Nearest neighbor machine translation is a successful approach for fast domain adaption, which interpolates the pre-trained transformers with domain-specific token-level k-nearest-neighbor (kNN) retrieval without retraining. Despite kNN MT's success, searching large reference corpus and fixed interpolation between the kNN and pre-trained model led to computational complexity and translation quality challenges. Among other papers, Dai et al. (2023) proposed methods to obtain a small number of reference samples dynamically for which they introduced a distance-aware interpolation method using an equation that includes free parameters. This paper proposes a simply trainable nearest neighbor machine translation and carry out inference experiments on GPU. Similar to Dai et al. (2023), we first adaptively construct a small datastore for each input sentence. Second, we train a single-layer network for the interpolation coefficient between the knnMT and pre-trained result to automatically interpolate in different domains. Experimental results on different domains show that our proposed method either improves or sometimes maintain the translation quality of methods in Dai et al. (2023) while being automatic. In addition, our GPU inference results demonstrate that knnMT can be integrated into GPUs with a drop of only 5% in terms of speed.

We study convex optimization problems under differential privacy (DP). With heavy-tailed gradients, existing works achieve suboptimal rates. The main obstacle is that existing gradient estimators have suboptimal tail properties, resulting in a superfluous factor of $d$ in the union bound. In this paper, we explore algorithms achieving optimal rates of DP optimization with heavy-tailed gradients. Our first method is a simple clipping approach. Under bounded $p$-th order moments of gradients, with $n$ samples, it achieves $\tilde{O}(\sqrt{d/n}+\sqrt{d}(\sqrt{d}/n\epsilon)^{1-1/p})$ population risk with $\epsilon\leq 1/\sqrt{d}$. We then propose an iterative updating method, which is more complex but achieves this rate for all $\epsilon\leq 1$. The results significantly improve over existing methods. Such improvement relies on a careful treatment of the tail behavior of gradient estimators. Our results match the minimax lower bound in \cite{kamath2022improved}, indicating that the theoretical limit of stochastic convex optimization under DP is achievable.

The widespread application of Artificial Intelligence (AI) techniques has significantly influenced the development of new therapeutic agents. These computational methods can be used to design and predict the properties of generated molecules. Multi-target Drug Discovery (MTDD) is an emerging paradigm for discovering drugs against complex disorders that do not respond well to more traditional target-specific treatments, such as central nervous system, immune system, and cardiovascular diseases. Still, there is yet to be an established benchmark suite for assessing the effectiveness of AI tools for designing multi-target compounds. Standardized benchmarks allow for comparing existing techniques and promote rapid research progress. Hence, this work proposes an evaluation framework for molecule generation techniques in MTDD scenarios, considering brain diseases as a case study. Our methodology involves using large language models to select the appropriate molecular targets, gathering and preprocessing the bioassay datasets, training quantitative structure-activity relationship models to predict target modulation, and assessing other essential drug-likeness properties for implementing the benchmarks. Additionally, this work will assess the performance of four deep generative models and evolutionary algorithms over our benchmark suite. In our findings, both evolutionary algorithms and generative models can achieve competitive results across the proposed benchmarks.

Time series modeling is crucial for many applications, however, it faces challenges such as complex spatio-temporal dependencies and distribution shifts in learning from historical context to predict task-specific outcomes. To address these challenges, we propose a novel approach using an agentic Retrieval-Augmented Generation (RAG) framework for time series analysis. The framework leverages a hierarchical, multi-agent architecture where the master agent orchestrates specialized sub-agents and delegates the end-user request to the relevant sub-agent. The sub-agents utilize smaller, pre-trained language models (SLMs) customized for specific time series tasks through fine-tuning using instruction tuning and direct preference optimization, and retrieve relevant prompts from a shared repository of prompt pools containing distilled knowledge about historical patterns and trends to improve predictions on new data. Our proposed modular, multi-agent RAG approach offers flexibility and achieves state-of-the-art performance across major time series tasks by tackling complex challenges more effectively than task-specific customized methods across benchmark datasets.

It can be difficult to interpret a coefficient of an uncertain model. A slope coefficient of a regression model may change as covariates are added or removed from the model. In the context of high-dimensional data, there are too many model extensions to check. However, as we show here, it is possible to efficiently search, with a branch and bound algorithm, for maximum and minimum values of that adjusted slope coefficient over a discrete space of regularized regression models. Here we introduce our algorithm, along with supporting mathematical results, an example application, and a link to our computer code, to help researchers summarize high-dimensional data and assess the stability of regression coefficients in uncertain models.

