignited intense interest in exotic (neither $q\bar{q}$ nor $qqq$) hadrons, but a $c\bar{c}$ interpretation of this state was difficult to exclude. An unequivocal exotic was discovered in the $Z_c(3900)^+$ meson -- a charged charmonium-like state. A variety of models of exotic structure have been advanced but consensus is elusive. The grand lesson from heavy quarkonia was that heavy quarks bring clarity. Thus, the recently reported triplet of all-charm tetraquark candidates -- $X(6600)$, $X(6900)$, and $X(7100)$ -- decaying to $J/ψ\,J/ψ$ is a great boon, promising important insights. We review some history of exotics, chronicle the road to prospective all-charm tetraquarks, discuss in some detail the divergent modeling of $J/ψ\,J/ψ$ structures, and offer some inferences about them. These states form a Regge trajectory and appear to be a family of radial excitations. A reported, but unexplained, threshold excess could hint at a fourth family member. We close with a brief look at a step beyond: all-bottom tetraquarks.

hep-ph↗

arXiv2024

Heavy flavor spectroscopy studies at CMS

The CMS Collaboration has performed many studies in the field of heavy flavor spectroscopy. In this report, recent studies on exotic resonances in proton-proton collisions at $\sqrt{s} = 13$ TeV at CMS are presented. For the exotic hadrons, these results include the first evidence for X(3872) in heavy-ion collisions and three new structures in $J/ψJ/ψ$ mass spectrum. Beside the exotic hadrons, we also found new decay channels in conventional beauty hadrons, including $B^{0}_{s}\rightarrowψ(2S)K^{0}_{S}$, $Λ_{b}^{0}\rightarrow J/ψΞ^{-}K^{+} $, $B^{0} \rightarrow ψ(2S)K^{0}_{S}π^{+} π^{-}$, and $Ξ_{b}^{-} \rightarrow ψ(2S)Ξ^{-}$.

hep-ex↗

arXiv2024

New Structures in the $J/ψ$ $J/ψ$ Mass Spectrum at CMS

A search is reported for structures near the $J/ψ$ $J/ψ$ mass threshold using a dataset of proton-proton collisions at $\sqrt{s} \: =13 \: \mathrm{TeV} $ recorded with the CMS detector at the LHC, corresponding to an integrated luminosity of about $135 \: \mathrm{fb^{-1}}$. Two structures are observed with a significance exceeding $5σ$ and evidence of an additional structure is reported with a local significance of $4.7σ$.

hep-ex↗

arXiv2024

AB$\mathbb{C}$MB: Deep Delensing Assisted Likelihood-Free Inference from CMB Polarization Maps

The existence of a cosmic background of primordial gravitational waves (PGWB) is a robust prediction of inflationary cosmology, but it has so far evaded discovery. The most promising avenue of its detection is via measurements of Cosmic Microwave Background (CMB) $B$-polarization. However, this is not straightforward due to (a) the fact that CMB maps are distorted by gravitational lensing and (b) the high-dimensional nature of CMB data, which renders likelihood-based analysis methods computationally extremely expensive. In this paper, we introduce an efficient likelihood-free, end-to-end inference method to directly infer the posterior distribution of the tensor-to-scalar ratio $r$ from lensed maps of the Stokes $Q$ and $U$ polarization parameters. Our method employs a generative model to delense the maps and utilizes the Approximate Bayesian Computation (ABC) algorithm to sample $r$. We demonstrate that our method yields unbiased estimates of $r$ with well-calibrated uncertainty quantification.

astro-ph.CO↗

arXiv2024

Cohort Squeeze: Beyond a Single Communication Round per Cohort in Cross-Device Federated Learning

Virtually all federated learning (FL) methods, including FedAvg, operate in the following manner: i) an orchestrating server sends the current model parameters to a cohort of clients selected via certain rule, ii) these clients then independently perform a local training procedure (e.g., via SGD or Adam) using their own training data, and iii) the resulting models are shipped to the server for aggregation. This process is repeated until a model of suitable quality is found. A notable feature of these methods is that each cohort is involved in a single communication round with the server only. In this work we challenge this algorithmic design primitive and investigate whether it is possible to ``squeeze more juice" out of each cohort than what is possible in a single communication round. Surprisingly, we find that this is indeed the case, and our approach leads to up to 74% reduction in the total communication cost needed to train a FL model in the cross-device setting. Our method is based on a novel variant of the stochastic proximal point method (SPPM-AS) which supports a large collection of client sampling procedures some of which lead to further gains when compared to classical client selection approaches.

