Authors: Wei "Wayne" Chen, Rachel Sun, Doksoo Lee, Carlos M. Portela, Wei Chen
Metamaterials with functional responses, such as wave-based responses or deformation-induced property variation under external stimuli, can exhibit varying properties or functionalities under different conditions. Herein, we aim at rapid inverse design of these metamaterials to meet target qualitative functional behaviors. This inverse problem is challenging due to its intractability and the existence of non-unique solutions. Past works mainly focus on deep-learning-based methods that are data-demanding, require time-consuming training and hyperparameter tuning, and are non-interpretable. To overcome these limitations, we propose the Random-forest-based Interpretable Generative Inverse Design (RIGID), a single-shot inverse design method to achieve the fast generation of metamaterial designs with on-demand functional behaviors. Unlike most existing methods, by exploiting the interpretability of the random forest, we eliminate the need to train an inverse model mapping responses to designs. Based on the likelihood of target satisfaction derived from the trained forward model, one can sample design solutions using Markov chain Monte Carlo methods. The RIGID method therefore functions as a generative model that captures the conditional distribution of satisfying solutions given a design target. We demonstrate the effectiveness and efficiency of RIGID on both acoustic and optical metamaterial design problems where only small datasets (less than 250 training samples) are available. Synthetic design problems are created to further illustrate and validate the mechanism of likelihood estimation in RIGID. This work offers a new perspective on solving on-demand inverse design problems, showcasing the potential for incorporating interpretable machine learning into generative design and eliminating its large data requirement.
Authors: Hao Chen, Lun Du, Yuxuan Lu, Qiang Fu, Xu Chen, Shi Han, Yanbin Kang, Guangming Lu, Zi Li
Online recruitment platforms typically employ Person-Job Fit models in the core service that automatically match suitable job seekers with appropriate job positions. While existing works leverage historical or contextual information, they often disregard a crucial aspect: job seekers' social relationships in professional networks. This paper emphasizes the importance of incorporating professional networks into the Person-Job Fit model. Our innovative approach consists of two stages: (1) defining a Workplace Heterogeneous Information Network (WHIN) to capture heterogeneous knowledge, including professional connections and pre-training representations of various entities using a heterogeneous graph neural network; (2) designing a Contextual Social Attention Graph Neural Network (CSAGNN) that supplements users' missing information with professional connections' contextual information. We introduce a job-specific attention mechanism in CSAGNN to handle noisy professional networks, leveraging pre-trained entity representations from WHIN. We demonstrate the effectiveness of our approach through experimental evaluations conducted across three real-world recruitment datasets from LinkedIn, showing superior performance compared to baseline models.
Authors: Mateusz Wilinski, Andrey Y. Lokhov
Recent years have seen a lot of progress in algorithms for learning parameters of spreading dynamics from both full and partial data. Some of the remaining challenges include model selection under the scenarios of unknown network structure, noisy data, missing observations in time, as well as an efficient incorporation of prior information to minimize the number of samples required for an accurate learning. Here, we introduce a universal learning method based on scalable dynamic message-passing technique that addresses these challenges often encountered in real data. The algorithm leverages available prior knowledge on the model and on the data, and reconstructs both network structure and parameters of a spreading model. We show that a linear computational complexity of the method with the key model parameters makes the algorithm scalable to large network instances.
Authors: Zixuan Chen, Subhodeep Mitra, R Ravi, Wolfgang Gatterbauer
We analyze a general problem in a crowd-sourced setting where one user asks a question (also called item) and other users return answers (also called labels) for this question. Different from existing crowd sourcing work which focuses on finding the most appropriate label for the question (the "truth"), our problem is to determine a ranking of the users based on their ability to answer questions. We call this problem "ability discovery" to emphasize the connection to and duality with the more well-studied problem of "truth discovery".
To model items and their labels in a principled way, we draw upon Item Response Theory (IRT) which is the widely accepted theory behind standardized tests such as SAT and GRE. We start from an idealized setting where the relative performance of users is consistent across items and better users choose better fitting labels for each item. We posit that a principled algorithmic solution to our more general problem should solve this ideal setting correctly and observe that the response matrices in this setting obey the Consecutive Ones Property (C1P). While C1P is well understood algorithmically with various discrete algorithms, we devise a novel variant of the HITS algorithm which we call "HITSNDIFFS" (or HND), and prove that it can recover the ideal C1P-permutation in case it exists. Unlike fast combinatorial algorithms for finding the consecutive ones permutation (if it exists), HND also returns an ordering when such a permutation does not exist. Thus it provides a principled heuristic for our problem that is guaranteed to return the correct answer in the ideal setting. Our experiments show that HND produces user rankings with robustly high accuracy compared to state-of-the-art truth discovery methods. We also show that our novel variant of HITS scales better in the number of users than ABH, the only prior spectral C1P reconstruction algorithm.
Authors: J. Gliozzo, G. Marinò, A. Bonometti, M. Frasca, D. Malchiodi
The prediction of tumor progression and chemotherapy response has been recently tackled exploiting Tumor Infiltrating Lymphocytes (TILs) and the nuclear protein Ki67 as prognostic factors. Recently, deep neural networks (DNNs) have been shown to achieve top results in estimating Ki67 expression and simultaneous determination of intratumoral TILs score in breast cancer cells. However, in the last ten years the extraordinary progress induced by deep models proliferated at least as much as their resource demand. The exorbitant computational costs required to query (and in some cases also to store) a deep model represent a strong limitation in resource-limited contexts, like that of IoT-based applications to support healthcare personnel. To this end, we propose a resource consumption-aware DNN for the effective estimate of the percentage of Ki67-positive cells in breast cancer screenings. Our approach reduced up to 75% and 89% the usage of memory and disk space respectively, up to 1.5x the energy consumption, and preserved or improved the overall accuracy of a benchmark state-of-the-art solution. Encouraged by such positive results, we developed and structured the adopted framework so as to allow its general purpose usage, along with a public software repository to support its usage.
Authors: Seyed Soroush Karimi Madahi, Bert Claessens, Chris Develder
Growth in the penetration of renewable energy sources makes supply more uncertain and leads to an increase in the system imbalance. This trend, together with the single imbalance pricing, opens an opportunity for balance responsible parties (BRPs) to perform energy arbitrage in the imbalance settlement mechanism. To this end, we propose a battery control framework based on distributional reinforcement learning (DRL). Our proposed control framework takes a risk-sensitive perspective, allowing BRPs to adjust their risk preferences: we aim to optimize a weighted sum of the arbitrage profit and a risk measure while constraining the daily number of cycles for the battery. We assess the performance of our proposed control framework using the Belgian imbalance prices of 2022 and compare two state-of-the-art RL methods, deep Q learning and soft actor-critic. Results reveal that the distributional soft actor-critic method can outperform other methods. Moreover, we note that our fully risk-averse agent appropriately learns to hedge against the risk related to the unknown imbalance price by (dis)charging the battery only when the agent is more certain about the price.
Authors: Cassandra Czobit, Reza Samavi
Image-to-image translation has gained popularity in the medical field to transform images from one domain to another. Medical image synthesis via domain transformation is advantageous in its ability to augment an image dataset where images for a given class is limited. From the learning perspective, this process contributes to data-oriented robustness of the model by inherently broadening the model's exposure to more diverse visual data and enabling it to learn more generalized features. In the case of generating additional neuroimages, it is advantageous to obtain unidentifiable medical data and augment smaller annotated datasets. This study proposes the development of a CycleGAN model for translating neuroimages from one field strength to another (e.g., 3 Tesla to 1.5). This model was compared to a model based on DCGAN architecture. CycleGAN was able to generate the synthetic and reconstructed images with reasonable accuracy. The mapping function from the source (3 Tesla) to target domain (1.5 Tesla) performed optimally with an average PSNR value of 25.69 $\pm$ 2.49 dB and an MAE value of 2106.27 +/- 1218.37.
Authors: Xiaoqian Liu, Jianbin Jiao, Junge Zhang
Decision-making is a dynamic process requiring perception, memory, and reasoning to make choices and find optimal policies. Traditional approaches to decision-making suffer from sample efficiency and generalization, while large-scale self-supervised pretraining has enabled fast adaptation with fine-tuning or few-shot learning in language and vision. We thus argue to integrate knowledge acquired from generic large-scale self-supervised pretraining into downstream decision-making problems. We propose Pretrain-Then-Adapt pipeline and survey recent work on data collection, pretraining objectives and adaptation strategies for decision-making pretraining and downstream inference. Finally, we identify critical challenges and future directions for developing decision foundation model with the help of generic and flexible self-supervised pretraining.
Authors: Maja Rudolph, Stefan Kurz, Barbara Rakitsch
Design patterns provide a systematic way to convey solutions to recurring modeling challenges. This paper introduces design patterns for hybrid modeling, an approach that combines modeling based on first principles with data-driven modeling techniques. While both approaches have complementary advantages there are often multiple ways to combine them into a hybrid model, and the appropriate solution will depend on the problem at hand. In this paper, we provide four base patterns that can serve as blueprints for combining data-driven components with domain knowledge into a hybrid approach. In addition, we also present two composition patterns that govern the combination of the base patterns into more complex hybrid models. Each design pattern is illustrated by typical use cases from application areas such as climate modeling, engineering, and physics.
Authors: Jin-Long Wu, Matthew E. Levine, Tapio Schneider, Andrew Stuart
Complex dynamical systems are notoriously difficult to model because some degrees of freedom (e.g., small scales) may be computationally unresolvable or are incompletely understood, yet they are dynamically important. For example, the small scales of cloud dynamics and droplet formation are crucial for controlling climate, yet are unresolvable in global climate models. Semi-empirical closure models for the effects of unresolved degrees of freedom often exist and encode important domain-specific knowledge. Building on such closure models and correcting them through learning the structural errors can be an effective way of fusing data with domain knowledge. Here we describe a general approach, principles, and algorithms for learning about structural errors. Key to our approach is to include structural error models inside the models of complex systems, for example, in closure models for unresolved scales. The structural errors then map, usually nonlinearly, to observable data. As a result, however, mismatches between model output and data are only indirectly informative about structural errors, due to a lack of labeled pairs of inputs and outputs of structural error models. Additionally, derivatives of the model may not exist or be readily available. We discuss how structural error models can be learned from indirect data with derivative-free Kalman inversion algorithms and variants, how sparsity constraints enforce a "do no harm" principle, and various ways of modeling structural errors. We also discuss the merits of using non-local and/or stochastic error models. In addition, we demonstrate how data assimilation techniques can assist the learning about structural errors in non-ergodic systems. The concepts and algorithms are illustrated in two numerical examples based on the Lorenz-96 system and a human glucose-insulin model.