Quantum machine learning (QML) is a category of algorithms that employ variational quantum circuits (VQCs) to tackle machine learning tasks. Recent discoveries have shown that QML models can effectively generalize from limited training data samples. This capability has sparked increased interest in deploying these models to address practical, real-world challenges, resulting in the emergence of Quantum Machine Learning as a Service (QMLaaS). QMLaaS represents a hybrid model that utilizes both classical and quantum computing resources. Classical computers play a crucial role in this setup, handling initial pre-processing and subsequent post-processing of data to compensate for the current limitations of quantum hardware. Since this is a new area, very little work exists to paint the whole picture of QMLaaS in the context of known security threats in the domain of classical and quantum machine learning. This SoK paper is aimed to bridge this gap by outlining the complete QMLaaS workflow, which encompasses both the training and inference phases and highlighting significant security concerns involving untrusted classical or quantum providers. QML models contain several sensitive assets, such as the model architecture, training/testing data, encoding techniques, and trained parameters. Unauthorized access to these components could compromise the model's integrity and lead to intellectual property (IP) theft. We pinpoint the critical security issues that must be considered to pave the way for a secure QMLaaS deployment.

Federated Graph Learning (FGL) aims to learn graph learning models over graph data distributed in multiple data owners, which has been applied in various applications such as social recommendation and financial fraud detection. Inherited from generic Federated Learning (FL), FGL similarly has the data heterogeneity issue where the label distribution may vary significantly for distributed graph data across clients. For instance, a client can have the majority of nodes from a class, while another client may have only a few nodes from the same class. This issue results in divergent local objectives and impairs FGL convergence for node-level tasks, especially for node classification. Moreover, FGL also encounters a unique challenge for the node classification task: the nodes from a minority class in a client are more likely to have biased neighboring information, which prevents FGL from learning expressive node embeddings with Graph Neural Networks (GNNs). To grapple with the challenge, we propose FedSpray, a novel FGL framework that learns local class-wise structure proxies in the latent space and aligns them to obtain global structure proxies in the server. Our goal is to obtain the aligned structure proxies that can serve as reliable, unbiased neighboring information for node classification. To achieve this, FedSpray trains a global feature-structure encoder and generates unbiased soft targets with structure proxies to regularize local training of GNN models in a personalized way. We conduct extensive experiments over four datasets, and experiment results validate the superiority of FedSpray compared with other baselines. Our code is available at https://github.com/xbfu/FedSpray.

Conventional Bayesian optimal experimental design seeks to maximize the expected information gain (EIG) on model parameters. However, the end goal of the experiment often is not to learn the model parameters, but to predict downstream quantities of interest (QoIs) that depend on the learned parameters. And designs that offer high EIG for parameters may not translate to high EIG for QoIs. Goal-oriented optimal experimental design (GO-OED) thus directly targets to maximize the EIG of QoIs. We introduce LF-GO-OED (likelihood-free goal-oriented optimal experimental design), a computational method for conducting GO-OED with nonlinear observation and prediction models. LF-GO-OED is specifically designed to accommodate implicit models, where the likelihood is intractable. In particular, it builds a density ratio estimator from samples generated from approximate Bayesian computation (ABC), thereby sidestepping the need for likelihood evaluations or density estimations. The overall method is validated on benchmark problems with existing methods, and demonstrated on scientific applications of epidemiology and neural science.

Continual learning has emerged as a crucial paradigm for learning from sequential data while preserving previous knowledge. In the realm of continual graph learning, where graphs continuously evolve based on streaming graph data, continual graph learning presents unique challenges that require adaptive and efficient graph learning methods in addition to the problem of catastrophic forgetting. The first challenge arises from the interdependencies between different graph data, where previous graphs can influence new data distributions. The second challenge lies in the efficiency concern when dealing with large graphs. To addresses these two problems, we produce an Efficient Continual Graph Learner (E-CGL) in this paper. We tackle the interdependencies issue by demonstrating the effectiveness of replay strategies and introducing a combined sampling strategy that considers both node importance and diversity. To overcome the limitation of efficiency, E-CGL leverages a simple yet effective MLP model that shares weights with a GCN during training, achieving acceleration by circumventing the computationally expensive message passing process. Our method comprehensively surpasses nine baselines on four graph continual learning datasets under two settings, meanwhile E-CGL largely reduces the catastrophic forgetting problem down to an average of -1.1%. Additionally, E-CGL achieves an average of 15.83x training time acceleration and 4.89x inference time acceleration across the four datasets. These results indicate that E-CGL not only effectively manages the correlation between different graph data during continual training but also enhances the efficiency of continual learning on large graphs. The code is publicly available at https://github.com/aubreygjh/E-CGL.

The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and difficulty of training. Efficient transformers, on the other hand, often rely on clever data-modality-dependent construction to get over the quadratic complexity of transformers. This greatly hinders their applications on different data modalities, which is one of the pillars of contemporary foundational modeling. In this paper, we lay the groundwork for efficient foundational modeling by proposing SAMSA - SAMpling-Self-Attention, a context-aware linear complexity self-attention mechanism that works well on multiple data modalities. Our mechanism is based on a differentiable sampling without replacement method we discovered. This enables the self-attention module to attend to the most important token set, where the importance is defined by data. Moreover, as differentiability is not needed in inference, the sparse formulation of our method costs little time overhead, further lowering computational costs. In short, SAMSA achieved competitive or even SOTA results on many benchmarks, while being faster in inference, compared to other very specialized models. Against full self-attention, real inference time significantly decreases while performance ranges from negligible degradation to outperformance. We release our source code in the repository: https://github.com/HySonLab/SAMSA