cs.LG↗

arXiv2024

PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression

There has been significant interest in "extreme" compression of large language models (LLMs), i.e., to 1-2 bits per parameter, which allows such models to be executed efficiently on resource-constrained devices. Existing work focused on improved one-shot quantization techniques and weight representations; yet, purely post-training approaches are reaching diminishing returns in terms of the accuracy-vs-bit-width trade-off. State-of-the-art quantization methods such as QuIP# and AQLM include fine-tuning (part of) the compressed parameters over a limited amount of calibration data; however, such fine-tuning techniques over compressed weights often make exclusive use of straight-through estimators (STE), whose performance is not well-understood in this setting. In this work, we question the use of STE for extreme LLM compression, showing that it can be sub-optimal, and perform a systematic study of quantization-aware fine-tuning strategies for LLMs. We propose PV-Tuning - a representation-agnostic framework that generalizes and improves upon existing fine-tuning strategies, and provides convergence guarantees in restricted cases. On the practical side, when used for 1-2 bit vector quantization, PV-Tuning outperforms prior techniques for highly-performant models such as Llama and Mistral. Using PV-Tuning, we achieve the first Pareto-optimal quantization for Llama 2 family models at 2 bits per parameter.

cs.LG↗

arXiv2024

FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity

The interest in federated learning has surged in recent research due to its unique ability to train a global model using privacy-secured information held locally on each client. This paper pays particular attention to the issue of client-side model heterogeneity, a pervasive challenge in the practical implementation of FL that escalates its complexity. Assuming a scenario where each client possesses varied memory storage, processing capabilities and network bandwidth - a phenomenon referred to as system heterogeneity - there is a pressing need to customize a unique model for each client. In response to this, we present an effective and adaptable federated framework FedP3, representing Federated Personalized and Privacy-friendly network Pruning, tailored for model heterogeneity scenarios. Our proposed methodology can incorporate and adapt well-established techniques to its specific instances. We offer a theoretical interpretation of FedP3 and its locally differential-private variant, DP-FedP3, and theoretically validate their efficiencies.

cs.LG↗

arXiv2024

DiffImpute: Tabular Data Imputation With Denoising Diffusion Probabilistic Model

Tabular data plays a crucial role in various domains but often suffers from missing values, thereby curtailing its potential utility. Traditional imputation techniques frequently yield suboptimal results and impose substantial computational burdens, leading to inaccuracies in subsequent modeling tasks. To address these challenges, we propose DiffImpute, a novel Denoising Diffusion Probabilistic Model (DDPM). Specifically, DiffImpute is trained on complete tabular datasets, ensuring that it can produce credible imputations for missing entries without undermining the authenticity of the existing data. Innovatively, it can be applied to various settings of Missing Completely At Random (MCAR) and Missing At Random (MAR). To effectively handle the tabular features in DDPM, we tailor four tabular denoising networks, spanning MLP, ResNet, Transformer, and U-Net. We also propose Harmonization to enhance coherence between observed and imputed data by infusing the data back and denoising them multiple times during the sampling stage. To enable efficient inference while maintaining imputation performance, we propose a refined non-Markovian sampling process that works along with Harmonization. Empirical evaluations on seven diverse datasets underscore the prowess of DiffImpute. Specifically, when paired with the Transformer as the denoising network, it consistently outperforms its competitors, boasting an average ranking of 1.7 and the most minimal standard deviation. In contrast, the next best method lags with a ranking of 2.8 and a standard deviation of 0.9. The code is available at https://github.com/Dendiiiii/DiffImpute.

cs.LG↗

arXiv2024

Domain-Aware Continual Zero-Shot Learning

Modern visual systems have a wide range of potential applications in vision tasks for natural science research, such as aiding in species discovery, monitoring animals in the wild, and so on. However, real-world vision tasks may experience changes in environmental conditions, leading to shifts in how captured images are presented. To address this issue, we introduce Domain-Aware Continual Zero-Shot Learning (DACZSL), a task to recognize images of unseen categories in continuously changing domains. Accordingly, we propose a Domain-Invariant Network (DIN) to learn factorized features for shifting domains and improved textual representation for unseen classes. DIN continually learns a global shared network for domain-invariant and task-invariant features, and per-task private networks for task-specific features. Furthermore, we enhance the dual network with class-wise learnable prompts to improve class-level text representation, thereby improving zero-shot prediction of future unseen classes. To evaluate DACZSL, we introduce two benchmarks, DomainNet-CZSL and iWildCam-CZSL. Our results show that DIN significantly outperforms existing baselines by over 5% in harmonic accuracy and over 1% in backward transfer and achieves a new SoTA.