Authors: Lei Yang
We introduce a novel generative model, the Discrete Distribution Networks (DDN), that approximates data distribution using hierarchical discrete distributions. We posit that since the features within a network inherently contain distributional information, liberating the network from a single output to concurrently generate multiple samples proves to be highly effective. Therefore, DDN fits the target distribution, including continuous ones, by generating multiple discrete sample points. To capture finer details of the target data, DDN selects the output that is closest to the Ground Truth (GT) from the coarse results generated in the first layer. This selected output is then fed back into the network as a condition for the second layer, thereby generating new outputs more similar to the GT. As the number of DDN layers increases, the representational space of the outputs expands exponentially, and the generated samples become increasingly similar to the GT. This hierarchical output pattern of discrete distributions endows DDN with two intriguing properties: highly compressed representation and more general zero-shot conditional generation. We demonstrate the efficacy of DDN and these intriguing properties through experiments on CIFAR-10 and FFHQ.
Authors: Ning Dai, Wei Yu Tang, Tianshuo Zhou, David H. Mathews, Liang Huang
The tasks of designing messenger RNAs and non-coding RNAs are discrete optimization problems, and several versions of these problems are NP-hard. As an alternative to commonly used local search methods, we formulate these problems as continuous optimization and develop a general framework for this optimization based on a new concept of "expected partition function". The basic idea is to start with a distribution over all possible candidate sequences, and extend the objective function from a sequence to a distribution. We then use gradient descent-based optimization methods to improve the extended objective function, and the distribution will gradually shrink towards a one-hot sequence (i.e., a single sequence). We consider two important case studies within this framework, the mRNA design problem optimizing for partition function (i.e., ensemble free energy) and the non-coding RNA design problem optimizing for conditional (i.e., Boltzmann) probability. In both cases, our approach demonstrate promising preliminary results. We make our code available at https://github.com/KuNyaa/RNA_Design_codebase.
Authors: Elliot Creager, Richard Zemel
Research on algorithmic recourse typically considers how an individual can reasonably change an unfavorable automated decision when interacting with a fixed decision-making system. This paper focuses instead on the online setting, where system parameters are updated dynamically according to interactions with data subjects. Beyond the typical individual-level recourse, the online setting opens up new ways for groups to shape system decisions by leveraging the parameter update rule. We show empirically that recourse can be improved when users coordinate by jointly computing their feature perturbations, underscoring the importance of collective action in mitigating adverse automated decisions.
Authors: Kandan Ramakrishnan, R. James Cotton, Xaq Pitkow, Andreas S. Tolias
Recent work on object-centric world models aim to factorize representations in terms of objects in a completely unsupervised or self-supervised manner. Such world models are hypothesized to be a key component to address the generalization problem. While self-supervision has shown improved performance however, OOD generalization has not been systematically and explicitly tested. In this paper, we conduct an extensive study on the generalization properties of contrastive world model. We systematically test the model under a number of different OOD generalization scenarios such as extrapolation to new object attributes, introducing new conjunctions or new attributes. Our experiments show that the contrastive world model fails to generalize under the different OOD tests and the drop in performance depends on the extent to which the samples are OOD. When visualizing the transition updates and convolutional feature maps, we observe that any changes in object attributes (such as previously unseen colors, shapes, or conjunctions of color and shape) breaks down the factorization of object representations. Overall, our work highlights the importance of object-centric representations for generalization and current models are limited in their capacity to learn such representations required for human-level generalization.
Authors: David Guirguis, Conrad Tucker, Jack Beuth
Addressing the uncertainty and variability in the quality of 3D printed metals can further the wide spread use of this technology. Process mapping for new alloys is crucial for determining optimal process parameters that consistently produce acceptable printing quality. Process mapping is typically performed by conventional methods and is used for the design of experiments and ex situ characterization of printed parts. On the other hand, in situ approaches are limited because their observable features are limited and they require complex high-cost setups to obtain temperature measurements to boost accuracy. Our method relaxes these limitations by incorporating the temporal features of molten metal dynamics during laser-metal interactions using video vision transformers and high-speed imaging. Our approach can be used in existing commercial machines and can provide in situ process maps for efficient defect and variability quantification. The generalizability of the approach is demonstrated by performing cross-dataset evaluations on alloys with different compositions and intrinsic thermofluid properties.
Authors: Paweł Leszczyński, Kamil Kutorasiński, Marcin Szewczyk, Jarosław Pawłowski
We present a general framework for modeling materials using deep neural networks. Material represented by multidimensional characteristics (that mimic measurements) is used to train the neural autoencoder model in an unsupervised manner. The encoder is trying to predict the material parameters of a theoretical model, which is then used in a decoder part. The decoder, using the predicted parameters, reconstructs the input characteristics. The neural model is trained to capture a synthetically generated set of characteristics that can cover a broad range of material behaviors, leading to a model that can generalize on the underlying physics rather than just optimize the model parameters for a single measurement. After setting up the model we prove its usefulness in the complex problem of modeling magnetic materials in the frequency and current (out-of-linear range) domains simultaneously.
Authors: Bruce D. Lee, Anders Rantzer, Nikolai Matni
The strategy of pre-training a large model on a diverse dataset, then fine-tuning for a particular application has yielded impressive results in computer vision, natural language processing, and robotic control. This strategy has vast potential in adaptive control, where it is necessary to rapidly adapt to changing conditions with limited data. Toward concretely understanding the benefit of pre-training for adaptive control, we study the adaptive linear quadratic control problem in the setting where the learner has prior knowledge of a collection of basis matrices for the dynamics. This basis is misspecified in the sense that it cannot perfectly represent the dynamics of the underlying data generating process. We propose an algorithm that uses this prior knowledge, and prove upper bounds on the expected regret after $T$ interactions with the system. In the regime where $T$ is small, the upper bounds are dominated by a term scales with either $\texttt{poly}(\log T)$ or $\sqrt{T}$, depending on the prior knowledge available to the learner. When $T$ is large, the regret is dominated by a term that grows with $\delta T$, where $\delta$ quantifies the level of misspecification. This linear term arises due to the inability to perfectly estimate the underlying dynamics using the misspecified basis, and is therefore unavoidable unless the basis matrices are also adapted online. However, it only dominates for large $T$, after the sublinear terms arising due to the error in estimating the weights for the basis matrices become negligible. We provide simulations that validate our analysis. Our simulations also show that offline data from a collection of related systems can be used as part of a pre-training stage to estimate a misspecified dynamics basis, which is in turn used by our adaptive controller.
Authors: Vamsi K. Potluru, Daniel Borrajo, Andrea Coletta, Niccolò Dalmasso, Yousef El-Laham, Elizabeth Fons, Mohsen Ghassemi, Sriram Gopalakrishnan, Vikesh Gosai, Eleonora Kreačić, Ganapathy Mani, Saheed Obitayo, Deepak Paramanand, Natraj Raman, Mikhail Solonin, Srijan Sood, Svitlana Vyetrenko, Haibei Zhu, Manuela Veloso, Tucker Balch
Synthetic data has made tremendous strides in various commercial settings including finance, healthcare, and virtual reality. We present a broad overview of prototypical applications of synthetic data in the financial sector and in particular provide richer details for a few select ones. These cover a wide variety of data modalities including tabular, time-series, event-series, and unstructured arising from both markets and retail financial applications. Since finance is a highly regulated industry, synthetic data is a potential approach for dealing with issues related to privacy, fairness, and explainability. Various metrics are utilized in evaluating the quality and effectiveness of our approaches in these applications. We conclude with open directions in synthetic data in the context of the financial domain.
Authors: Si Zhang, Philip W. L. Fong
This paper proposes a computational model for policy administration. As an organization evolves, new users and resources are gradually placed under the mediation of the access control model. Each time such new entities are added, the policy administrator must deliberate on how the access control policy shall be revised to reflect the new reality. A well-designed access control model must anticipate such changes so that the administration cost does not become prohibitive when the organization scales up. Unfortunately, past Access Control research does not offer a formal way to quantify the cost of policy administration. In this work, we propose to model ongoing policy administration in an active learning framework. Administration cost can be quantified in terms of query complexity. We demonstrate the utility of this approach by applying it to the evolution of protection domains. We also modelled different policy administration strategies in our framework. This allowed us to formally demonstrate that domain-based policies have a cost advantage over access control matrices because of the use of heuristic reasoning when the policy evolves. To the best of our knowledge, this is the first work to employ an active learning framework to study the cost of policy deliberation and demonstrate the cost advantage of heuristic policy administration.
Authors: Xiaotong Guo, Hanyong Xu, Dingyi Zhuang, Yunhan Zheng, Jinhua Zhao
The rapid growth of the ride-hailing industry has revolutionized urban transportation worldwide. Despite its benefits, equity concerns arise as underserved communities face limited accessibility to affordable ride-hailing services. A key issue in this context is the vehicle rebalancing problem, where idle vehicles are moved to areas with anticipated demand. Without equitable approaches in demand forecasting and rebalancing strategies, these practices can further deepen existing inequities. In the realm of ride-hailing, three main facets of fairness are recognized: algorithmic fairness, fairness to drivers, and fairness to riders. This paper focuses on enhancing both algorithmic and rider fairness through a novel vehicle rebalancing method. We introduce an approach that combines a Socio-Aware Spatial-Temporal Graph Convolutional Network (SA-STGCN) for refined demand prediction and a fairness-integrated Matching-Integrated Vehicle Rebalancing (MIVR) model for subsequent vehicle rebalancing. Our methodology is designed to reduce prediction discrepancies and ensure equitable service provision across diverse regions. The effectiveness of our system is evaluated using simulations based on real-world ride-hailing data. The results suggest that our proposed method enhances both accuracy and fairness in forecasting ride-hailing demand, ultimately resulting in more equitable vehicle rebalancing in subsequent operations. Specifically, the algorithm developed in this study effectively reduces the standard deviation and average customer wait times by 6.48% and 0.49%, respectively. This achievement signifies a beneficial outcome for ride-hailing platforms, striking a balance between operational efficiency and fairness.
Authors: Wenhao Lu, Xufeng Zhao, Thilo Fryen, Jae Hee Lee, Mengdi Li, Sven Magg, Stefan Wermter
Reinforcement learning (RL) is a powerful technique for training intelligent agents, but understanding why these agents make specific decisions can be quite challenging. This lack of transparency in RL models has been a long-standing problem, making it difficult for users to grasp the reasons behind an agent's behaviour. Various approaches have been explored to address this problem, with one promising avenue being reward decomposition (RD). RD is appealing as it sidesteps some of the concerns associated with other methods that attempt to rationalize an agent's behaviour in a post-hoc manner. RD works by exposing various facets of the rewards that contribute to the agent's objectives during training. However, RD alone has limitations as it primarily offers insights based on sub-rewards and does not delve into the intricate cause-and-effect relationships that occur within an RL agent's neural model. In this paper, we present an extension of RD that goes beyond sub-rewards to provide more informative explanations. Our approach is centred on a causal learning framework that leverages information-theoretic measures for explanation objectives that encourage three crucial properties of causal factors: \emph{causal sufficiency}, \emph{sparseness}, and \emph{orthogonality}. These properties help us distill the cause-and-effect relationships between the agent's states and actions or rewards, allowing for a deeper understanding of its decision-making processes. Our framework is designed to generate local explanations and can be applied to a wide range of RL tasks with multiple reward channels. Through a series of experiments, we demonstrate that our approach offers more meaningful and insightful explanations for the agent's action selections.
Authors: Shanchuan Lin, Xiao Yang
Diffusion models trained with mean squared error loss tend to generate unrealistic samples. Current state-of-the-art models rely on classifier-free guidance to improve sample quality, yet its surprising effectiveness is not fully understood. In this paper, We show that the effectiveness of classifier-free guidance partly originates from it being a form of implicit perceptual guidance. As a result, we can directly incorporate perceptual loss in diffusion training to improve sample quality. Since the score matching objective used in diffusion training strongly resembles the denoising autoencoder objective used in unsupervised training of perceptual networks, the diffusion model itself is a perceptual network and can be used to generate meaningful perceptual loss. We propose a novel self-perceptual objective that results in diffusion models capable of generating more realistic samples. For conditional generation, our method only improves sample quality without entanglement with the conditional input and therefore does not sacrifice sample diversity. Our method can also improve sample quality for unconditional generation, which was not possible with classifier-free guidance before.
Authors: Mahshid Helali Moghadam, Mateusz Rzymowski, Lukasz Kulas
The integration of sensorized vessels, enabling real-time data collection and machine learning-driven data analysis marks a pivotal advancement in the maritime industry. This transformative technology not only can enhance safety, efficiency, and sustainability but also usher in a new era of cost-effective and smart maritime transportation in our increasingly interconnected world. This study presents a deep learning-driven anomaly detection system augmented with interpretable machine learning models for identifying performance anomalies in an industrial sensorized vessel, called TUCANA. We Leverage a human-in-the-loop unsupervised process that involves utilizing standard and Long Short-Term Memory (LSTM) autoencoders augmented with interpretable surrogate models, i.e., random forest and decision tree, to add transparency and interpretability to the results provided by the deep learning models. The interpretable models also enable automated rule generation for translating the inference into human-readable rules. Additionally, the process also includes providing a projection of the results using t-distributed stochastic neighbor embedding (t-SNE), which helps with a better understanding of the structure and relationships within the data and assessment of the identified anomalies. We empirically evaluate the system using real data acquired from the vessel TUCANA and the results involve achieving over 80% precision and 90% recall with the LSTM model used in the process. The interpretable models also provide logical rules aligned with expert thinking, and the t-SNE-based projection enhances interpretability. Our system demonstrates that the proposed approach can be used effectively in real-world scenarios, offering transparency and precision in performance anomaly detection.
Authors: Ali Eshragh, Luke Yerbury, Asef Nazari, Fred Roosta, Michael W. Mahoney
We develop a new efficient sequential approximate leverage score algorithm, SALSA, using methods from randomized numerical linear algebra (RandNLA) for large matrices. We demonstrate that, with high probability, the accuracy of SALSA's approximations is within $(1 + O({\varepsilon}))$ of the true leverage scores. In addition, we show that the theoretical computational complexity and numerical accuracy of SALSA surpass existing approximations. These theoretical results are subsequently utilized to develop an efficient algorithm, named LSARMA, for fitting an appropriate ARMA model to large-scale time series data. Our proposed algorithm is, with high probability, guaranteed to find the maximum likelihood estimates of the parameters for the true underlying ARMA model. Furthermore, it has a worst-case running time that significantly improves those of the state-of-the-art alternatives in big data regimes. Empirical results on large-scale data strongly support these theoretical results and underscore the efficacy of our new approach.
Authors: Lujia Wang, Hairong Wang, Fulvio D'Angelo, Lee Curtin, Christopher P. Sereduk, Gustavo De Leon, Kyle W. Singleton, Javier Urcuyo, Andrea Hawkins-Daarud, Pamela R. Jackson, Chandan Krishna, Richard S. Zimmerman, Devi P. Patra, Bernard R. Bendok, Kris A. Smith, Peter Nakaji, Kliment Donev, Leslie C. Baxter, Maciej M. Mrugała, Michele Ceccarelli, Antonio Iavarone, Kristin R. Swanson, Nhan L. Tran, Leland S. Hu, Jing Li
Glioblastoma (GBM) is one of the most aggressive and lethal human cancers. Intra-tumoral genetic heterogeneity poses a significant challenge for treatment. Biopsy is invasive, which motivates the development of non-invasive, MRI-based machine learning (ML) models to quantify intra-tumoral genetic heterogeneity for each patient. This capability holds great promise for enabling better therapeutic selection to improve patient outcomes. We proposed a novel Weakly Supervised Ordinal Support Vector Machine (WSO-SVM) to predict regional genetic alteration status within each GBM tumor using MRI. WSO-SVM was applied to a unique dataset of 318 image-localized biopsies with spatially matched multiparametric MRI from 74 GBM patients. The model was trained to predict the regional genetic alteration of three GBM driver genes (EGFR, PDGFRA, and PTEN) based on features extracted from the corresponding region of five MRI contrast images. For comparison, a variety of existing ML algorithms were also applied. The classification accuracy of each gene was compared between the different algorithms. The SHapley Additive exPlanations (SHAP) method was further applied to compute contribution scores of different contrast images. Finally, the trained WSO-SVM was used to generate prediction maps within the tumoral area of each patient to help visualize the intra-tumoral genetic heterogeneity. This study demonstrated the feasibility of using MRI and WSO-SVM to enable non-invasive prediction of intra-tumoral regional genetic alteration for each GBM patient, which can inform future adaptive therapies for individualized oncology.
Authors: Hengrui Cai, Shengjie Liu, Rui Song
This paper explores the causal reasoning of large language models (LLMs) to enhance their interpretability and reliability in advancing artificial intelligence. Despite the proficiency of LLMs in a range of tasks, their potential for understanding causality requires further exploration. We propose a novel causal attribution model that utilizes "do-operators" for constructing counterfactual scenarios, allowing us to systematically quantify the influence of input numerical data and LLMs' pre-existing knowledge on their causal reasoning processes. Our newly developed experimental setup assesses LLMs' reliance on contextual information and inherent knowledge across various domains. Our evaluation reveals that LLMs' causal reasoning ability depends on the context and domain-specific knowledge provided, and supports the argument that "knowledge is, indeed, what LLMs principally require for sound causal reasoning". On the contrary, in the absence of knowledge, LLMs still maintain a degree of causal reasoning using the available numerical data, albeit with limitations in the calculations.
Authors: Deepak Akhare, Tengfei Luo, Jian-Xun Wang
The hybrid neural differentiable models mark a significant advancement in the field of scientific machine learning. These models, integrating numerical representations of known physics into deep neural networks, offer enhanced predictive capabilities and show great potential for data-driven modeling of complex physical systems. However, a critical and yet unaddressed challenge lies in the quantification of inherent uncertainties stemming from multiple sources. Addressing this gap, we introduce a novel method, DiffHybrid-UQ, for effective and efficient uncertainty propagation and estimation in hybrid neural differentiable models, leveraging the strengths of deep ensemble Bayesian learning and nonlinear transformations. Specifically, our approach effectively discerns and quantifies both aleatoric uncertainties, arising from data noise, and epistemic uncertainties, resulting from model-form discrepancies and data sparsity. This is achieved within a Bayesian model averaging framework, where aleatoric uncertainties are modeled through hybrid neural models. The unscented transformation plays a pivotal role in enabling the flow of these uncertainties through the nonlinear functions within the hybrid model. In contrast, epistemic uncertainties are estimated using an ensemble of stochastic gradient descent (SGD) trajectories. This approach offers a practical approximation to the posterior distribution of both the network parameters and the physical parameters. Notably, the DiffHybrid-UQ framework is designed for simplicity in implementation and high scalability, making it suitable for parallel computing environments. The merits of the proposed method have been demonstrated through problems governed by both ordinary and partial differentiable equations.
Authors: Guojian Wang, Faguo Wu, Xiao Zhang, Tianyuan Chen
The sparsity of reward feedback remains a challenging problem in online deep reinforcement learning (DRL). Previous approaches have utilized temporal credit assignment (CA) to achieve impressive results in multiple hard tasks. However, many CA methods relied on complex architectures or introduced sensitive hyperparameters to estimate the impact of state-action pairs. Meanwhile, the premise of the feasibility of CA methods is to obtain trajectories with sparse rewards, which can be troublesome in sparse-reward environments with large state spaces. To tackle these problems, we propose a simple and efficient algorithm called Policy Optimization with Smooth Guidance (POSG) that leverages a small set of sparse-reward demonstrations to make reliable and effective long-term credit assignments while efficiently facilitating exploration. The key idea is that the relative impact of state-action pairs can be indirectly estimated using offline demonstrations rather than directly leveraging the sparse reward trajectories generated by the agent. Specifically, we first obtain the trajectory importance by considering both the trajectory-level distance to demonstrations and the returns of the relevant trajectories. Then, the guidance reward is calculated for each state-action pair by smoothly averaging the importance of the trajectories through it, merging the demonstration's distribution and reward information. We theoretically analyze the performance improvement bound caused by smooth guidance rewards and derive a new worst-case lower bound on the performance improvement. Extensive results demonstrate POSG's significant advantages in control performance and convergence speed compared to benchmark DRL algorithms. Notably, the specific metrics and quantifiable results are investigated to demonstrate the superiority of POSG.
Authors: Xiaogang Xing, Ming Xu, Yujing Bai, Dongdong Yang
Backdoor attacks in the traditional graph neural networks (GNNs) field are easily detectable due to the dilemma of confusing labels. To explore the backdoor vulnerability of GNNs and create a more stealthy backdoor attack method, a clean-label graph backdoor attack method(CGBA) in the node classification task is proposed in this paper. Differently from existing backdoor attack methods, CGBA requires neither modification of node labels nor graph structure. Specifically, to solve the problem of inconsistency between the contents and labels of the samples, CGBA selects poisoning samples in a specific target class and uses the label of sample as the target label (i.e., clean-label) after injecting triggers into the target samples. To guarantee the similarity of neighboring nodes, the raw features of the nodes are elaborately picked as triggers to further improve the concealment of the triggers. Extensive experiments results show the effectiveness of our method. When the poisoning rate is 0.04, CGBA can achieve an average attack success rate of 87.8%, 98.9%, 89.1%, and 98.5%, respectively.