cs.CV↗

arXiv2023

Graph Denoising Diffusion for Inverse Protein Folding

Inverse protein folding is challenging due to its inherent one-to-many mapping characteristic, where numerous possible amino acid sequences can fold into a single, identical protein backbone. This task involves not only identifying viable sequences but also representing the sheer diversity of potential solutions. However, existing discriminative models, such as transformer-based auto-regressive models, struggle to encapsulate the diverse range of plausible solutions. In contrast, diffusion probabilistic models, as an emerging genre of generative approaches, offer the potential to generate a diverse set of sequence candidates for determined protein backbones. We propose a novel graph denoising diffusion model for inverse protein folding, where a given protein backbone guides the diffusion process on the corresponding amino acid residue types. The model infers the joint distribution of amino acids conditioned on the nodes' physiochemical properties and local environment. Moreover, we utilize amino acid replacement matrices for the diffusion forward process, encoding the biologically-meaningful prior knowledge of amino acids from their spatial and sequential neighbors as well as themselves, which reduces the sampling space of the generative process. Our model achieves state-of-the-art performance over a set of popular baseline methods in sequence recovery and exhibits great potential in generating diverse protein sequences for a determined protein backbone structure.

q-bio.QM↗

arXiv2023

Continual Zero-Shot Learning through Semantically Guided Generative Random Walks

Learning novel concepts, remembering previous knowledge, and adapting it to future tasks occur simultaneously throughout a human's lifetime. To model such comprehensive abilities, continual zero-shot learning (CZSL) has recently been introduced. However, most existing methods overused unseen semantic information that may not be continually accessible in realistic settings. In this paper, we address the challenge of continual zero-shot learning where unseen information is not provided during training, by leveraging generative modeling. The heart of the generative-based methods is to learn quality representations from seen classes to improve the generative understanding of the unseen visual space. Motivated by this, we introduce generalization-bound tools and provide the first theoretical explanation for the benefits of generative modeling to CZSL tasks. Guided by the theoretical analysis, we then propose our learning algorithm that employs a novel semantically guided Generative Random Walk (GRW) loss. The GRW loss augments the training by continually encouraging the model to generate realistic and characterized samples to represent the unseen space. Our algorithm achieves state-of-the-art performance on AWA1, AWA2, CUB, and SUN datasets, surpassing existing CZSL methods by 3-7\%. The code has been made available here \url{https://github.com/wx-zhang/IGCZSL}

cs.CV↗

arXiv2023

Explicit Personalization and Local Training: Double Communication Acceleration in Federated Learning

Federated Learning is an evolving machine learning paradigm, in which multiple clients perform computations based on their individual private data, interspersed by communication with a remote server. A common strategy to curtail communication costs is Local Training, which consists in performing multiple local stochastic gradient descent steps between successive communication rounds. However, the conventional approach to local training overlooks the practical necessity for client-specific personalization, a technique to tailor local models to individual needs. We introduce Scafflix, a novel algorithm that efficiently integrates explicit personalization with local training. This innovative approach benefits from these two techniques, thereby achieving doubly accelerated communication, as we demonstrate both in theory and practice.

cs.LG↗

arXiv2023

Accurate and Definite Mutational Effect Prediction with Lightweight Equivariant Graph Neural Networks

Directed evolution as a widely-used engineering strategy faces obstacles in finding desired mutants from the massive size of candidate modifications. While deep learning methods learn protein contexts to establish feasible searching space, many existing models are computationally demanding and fail to predict how specific mutational tests will affect a protein's sequence or function. This research introduces a lightweight graph representation learning scheme that efficiently analyzes the microenvironment of wild-type proteins and recommends practical higher-order mutations exclusive to the user-specified protein and function of interest. Our method enables continuous improvement of the inference model by limited computational resources and a few hundred mutational training samples, resulting in accurate prediction of variant effects that exhibit near-perfect correlation with the ground truth across deep mutational scanning assays of 19 proteins. With its affordability and applicability to both computer scientists and biochemical laboratories, our solution offers a wide range of benefits that make it an ideal choice for the community.

q-bio.QM↗