Authors: Harsh Chaudhari, Anuja Patil, Dhanashree Lavekar, Pranav Khairnar, Raviraj Joshi
This work introduces the L3Cube-MahaSocialNER dataset, the first and largest social media dataset specifically designed for Named Entity Recognition (NER) in the Marathi language. The dataset comprises 18,000 manually labeled sentences covering eight entity classes, addressing challenges posed by social media data, including non-standard language and informal idioms. Deep learning models, including CNN, LSTM, BiLSTM, and Transformer models, are evaluated on the individual dataset with IOB and non-IOB notations. The results demonstrate the effectiveness of these models in accurately recognizing named entities in Marathi informal text. The L3Cube-MahaSocialNER dataset offers user-centric information extraction and supports real-time applications, providing a valuable resource for public opinion analysis, news, and marketing on social media platforms. We also show that the zero-shot results of the regular NER model are poor on the social NER test set thus highlighting the need for more social NER datasets. The datasets and models are publicly available at https://github.com/l3cube-pune/MarathiNLP
Authors: Anish Lakkapragada
Linear Regression and neural networks are widely used to model data. Neural networks distinguish themselves from linear regression with their use of activation functions that enable modeling nonlinear functions. The standard argument for these activation functions is that without them, neural networks only can model a line. However, a novel explanation we propose in this paper for the impracticality of neural networks without activation functions, or linear neural networks, is that they actually reduce both training and testing performance. Having more parameters makes LNNs harder to optimize, and thus they require more training iterations than linear regression to even potentially converge to the optimal solution. We prove this hypothesis through an analysis of the optimization of an LNN and rigorous testing comparing the performance between both LNNs and linear regression on synthethic, noisy datasets.
Authors: Saikat Barua, Dr. Sifat Momen
In order to fully harness the potential of machine learning, it is crucial to establish a system that renders the field more accessible and less daunting for individuals who may not possess a comprehensive understanding of its intricacies. The paper describes the design of a system that integrates AutoML, XAI, and synthetic data generation to provide a great UX design for users. The system allows users to navigate and harness the power of machine learning while abstracting its complexities and providing high usability. The paper proposes two novel classifiers, Logistic Regression Forest and Support Vector Tree, for enhanced model performance, achieving 96\% accuracy on a diabetes dataset and 93\% on a survey dataset. The paper also introduces a model-dependent local interpreter called MEDLEY and evaluates its interpretation against LIME, Greedy, and Parzen. Additionally, the paper introduces LLM-based synthetic data generation, library-based data generation, and enhancing the original dataset with GAN. The findings on synthetic data suggest that enhancing the original dataset with GAN is the most reliable way to generate synthetic data, as evidenced by KS tests, standard deviation, and feature importance. The authors also found that GAN works best for quantitative datasets.
Authors: Jingjing Xu, Caesar Wu, Yuan-Fang Li, Pascal Bouvry
In the domain of multivariate forecasting, transformer models stand out as powerful apparatus, displaying exceptional capabilities in handling messy datasets from real-world contexts. However, the inherent complexity of these datasets, characterized by numerous variables and lengthy temporal sequences, poses challenges, including increased noise and extended model runtime. This paper focuses on reducing redundant information to elevate forecasting accuracy while optimizing runtime efficiency. We propose a novel transformer forecasting framework enhanced by Principal Component Analysis (PCA) to tackle this challenge. The framework is evaluated by five state-of-the-art (SOTA) models and four diverse real-world datasets. Our experimental results demonstrate the framework's ability to minimize prediction errors across all models and datasets while significantly reducing runtime. From the model perspective, one of the PCA-enhanced models: PCA+Crossformer, reduces mean square errors (MSE) by 33.3% and decreases runtime by 49.2% on average. From the dataset perspective, the framework delivers 14.3% MSE and 76.6% runtime reduction on Electricity datasets, as well as 4.8% MSE and 86.9% runtime reduction on Traffic datasets. This study aims to advance various SOTA models and enhance transformer-based time series forecasting for intricate data.
Authors: Jalo Nousiainen, Byron Engler, Markus Kasper, Chang Rajani, Tapio Helin, Cédric T. Heritier, Sascha P. Quanz, Adrian M. Glauser
Direct imaging of Earth-like exoplanets is one of the most prominent scientific drivers of the next generation of ground-based telescopes. Typically, Earth-like exoplanets are located at small angular separations from their host stars, making their detection difficult. Consequently, the adaptive optics (AO) system's control algorithm must be carefully designed to distinguish the exoplanet from the residual light produced by the host star.
A new promising avenue of research to improve AO control builds on data-driven control methods such as Reinforcement Learning (RL). RL is an active branch of the machine learning research field, where control of a system is learned through interaction with the environment. Thus, RL can be seen as an automated approach to AO control, where its usage is entirely a turnkey operation. In particular, model-based reinforcement learning (MBRL) has been shown to cope with both temporal and misregistration errors. Similarly, it has been demonstrated to adapt to non-linear wavefront sensing while being efficient in training and execution.
In this work, we implement and adapt an RL method called Policy Optimization for AO (PO4AO) to the GHOST test bench at ESO headquarters, where we demonstrate a strong performance of the method in a laboratory environment. Our implementation allows the training to be performed parallel to inference, which is crucial for on-sky operation. In particular, we study the predictive and self-calibrating aspects of the method. The new implementation on GHOST running PyTorch introduces only around 700 microseconds in addition to hardware, pipeline, and Python interface latency. We open-source well-documented code for the implementation and specify the requirements for the RTC pipeline. We also discuss the important hyperparameters of the method, the source of the latency, and the possible paths for a lower latency implementation.
Authors: Yuanzhao Zhai, Han Zhang, Yu Lei, Yue Yu, Kele Xu, Dawei Feng, Bo Ding, Huaimin Wang
Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs). However, a notable challenge in RLHF is overoptimization, where beyond a certain threshold, the pursuit of higher rewards leads to a decline in human preferences. In this paper, we observe the weakness of KL regularization which is commonly employed in existing RLHF methods to address overoptimization. To mitigate this limitation, we scrutinize the RLHF objective in the offline dataset and propose uncertainty-penalized RLHF (UP-RLHF), which incorporates uncertainty regularization during RL-finetuning. To enhance the uncertainty quantification abilities for reward models, we first propose a diverse low-rank adaptation (LoRA) ensemble by maximizing the nuclear norm of LoRA matrix concatenations. Then we optimize policy models utilizing penalized rewards, determined by both rewards and uncertainties provided by the diverse reward LoRA ensembles. Our experimental results, based on two real human preference datasets, showcase the effectiveness of diverse reward LoRA ensembles in quantifying reward uncertainty. Additionally, uncertainty regularization in UP-RLHF proves to be pivotal in mitigating overoptimization, thereby contributing to the overall performance.
Authors: Vladyslav Gapyak, Corinna Rentschler, Thomas März, Andreas Weinmann
Magnetic particle imaging (MPI) is an emerging medical imaging modality which has gained increasing interest in recent years. Among the benefits of MPI are its high temporal resolution, and that the technique does not expose the specimen to any kind of ionizing radiation. It is based on the non-linear response of magnetic nanoparticles to an applied magnetic field. From the electric signal measured in receive coils, the particle concentration has to be reconstructed. Due to the ill-posedness of the reconstruction problem, various regularization methods have been proposed for reconstruction ranging from early stopping methods, via classical Tikhonov regularization and iterative methods to modern machine learning approaches. In this work, we contribute to the latter class: we propose a plug-and-play approach based on a generic zero-shot denoiser with an $\ell^1$-prior. Moreover, we develop parameter selection strategies. Finally, we quantitatively and qualitatively evaluate the proposed algorithmic scheme on the 3D Open MPI data set with different levels of preprocessing.
Authors: Yusuf Sale, Paul Hofman, Lisa Wimmer, Eyke Hüllermeier, Thomas Nagler
Uncertainty quantification is a critical aspect of machine learning models, providing important insights into the reliability of predictions and aiding the decision-making process in real-world applications. This paper proposes a novel way to use variance-based measures to quantify uncertainty on the basis of second-order distributions in classification problems. A distinctive feature of the measures is the ability to reason about uncertainties on a class-based level, which is useful in situations where nuanced decision-making is required. Recalling some properties from the literature, we highlight that the variance-based measures satisfy important (axiomatic) properties. In addition to this axiomatic approach, we present empirical results showing the measures to be effective and competitive to commonly used entropy-based measures.
Authors: Reza Fayyazi, Rozhina Taghdimi, Shanchieh Jay Yang
Tactics, Techniques, and Procedures (TTPs) outline the methods attackers use to exploit vulnerabilities. The interpretation of TTPs in the MITRE ATT&CK framework can be challenging for cybersecurity practitioners due to presumed expertise, complex dependencies, and inherent ambiguity. Meanwhile, advancements with Large Language Models (LLMs) have led to recent surge in studies exploring its uses in cybersecurity operations. This leads us to question how well encoder-only (e.g., RoBERTa) and decoder-only (e.g., GPT-3.5) LLMs can comprehend and summarize TTPs to inform analysts of the intended purposes (i.e., tactics) of a cyberattack procedure. The state-of-the-art LLMs have shown to be prone to hallucination by providing inaccurate information, which is problematic in critical domains like cybersecurity. Therefore, we propose the use of Retrieval Augmented Generation (RAG) techniques to extract relevant contexts for each cyberattack procedure for decoder-only LLMs (without fine-tuning). We further contrast such approach against supervised fine-tuning (SFT) of encoder-only LLMs. Our results reveal that both the direct-use of decoder-only LLMs (i.e., its pre-trained knowledge) and the SFT of encoder-only LLMs offer inaccurate interpretation of cyberattack procedures. Significant improvements are shown when RAG is used for decoder-only LLMs, particularly when directly relevant context is found. This study further sheds insights on the limitations and capabilities of using RAG for LLMs in interpreting TTPs.
Authors: Samuel Holt, Zhaozhi Qian, Mihaela van der Schaar
Symbolic regression (SR) aims to discover concise closed-form mathematical equations from data, a task fundamental to scientific discovery. However, the problem is highly challenging because closed-form equations lie in a complex combinatorial search space. Existing methods, ranging from heuristic search to reinforcement learning, fail to scale with the number of input variables. We make the observation that closed-form equations often have structural characteristics and invariances (e.g., the commutative law) that could be further exploited to build more effective symbolic regression solutions. Motivated by this observation, our key contribution is to leverage pre-trained deep generative models to capture the intrinsic regularities of equations, thereby providing a solid foundation for subsequent optimization steps. We show that our novel formalism unifies several prominent approaches of symbolic regression and offers a new perspective to justify and improve on the previous ad hoc designs, such as the usage of cross-entropy loss during pre-training. Specifically, we propose an instantiation of our framework, Deep Generative Symbolic Regression (DGSR). In our experiments, we show that DGSR achieves a higher recovery rate of true equations in the setting of a larger number of input variables, and it is more computationally efficient at inference time than state-of-the-art RL symbolic regression solutions.
Authors: Seyed Hassan Yajadda, Farshad Safaei
Despite technological advancements, the significance of interdisciplinary subjects like complex networks has grown. Exploring communication within these networks is crucial, with traffic becoming a key concern due to the expanding population and increased need for connections. Congestion tends to originate in specific network areas but quickly proliferates throughout. Consequently, understanding the transition from a flow-free state to a congested state is vital. Numerous studies have delved into comprehending the emergence and control of congestion in complex networks, falling into three general categories: soft strategies, hard strategies, and resource allocation strategies. This article introduces a routing algorithm leveraging reinforcement learning to address two primary objectives: congestion control and optimizing path length based on the shortest path algorithm, ultimately enhancing network throughput compared to previous methods. Notably, the proposed method proves effective not only in Barab\'asi-Albert scale-free networks but also in other network models such as Watts-Strogatz (small-world) and Erd\"os-R\'enyi (random network). Simulation experiment results demonstrate that, across various traffic scenarios and network topologies, the proposed method can enhance efficiency criteria by up to 30% while reducing maximum node congestion by five times.
Authors: Daniel Huttenlocher, Hannah Li, Liang Lyu, Asuman Ozdaglar, James Siderius
Many online platforms of today, including social media sites, are two-sided markets bridging content creators and users. Most of the existing literature on platform recommendation algorithms largely focuses on user preferences and decisions, and does not simultaneously address creator incentives. We propose a model of content recommendation that explicitly focuses on the dynamics of user-content matching, with the novel property that both users and creators may leave the platform permanently if they do not experience sufficient engagement. In our model, each player decides to participate at each time step based on utilities derived from the current match: users based on alignment of the recommended content with their preferences, and creators based on their audience size. We show that a user-centric greedy algorithm that does not consider creator departures can result in arbitrarily poor total engagement, relative to an algorithm that maximizes total engagement while accounting for two-sided departures. Moreover, in stark contrast to the case where only users or only creators leave the platform, we prove that with two-sided departures, approximating maximum total engagement within any constant factor is NP-hard. We present two practical algorithms, one with performance guarantees under mild assumptions on user preferences, and another that tends to outperform algorithms that ignore two-sided departures in practice.
Authors: M. AbdulRazek, G. Khoriba, M. Belal
Medical imaging is an essential tool for diagnosing and treating diseases. However, lacking medical images can lead to inaccurate diagnoses and ineffective treatments. Generative models offer a promising solution for addressing medical image shortage problems due to their ability to generate new data from existing datasets and detect anomalies in this data. Data augmentation with position augmentation methods like scaling, cropping, flipping, padding, rotation, and translation could lead to more overfitting in domains with little data, such as medical image data. This paper proposes the GAN-GA, a generative model optimized by embedding a genetic algorithm. The proposed model enhances image fidelity and diversity while preserving distinctive features. The proposed medical image synthesis approach improves the quality and fidelity of medical images, an essential aspect of image interpretation. To evaluate synthesized images: Frechet Inception Distance (FID) is used. The proposed GAN-GA model is tested by generating Acute lymphoblastic leukemia (ALL) medical images, an image dataset, and is the first time to be used in generative models. Our results were compared to those of InfoGAN as a baseline model. The experimental results show that the proposed optimized GAN-GA enhances FID scores by about 6.8\%, especially in earlier training epochs. The source code and dataset will be available at: https://github.com/Mustafa-AbdulRazek/InfoGAN-GA.
Authors: Elnatan Kadar, Guy Gilboa
We propose a new way to explain and to visualize neural network classification through a decomposition-based explainable AI (DXAI). Instead of providing an explanation heatmap, our method yields a decomposition of the image into class-agnostic and class-distinct parts, with respect to the data and chosen classifier. Following a fundamental signal processing paradigm of analysis and synthesis, the original image is the sum of the decomposed parts. We thus obtain a radically different way of explaining classification. The class-agnostic part ideally is composed of all image features which do not posses class information, where the class-distinct part is its complementary. This new visualization can be more helpful and informative in certain scenarios, especially when the attributes are dense, global and additive in nature, for instance, when colors or textures are essential for class distinction. Code is available at https://github.com/dxai2024/dxai.
Authors: Natchanon Luangsomboon, Fahimeh Fazel, Jörg Liebeherr, Ashkan Sobhani, Shichao Guan, Xingjun Chu
Traffic from distributed training of machine learning (ML) models makes up a large and growing fraction of the traffic mix in enterprise data centers. While work on distributed ML abounds, the network traffic generated by distributed ML has received little attention. Using measurements on a testbed network, we investigate the traffic characteristics generated by the training of the ResNet-50 neural network with an emphasis on studying its short-term burstiness. For the latter we propose metrics that quantify traffic burstiness at different time scales. Our analysis reveals that distributed ML traffic exhibits a very high degree of burstiness on short time scales, exceeding a 60:1 peak-to-mean ratio on time intervals as long as 5~ms. We observe that training software orchestrates transmissions in such a way that burst transmissions from different sources within the same application do not result in congestion and packet losses. An extrapolation of the measurement data to multiple applications underscores the challenges of distributed ML traffic for congestion and flow control algorithms.
Authors: Yinglun Xu, Gagandeep Singh
In this work, we consider the offline preference-based reinforcement learning problem. We focus on the two-phase learning approach that is prevalent in previous reinforcement learning from human preference works. We find a challenge in applying two-phase learning in the offline PBRL setting that the learned utility model can be too hard for the learning agent to optimize during the second learning phase. To overcome the challenge, we propose a two-phasing learning approach under behavior regularization through action clipping. The insight is that the state-actions which are poorly covered by the dataset can only provide limited information and increase the complexity of the problem in the second learning phase. Our method ignores such state-actions during the second learning phase to achieve higher learning efficiency. We empirically verify that our method has high learning efficiency on a variety of datasets in robotic control environments.
Authors: Sebastian-Vasile Echim, Iulian-Marius Tăiatu, Dumitru-Clementin Cercel, Florin Pop
This work focuses on plant leaf disease classification and explores three crucial aspects: adversarial training, model explainability, and model compression. The models' robustness against adversarial attacks is enhanced through adversarial training, ensuring accurate classification even in the presence of threats. Leveraging explainability techniques, we gain insights into the model's decision-making process, improving trust and transparency. Additionally, we explore model compression techniques to optimize computational efficiency while maintaining classification performance. Through our experiments, we determine that on a benchmark dataset, the robustness can be the price of the classification accuracy with performance reductions of 3%-20% for regular tests and gains of 50%-70% for adversarial attack tests. We also demonstrate that a student model can be 15-25 times more computationally efficient for a slight performance reduction, distilling the knowledge of more complex models.
Authors: Shaan Ul Haque, Sajad Khodadadian, Siva Theja Maguluri
Stochastic approximation (SA) is an iterative algorithm to find the fixed point of an operator given noisy samples of this operator. SA appears in many areas such as optimization and Reinforcement Learning (RL). When implemented in practice, the noise that appears in the update of RL algorithms is naturally Markovian. Furthermore, in some settings, such as gradient TD, SA is employed in a two-time-scale manner. The mix of Markovian noise along with the two-time-scale structure results in an algorithm which is complex to analyze theoretically. In this paper, we characterize a tight convergence bound for the iterations of linear two-time-scale SA with Markovian noise. Our results show the convergence behavior of this algorithm given various choices of step sizes. Applying our result to the well-known TDC algorithm, we show the first $O(1/\epsilon)$ sample complexity for the convergence of this algorithm, outperforming all the previous work. Similarly, our results can be applied to establish the convergence behavior of a variety of RL algorithms, such as TD-learning with Polyak averaging, GTD, and GTD2.
Authors: Yuhta Takida, Yukara Ikemiya, Takashi Shibuya, Kazuki Shimada, Woosung Choi, Chieh-Hsin Lai, Naoki Murata, Toshimitsu Uesaka, Kengo Uchida, Wei-Hsiang Liao, Yuki Mitsufuji
Vector quantization (VQ) is a technique to deterministically learn features with discrete codebook representations. It is commonly performed with a variational autoencoding model, VQ-VAE, which can be further extended to hierarchical structures for making high-fidelity reconstructions. However, such hierarchical extensions of VQ-VAE often suffer from the codebook/layer collapse issue, where the codebook is not efficiently used to express the data, and hence degrades reconstruction accuracy. To mitigate this problem, we propose a novel unified framework to stochastically learn hierarchical discrete representation on the basis of the variational Bayes framework, called hierarchically quantized variational autoencoder (HQ-VAE). HQ-VAE naturally generalizes the hierarchical variants of VQ-VAE, such as VQ-VAE-2 and residual-quantized VAE (RQ-VAE), and provides them with a Bayesian training scheme. Our comprehensive experiments on image datasets show that HQ-VAE enhances codebook usage and improves reconstruction performance. We also validated HQ-VAE in terms of its applicability to a different modality with an audio dataset.
Authors: Enas Altarawneh, Ameeta Agrawal, Michael Jenkin, Manos Papagelis
Understanding and predicting the emotional trajectory in multi-party multi-turn conversations is of great significance. Such information can be used, for example, to generate empathetic response in human-machine interaction or to inform models of pre-emptive toxicity detection. In this work, we introduce the novel problem of Predicting Emotions in Conversations (PEC) for the next turn (n+1), given combinations of textual and/or emotion input up to turn n. We systematically approach the problem by modeling three dimensions inherently connected to evoked emotions in dialogues, including (i) sequence modeling, (ii) self-dependency modeling, and (iii) recency modeling. These modeling dimensions are then incorporated into two deep neural network architectures, a sequence model and a graph convolutional network model. The former is designed to capture the sequence of utterances in a dialogue, while the latter captures the sequence of utterances and the network formation of multi-party dialogues. We perform a comprehensive empirical evaluation of the various proposed models for addressing the PEC problem. The results indicate (i) the importance of the self-dependency and recency model dimensions for the prediction task, (ii) the quality of simpler sequence models in short dialogues, (iii) the importance of the graph neural models in improving the predictions in long dialogues.
Authors: Paul K. Mandal, Cole Leo, Connor Hurley
In the modern world, the amount of visual data recorded has been rapidly increasing. In many cases, data is stored in geographically distinct locations and thus requires a large amount of time and space to consolidate. Sometimes, there are also regulations for privacy protection which prevent data consolidation. In this work, we present federated implementations for object detection and recognition using a federated Faster R-CNN (FRCNN) and image segmentation using a federated Fully Convolutional Network (FCN). Our FRCNN was trained on 5000 examples of the COCO2017 dataset while our FCN was trained on the entire train set of the CamVid dataset. The proposed federated models address the challenges posed by the increasing volume and decentralized nature of visual data, offering efficient solutions in compliance with privacy regulations.
Authors: Wei-Jer Chang, Francesco Pittaluga, Masayoshi Tomizuka, Wei Zhan, Manmohan Chandraker
Evaluating the performance of autonomous vehicle planning algorithms necessitates simulating long-tail traffic scenarios. Traditional methods for generating safety-critical scenarios often fall short in realism and controllability. Furthermore, these techniques generally neglect the dynamics of agent interactions. To mitigate these limitations, we introduce a novel closed-loop simulation framework rooted in guided diffusion models. Our approach yields two distinct advantages: 1) the generation of realistic long-tail scenarios that closely emulate real-world conditions, and 2) enhanced controllability, enabling more comprehensive and interactive evaluations. We achieve this through novel guidance objectives that enhance road progress while lowering collision and off-road rates. We develop a novel approach to simulate safety-critical scenarios through an adversarial term in the denoising process, which allows the adversarial agent to challenge a planner with plausible maneuvers, while all agents in the scene exhibit reactive and realistic behaviors. We validate our framework empirically using the NuScenes dataset, demonstrating improvements in both realism and controllability. These findings affirm that guided diffusion models provide a robust and versatile foundation for safety-critical, interactive traffic simulation, extending their utility across the broader landscape of autonomous driving. For additional resources and demonstrations, visit our project page at https://safe-sim.github.io.
Authors: Rahatara Ferdousi, Chunsheng Yang, M. Anwar Hossain, Fedwa Laamarti, M. Shamim Hossain, Abdulmotaleb El Saddik
Recent advancements in cognitive computing, with the integration of deep learning techniques, have facilitated the development of intelligent cognitive systems (ICS). This is particularly beneficial in the context of rail defect detection, where the ICS would emulate human-like analysis of image data for defect patterns. Despite the success of Convolutional Neural Networks (CNN) in visual defect classification, the scarcity of large datasets for rail defect detection remains a challenge due to infrequent accident events that would result in defective parts and images. Contemporary researchers have addressed this data scarcity challenge by exploring rule-based and generative data augmentation models. Among these, Variational Autoencoder (VAE) models can generate realistic data without extensive baseline datasets for noise modeling. This study proposes a VAE-based synthetic image generation technique for rail defects, incorporating weight decay regularization and image reconstruction loss to prevent overfitting. The proposed method is applied to create a synthetic dataset for the Canadian Pacific Railway (CPR) with just 50 real samples across five classes. Remarkably, 500 synthetic samples are generated with a minimal reconstruction loss of 0.021. A Visual Transformer (ViT) model underwent fine-tuning using this synthetic CPR dataset, achieving high accuracy rates (98%-99%) in classifying the five defect classes. This research offers a promising solution to the data scarcity challenge in rail defect detection, showcasing the potential for robust ICS development in this domain.
Authors: Yunfeng Fan, Wenchao Xu, Haozhao Wang, Penghui Ruan, Song Guo
Selecting proper clients to participate in the iterative federated learning (FL) rounds is critical to effectively harness a broad range of distributed datasets. Existing client selection methods simply consider the variability among FL clients with uni-modal data, however, have yet to consider clients with multi-modalities. We reveal that traditional client selection scheme in MFL may suffer from a severe modality-level bias, which impedes the collaborative exploitation of multi-modal data, leading to insufficient local data exploration and global aggregation. To tackle this challenge, we propose a Client-wise Modality Selection scheme for MFL (CMSFed) that can comprehensively utilize information from each modality via avoiding such client selection bias caused by modality imbalance. Specifically, in each MFL round, the local data from different modalities are selectively employed to participate in local training and aggregation to mitigate potential modality imbalance of the global model. To approximate the fully aggregated model update in a balanced way, we introduce a novel local training loss function to enhance the weak modality and align the divergent feature spaces caused by inconsistent modality adoption strategies for different clients simultaneously. Then, a modality-level gradient decoupling method is designed to derive respective submodular functions to maintain the gradient diversity during the selection progress and balance MFL according to local modality imbalance in each iteration. Our extensive experiments showcase the superiority of CMSFed over baselines and its effectiveness in multi-modal data exploitation.
Authors: Yequan Zhao, Xian Xian, Xinling Yu, Ziyue Liu, Zhixiong Chen, Geza Kurczveil, Raymond G. Beausoleil, Zheng Zhang
Solving partial differential equations (PDEs) numerically often requires huge computing time, energy cost, and hardware resources in practical applications. This has limited their applications in many scenarios (e.g., autonomous systems, supersonic flows) that have a limited energy budget and require near real-time response. Leveraging optical computing, this paper develops an on-chip training framework for physics-informed neural networks (PINNs), aiming to solve high-dimensional PDEs with fJ/MAC photonic power consumption and ultra-low latency. Despite the ultra-high speed of optical neural networks, training a PINN on an optical chip is hard due to (1) the large size of photonic devices, and (2) the lack of scalable optical memory devices to store the intermediate results of back-propagation (BP). To enable realistic optical PINN training, this paper presents a scalable method to avoid the BP process. We also employ a tensor-compressed approach to improve the convergence and scalability of our optical PINN training. This training framework is designed with tensorized optical neural networks (TONN) for scalable inference acceleration and MZI phase-domain tuning for \textit{in-situ} optimization. Our simulation results of a 20-dim HJB PDE show that our photonic accelerator can reduce the number of MZIs by a factor of $1.17\times 10^3$, with only $1.36$ J and $1.15$ s to solve this equation. This is the first real-size optical PINN training framework that can be applied to solve high-dimensional PDEs.
Authors: Dehua Peng, Zhipeng Gui, Huayi Wu
The characteristics and interpretability of data become more abstract and complex as the dimensionality increases. Common patterns and relationships that hold in in low-dimensional space may fail to hold in higher-dimensional space. This phenomenon leads to a decreasing performance for the regression, classification or clustering models or algorithms, which is known as curse of dimensionality. Curse of dimensionality can be attributed to many causes. In this paper, we first summarize five challenges associated with manipulating high-dimensional data, and explains the potential causes for the failure of regression, classification or clustering tasks. Subsequently, we delve into two major causes of the curse of dimensionality, distance concentration and manifold effect, by performing theoretical and empirical analyses. The results demonstrate that nearest neighbor search (NNS) using three typical distance measurements, Minkowski distance, Chebyshev distance, and cosine distance, becomes meaningless as the dimensionality increases. Meanwhile, the data incorporates more redundant features, and the variance contribution of principal component analysis (PCA) is skewed towards a few dimensions. By interpreting the causes of the curse of dimensionality, we can better understand the limitations of current models and algorithms, and drive to improve the performance of data analysis and machine learning tasks in high-dimensional space.
Authors: Wanlin Cai, Yuxuan Liang, Xianggen Liu, Jianshuai Feng, Yuankai Wu
Multivariate time series forecasting poses an ongoing challenge across various disciplines. Time series data often exhibit diverse intra-series and inter-series correlations, contributing to intricate and interwoven dependencies that have been the focus of numerous studies. Nevertheless, a significant research gap remains in comprehending the varying inter-series correlations across different time scales among multiple time series, an area that has received limited attention in the literature. To bridge this gap, this paper introduces MSGNet, an advanced deep learning model designed to capture the varying inter-series correlations across multiple time scales using frequency domain analysis and adaptive graph convolution. By leveraging frequency domain analysis, MSGNet effectively extracts salient periodic patterns and decomposes the time series into distinct time scales. The model incorporates a self-attention mechanism to capture intra-series dependencies, while introducing an adaptive mixhop graph convolution layer to autonomously learn diverse inter-series correlations within each time scale. Extensive experiments are conducted on several real-world datasets to showcase the effectiveness of MSGNet. Furthermore, MSGNet possesses the ability to automatically learn explainable multi-scale inter-series correlations, exhibiting strong generalization capabilities even when applied to out-of-distribution samples.
Authors: Jaebak Kim
Experimental particle physics uses machine learning for many of tasks, where one application is to classify signal and background events. The classification can be used to bin an analysis region to enhance the expected significance for a mass resonance search. In natural language processing, one of the leading neural network architectures is the transformer. In this work, an event classifier transformer is proposed to bin an analysis region, in which the network is trained with special techniques. The techniques developed here can enhance the significance and reduce the correlation between the network's output and the reconstructed mass. It is found that this trained network can perform better than boosted decision trees and feed-forward networks.
Authors: D López-Pérez, A De Domenico, N Piovesan, M . Debbah
The energy consumption of mobile networks poses a critical challenge. Mitigating this concern necessitates the deployment and optimization of network energy-saving solutions, such as carrier shutdown, to dynamically manage network resources. Traditional optimization approaches encounter complexity due to factors like the large number of cells, stochastic traffic, channel variations, and intricate trade-offs. This paper introduces the simulated reality of communication networks (SRCON) framework, a novel, data-driven modeling paradigm that harnesses live network data and employs a blend of machine learning (ML)- and expert-based models. These mix of models accurately characterizes the functioning of network components, and predicts network energy efficiency and user equipment (UE) quality of service for any energy carrier shutdown configuration in a specific network. Distinguishing itself from existing methods, SRCON eliminates the reliance on expensive expert knowledge, drive testing, or incomplete maps for predicting network performance. This paper details the pipeline employed by SRCON to decompose the large network energy efficiency modeling problem into ML and expert-based submodels. It demonstrates how, by embracing stochasticity, and carefully crafting the relationship between such submodels, the overall computational complexity can be reduced and prediction accuracy enhanced. Results derived from real network data underscore the paradigm shift introduced by SRCON, showcasing significant gains over a state-of-the art method used by a operator for network energy efficiency modeling. The reliability of this local, data-driven modeling of the network proves to be a key asset for network energy-saving optimization.
Authors: Chenxi Zhao, Min Sheng, Junyu Liu, Tianshu Chu, Jiandong Li
The limited energy and computing resources of unmanned aerial vehicles (UAVs) hinder the application of aerial artificial intelligence. The utilization of split inference in UAVs garners significant attention due to its effectiveness in mitigating computing and energy requirements. However, achieving energy-efficient split inference in UAVs remains complex considering of various crucial parameters such as energy level and delay constraints, especially involving multiple tasks. In this paper, we present a two-timescale approach for energy minimization in split inference, where discrete and continuous variables are segregated into two timescales to reduce the size of action space and computational complexity. This segregation enables the utilization of tiny reinforcement learning (TRL) for selecting discrete transmission modes for sequential tasks. Moreover, optimization programming (OP) is embedded between TRL's output and reward function to optimize the continuous transmit power. Specifically, we replace the optimization of transmit power with that of transmission time to decrease the computational complexity of OP since we reveal that energy consumption monotonically decreases with increasing transmission time. The replacement significantly reduces the feasible region and enables a fast solution according to the closed-form expression for optimal transmit power. Simulation results show that the proposed algorithm can achieve a higher probability of successful task completion with lower energy consumption.
Authors: Nikhil Sardana, Jonathan Frankle
Large language model (LLM) scaling laws are empirical formulas that estimate changes in model quality as a result of increasing parameter count and training data. However, these formulas, including the popular DeepMind Chinchilla scaling laws, neglect to include the cost of inference. We modify the Chinchilla scaling laws to calculate the optimal LLM parameter count and pre-training data size to train and deploy a model of a given quality and inference demand. We conduct our analysis both in terms of a compute budget and real-world costs and find that LLM researchers expecting reasonably large inference demand (~1B requests) should train models smaller and longer than Chinchilla-optimal.
Authors: Silvan David Peter
Symbolic Music Alignment is the process of matching performed MIDI notes to corresponding score notes. In this paper, we introduce a reinforcement learning (RL)-based online symbolic music alignment technique. The RL agent - an attention-based neural network - iteratively estimates the current score position from local score and performance contexts. For this symbolic alignment task, environment states can be sampled exhaustively and the reward is dense, rendering a formulation as a simplified offline RL problem straightforward. We evaluate the trained agent in three ways. First, in its capacity to identify correct score positions for sampled test contexts; second, as the core technique of a complete algorithm for symbolic online note-wise alignment; and finally, as a real-time symbolic score follower. We further investigate the pitch-based score and performance representations used as the agent's inputs. To this end, we develop a second model, a two-step Dynamic Time Warping (DTW)-based offline alignment algorithm leveraging the same input representation. The proposed model outperforms a state-of-the-art reference model of offline symbolic music alignment.
Authors: Alejandro Moreo, Pablo González, Juan José del Coz
Several disciplines, like the social sciences, epidemiology, sentiment analysis, or market research, are interested in knowing the distribution of the classes in a population rather than the individual labels of the members thereof. Quantification is the supervised machine learning task concerned with obtaining accurate predictors of class prevalence, and to do so particularly in the presence of label shift. The distribution-matching (DM) approaches represent one of the most important families among the quantification methods that have been proposed in the literature so far. Current DM approaches model the involved populations by means of histograms of posterior probabilities. In this paper, we argue that their application to the multiclass setting is suboptimal since the histograms become class-specific, thus missing the opportunity to model inter-class information that may exist in the data. We propose a new representation mechanism based on multivariate densities that we model via kernel density estimation (KDE). The experiments we have carried out show our method, dubbed KDEy, yields superior quantification performance with respect to previous DM approaches. We also investigate the KDE-based representation within the maximum likelihood framework and show KDEy often shows superior performance with respect to the expectation-maximization method for quantification, arguably the strongest contender in the quantification arena to date.
Authors: Dimitrios Psychogyios, Emanuele Colleoni, Beatrice Van Amsterdam, Chih-Yang Li, Shu-Yu Huang, Yuchong Li, Fucang Jia, Baosheng Zou, Guotai Wang, Yang Liu, Maxence Boels, Jiayu Huo, Rachel Sparks, Prokar Dasgupta, Alejandro Granados, Sebastien Ourselin, Mengya Xu, An Wang, Yanan Wu, Long Bai, Hongliang Ren, Atsushi Yamada, Yuriko Harai, Yuto Ishikawa, Kazuyuki Hayashi, Jente Simoens, Pieter DeBacker, Francesco Cisternino, Gabriele Furnari, Alex Mottrie, Federica Ferraguti, Satoshi Kondo, Satoshi Kasai, Kousuke Hirasawa, Soohee Kim, Seung Hyun Lee, Kyu Eun Lee, Hyoun-Joong Kong, Kui Fu, Chao Li, Shan An, Stefanie Krell, Sebastian Bodenstedt, Nicolas Ayobi, Alejandra Perez, Santiago Rodriguez, Juanita Puentes, Pablo Arbelaez, Omid Mohareri, Danail Stoyanov
Surgical tool segmentation and action recognition are fundamental building blocks in many computer-assisted intervention applications, ranging from surgical skills assessment to decision support systems. Nowadays, learning-based action recognition and segmentation approaches outperform classical methods, relying, however, on large, annotated datasets. Furthermore, action recognition and tool segmentation algorithms are often trained and make predictions in isolation from each other, without exploiting potential cross-task relationships. With the EndoVis 2022 SAR-RARP50 challenge, we release the first multimodal, publicly available, in-vivo, dataset for surgical action recognition and semantic instrumentation segmentation, containing 50 suturing video segments of Robotic Assisted Radical Prostatectomy (RARP). The aim of the challenge is twofold. First, to enable researchers to leverage the scale of the provided dataset and develop robust and highly accurate single-task action recognition and tool segmentation approaches in the surgical domain. Second, to further explore the potential of multitask-based learning approaches and determine their comparative advantage against their single-task counterparts. A total of 12 teams participated in the challenge, contributing 7 action recognition methods, 9 instrument segmentation techniques, and 4 multitask approaches that integrated both action recognition and instrument segmentation.
Authors: Dipankar Sarkar
This paper aims to introduce and analyze the Viz system in a comprehensive way, a novel system architecture that integrates Quantized Low-Rank Adapters (QLoRA) to fine-tune large language models (LLM) within a legally compliant and resource efficient marketplace. Viz represents a significant contribution to the field of artificial intelligence, particularly in addressing the challenges of computational efficiency, legal compliance, and economic sustainability in the utilization and monetization of LLMs. The paper delineates the scholarly discourse and developments that have informed the creation of Viz, focusing primarily on the advancements in LLM models, copyright issues in AI training (NYT case, 2023), and the evolution of model fine-tuning techniques, particularly low-rank adapters and quantized low-rank adapters, to create a sustainable and economically compliant framework for LLM utilization. The economic model it proposes benefits content creators, AI developers, and end-users, delineating a harmonious integration of technology, economy, and law, offering a comprehensive solution to the complex challenges of today's AI landscape.
Authors: Yuxiao Hu, Qian Li, Xiaodan Shi, Jinyue Yan, Yuntian Chen
Accurate air quality forecasting is crucial for public health, environmental monitoring and protection, and urban planning. However, existing methods fail to effectively utilize multi-scale information, both spatially and temporally. Spatially, there is a lack of integration between individual monitoring stations and city-wide scales. Temporally, the periodic nature of air quality variations is often overlooked or inadequately considered. To address these limitations, we present a novel Multi-spatial Multi-temporal air quality forecasting method based on Graph Convolutional Networks and Gated Recurrent Units (M2G2), bridging the gap in air quality forecasting across spatial and temporal scales. The proposed framework consists of two modules: Multi-scale Spatial GCN (MS-GCN) for spatial information fusion and Multi-scale Temporal GRU(MT-GRU) for temporal information integration. In the spatial dimension, the MS-GCN module employs a bidirectional learnable structure and a residual structure, enabling comprehensive information exchange between individual monitoring stations and the city-scale graph. Regarding the temporal dimension, the MT-GRU module adaptively combines information from different temporal scales through parallel hidden states. Leveraging meteorological indicators and four air quality indicators, we present comprehensive comparative analyses and ablation experiments, showcasing the higher accuracy of M2G2 in comparison to nine currently available advanced approaches across all aspects. The improvements of M2G2 over the second-best method on RMSE of the 24h/48h/72h are as follows: PM2.5: (7.72%, 6.67%, 10.45%); PM10: (6.43%, 5.68%, 7.73%); NO2: (5.07%, 7.76%, 16.60%); O3: (6.46%, 6.86%, 9.79%). Furthermore, we demonstrate the effectiveness of each module of M2G2 by ablation study.
Authors: Sayantan Auddy, Sebastian Bergner, Justus Piater
In continual learning from demonstration (CLfD), a robot learns a sequence of real-world motion skills continually from human demonstrations. Recently, hypernetworks have been successful in solving this problem. In this paper, we perform an exploratory study of the effects of different optimizers, initializers, and network architectures on the continual learning performance of hypernetworks for CLfD. Our results show that adaptive learning rate optimizers work well, but initializers specially designed for hypernetworks offer no advantages for CLfD. We also show that hypernetworks that are capable of stable trajectory predictions are robust to different network architectures. Our open-source code is available at https://github.com/sebastianbergner/ExploringCLFD.
Authors: Qifang Zhao, Weidong Ren, Tianyu Li, Xiaoxiao Xu, Hong Liu
We introduce \textit{GraphGPT}, a novel model for Graph learning by self-supervised Generative Pre-training Transformers. Our model transforms each graph or sampled subgraph into a sequence of tokens representing the node, edge and attributes reversibly using the Eulerian path first. Then we feed the tokens into a standard transformer decoder and pre-train it with the next-token-prediction (NTP) task. Lastly, we fine-tune the GraphGPT model with the supervised tasks. This intuitive, yet effective model achieves superior or close results to the state-of-the-art methods for the graph-, edge- and node-level tasks on the large scale molecular dataset PCQM4Mv2, the protein-protein association dataset ogbl-ppa and the ogbn-proteins dataset from the Open Graph Benchmark (OGB). Furthermore, the generative pre-training enables us to train GraphGPT up to 400M+ parameters with consistently increasing performance, which is beyond the capability of GNNs and previous graph transformers. The source code and pre-trained checkpoints will be released soon\footnote{\url{https://github.com/alibaba/graph-gpt}} to pave the way for the graph foundation model research, and also to assist the scientific discovery in pharmaceutical, chemistry, material and bio-informatics domains, etc.
Authors: Massinissa Hamidi, Aomar Osmani
In this paper we will discuss metalearning and how we can go beyond the current classical learning paradigm. We will first address the importance of inductive biases in the learning process and what is at stake: the quantities of data necessary to learn. We will subsequently see the importance of choosing suitable parameterizations to end up with well-defined learning processes. Especially since in the context of real-world applications, we face numerous biases due, e.g., to the specificities of sensors, the heterogeneity of data sources, the multiplicity of points of view, etc. This will lead us to the idea of exploiting the structuring of the concepts to be learned in order to organize the learning process that we published previously. We conclude by discussing the perspectives around parameter-tying schemes and the emergence of universal aspects in the models thus learned.
Authors: Shun Liu, Kexin Wu, Chufeng Jiang, Bin Huang, Danqing Ma
In the realm of cryptocurrency, the prediction of Bitcoin prices has garnered substantial attention due to its potential impact on financial markets and investment strategies. This paper propose a comparative study on hybrid machine learning algorithms and leverage on enhancing model interpretability. Specifically, linear regression(OLS, LASSO), long-short term memory(LSTM), decision tree regressors are introduced. Through the grounded experiments, we observe linear regressor achieves the best performance among candidate models. For the interpretability, we carry out a systematic overview on the preprocessing techniques of time-series statistics, including decomposition, auto-correlational function, exponential triple forecasting, which aim to excavate latent relations and complex patterns appeared in the financial time-series forecasting. We believe this work may derive more attention and inspire more researches in the realm of time-series analysis and its realistic applications.
Authors: Vansh Sharma, Venkat Raman
This research explores the integration of large language models (LLMs) into scientific data assimilation, focusing on combustion science as a case study. Leveraging foundational models integrated with Retrieval-Augmented Generation (RAG) framework, the study introduces an approach to process diverse combustion research data, spanning experimental studies, simulations, and literature. The multifaceted nature of combustion research emphasizes the critical role of knowledge processing in navigating and extracting valuable information from a vast and diverse pool of sources. The developed approach minimizes computational and economic expenses while optimizing data privacy and accuracy. It incorporates prompt engineering and offline open-source LLMs, offering user autonomy in selecting base models. The study provides a thorough examination of text segmentation strategies, conducts comparative studies between LLMs, and explores various optimized prompts to demonstrate the effectiveness of the framework. By incorporating an external database, the framework outperforms a conventional LLM in generating accurate responses and constructing robust arguments. Additionally, the study delves into the investigation of optimized prompt templates for the purpose of efficient extraction of scientific literature. The research addresses concerns related to hallucinations and false research articles by introducing a custom workflow developed with a detection algorithm to filter out inaccuracies. Despite identified areas for improvement, the framework consistently delivers accurate domain-specific responses with minimal human oversight. The prompt-agnostic approach introduced holds promise for future deliberations. The study underscores the significance of integrating LLMs and knowledge processing techniques in scientific research, providing a foundation for advancements in data assimilation and utilization.
Authors: Run Shao, Cheng Yang, Qiujun Li, Qing Zhu, Yongjun Zhang, YanSheng Li, Yu Liu, Yong Tang, Dapeng Liu, Shizhong Yang, Jiayi Ma, Haifeng Li
For a long time, due to the high heterogeneity in structure and semantics among various spatiotemporal modal data, the joint interpretation of multimodal spatiotemporal data has been an extremely challenging problem. The primary challenge resides in striking a trade-off between the cohesion and autonomy of diverse modalities, and this trade-off exhibits a progressively nonlinear nature as the number of modalities expands. We introduce the Language as Reference Framework (LaRF), a fundamental principle for constructing a multimodal unified model, aiming to strike a trade-off between the cohesion and autonomy among different modalities. We propose a multimodal spatiotemporal general artificial intelligence model, called AllSpark. Our model integrates thirteen different modalities into a unified framework, including 1D (text, code), 2D (RGB, infrared, SAR, multispectral, hyperspectral, tables, graphs, trajectory, oblique photography), and 3D (point clouds, videos) modalities. To achieve modal cohesion, AllSpark uniformly maps diverse modal features to the language modality. In addition, we design modality-specific prompts to guide multi-modal large language models in accurately perceiving multimodal data. To maintain modality autonomy, AllSpark introduces modality-specific encoders to extract the tokens of various spatiotemporal modalities. And modal bridge is employed to achieve dimensional projection from each modality to the language modality. Finally, observing a gap between the model's interpretation and downstream tasks, we designed task heads to enhance the model's generalization capability on specific downstream tasks. Experiments indicate that AllSpark achieves competitive accuracy in modalities such as RGB and trajectory compared to state-of-the-art models.
Authors: A Ch Madhusudanarao, Rahul Singh
We study chance constrained optimization problems $\min_x f(x)$ s.t. $P(\left\{ \theta: g(x,\theta)\le 0 \right\})\ge 1-\epsilon$ where $\epsilon\in (0,1)$ is the violation probability, when the distribution $P$ is not known to the decision maker (DM). When the DM has access to a set of distributions $\mathcal{U}$ such that $P$ is contained in $\mathcal{U}$, then the problem is known as the ambiguous chance-constrained problem \cite{erdougan2006ambiguous}. We study ambiguous chance-constrained problem for the case when $\mathcal{U}$ is of the form $\left\{\mu:\frac{\mu (y)}{\nu(y)}\leq C, \forall y\in\Theta, \mu(y)\ge 0\right\}$, where $\nu$ is a ``reference distribution.'' We show that in this case the original problem can be ``well-approximated'' by a sampled problem in which $N$ i.i.d. samples of $\theta$ are drawn from $\nu$, and the original constraint is replaced with $g(x,\theta_i)\le 0,~i=1,2,\ldots,N$. We also derive the sample complexity associated with this approximation, i.e., for $\epsilon,\delta>0$ the number of samples which must be drawn from $\nu$ so that with a probability greater than $1-\delta$ (over the randomness of $\nu$), the solution obtained by solving the sampled program yields an $\epsilon$-feasible solution for the original chance constrained problem.
Authors: Omid Rohanian, Mohammadmahdi Nouriborji, David A. Clifton
Large Language Models (LLMs), particularly those similar to ChatGPT, have significantly influenced the field of Natural Language Processing (NLP). While these models excel in general language tasks, their performance in domain-specific downstream tasks such as biomedical and clinical Named Entity Recognition (NER), Relation Extraction (RE), and Medical Natural Language Inference (NLI) is still evolving. In this context, our study investigates the potential of instruction tuning for biomedical language processing, applying this technique to two general LLMs of substantial scale. We present a comprehensive, instruction-based model trained on a dataset that consists of approximately $200,000$ instruction-focused samples. This dataset represents a carefully curated compilation of existing data, meticulously adapted and reformatted to align with the specific requirements of our instruction-based tasks. This initiative represents an important step in utilising such models to achieve results on par with specialised encoder-only models like BioBERT and BioClinicalBERT for various classical biomedical NLP tasks. Our work includes an analysis of the dataset's composition and its impact on model performance, providing insights into the intricacies of instruction tuning. By sharing our codes, models, and the distinctively assembled instruction-based dataset, we seek to encourage ongoing research and development in this area.
Authors: Yash Bingi, Yiqiao Yin
Large Lanugage Models (LLMs) are gaining increasing popularity in a variety of use cases, from language understanding and writing to assistance in application development. One of the most important aspects for optimal funcionality of LLMs is embedding layers. Word embeddings are distributed representations of words in a continuous vector space. In the context of LLMs, words or tokens from the input text are transformed into high-dimensional vectors using unique algorithms specific to the model. Our research examines the embedding algorithms from leading companies in the industry, such as OpenAI, Google's PaLM, and BERT. Using medical data, we have analyzed similarity scores of each embedding layer, observing differences in performance among each algorithm. To enhance each model and provide an additional encoding layer, we also implemented Siamese Neural Networks. After observing changes in performance with the addition of the model, we measured the carbon footage per epoch of training. The carbon footprint associated with large language models (LLMs) is a significant concern, and should be taken into consideration when selecting algorithms for a variety of use cases. Overall, our research compared the accuracy different, leading embedding algorithms and their carbon footage, allowing for a holistic review of each embedding algorithm.
Authors: Rachel Redberg, Antti Koskela, Yu-Xiang Wang
In the arena of privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) has outstripped the objective perturbation mechanism in popularity and interest. Though unrivaled in versatility, DP-SGD requires a non-trivial privacy overhead (for privately tuning the model's hyperparameters) and a computational complexity which might be extravagant for simple models such as linear and logistic regression. This paper revamps the objective perturbation mechanism with tighter privacy analyses and new computational tools that boost it to perform competitively with DP-SGD on unconstrained convex generalized linear problems.
Authors: Ying Sheng, Shiyi Cao, Dacheng Li, Banghua Zhu, Zhuohan Li, Danyang Zhuo, Joseph E. Gonzalez, Ion Stoica
High-demand LLM inference services (e.g., ChatGPT and BARD) support a wide range of requests from short chat conversations to long document reading. To ensure that all client requests are processed fairly, most major LLM inference services have request rate limits, to ensure that no client can dominate the request queue. However, this rudimentary notion of fairness also results in under-utilization of the resources and poor client experience when there is spare capacity. While there is a rich literature on fair scheduling, serving LLMs presents new challenges due to their unpredictable request lengths and their unique batching characteristics on parallel accelerators. This paper introduces the definition of LLM serving fairness based on a cost function that accounts for the number of input and output tokens processed. To achieve fairness in serving, we propose a novel scheduling algorithm, the Virtual Token Counter (VTC), a fair scheduler based on the continuous batching mechanism. We prove a 2x tight upper bound on the service difference between two backlogged clients, adhering to the requirement of work-conserving. Through extensive experiments, we demonstrate the superior performance of VTC in ensuring fairness, especially in contrast to other baseline methods, which exhibit shortcomings under various conditions.
Authors: Julian B. B. Beckmann, Mick D. Mantle, Andrew J. Sederman, Lynn F. Gladden
Sub-sampling is applied to simulated $T_1$-$D$ NMR signals and its influence on inversion performance is evaluated. For this different levels of sub-sampling were employed ranging from the fully sampled signal down to only less than two percent of the original data points. This was combined with multiple sample schemes including fully random sampling, truncation and a combination of both. To compare the performance of different inversion algorithms, the so-generated sub-sampled signals were inverted using Tikhonov regularization, modified total generalized variation (MTGV) regularization, deep learning and a combination of deep learning and Tikhonov regularization. Further, the influence of the chosen cost function on the relative inversion performance was investigated. Overall, it could be shown that for a vast majority of instances, deep learning clearly outperforms regularization based inversion methods, if the signal is fully or close to fully sampled. However, in the case of significantly sub-sampled signals regularization yields better inversion performance than its deep learning counterpart with MTGV clearly prevailing over Tikhonov. Additionally, fully random sampling could be identified as the best overall sampling scheme independent of the inversion method. Finally, it could also be shown that the choice of cost function does vastly influence the relative rankings of the tested inversion algorithms highlighting the importance of choosing the cost function accordingly to experimental intentions.
Authors: Tim Z. Xiao, Weiyang Liu, Robert Bamler
Bayesian neural networks (BNNs) are a principled approach to modeling predictive uncertainties in deep learning, which are important in safety-critical applications. Since exact Bayesian inference over the weights in a BNN is intractable, various approximate inference methods exist, among which sampling methods such as Hamiltonian Monte Carlo (HMC) are often considered the gold standard. While HMC provides high-quality samples, it lacks interpretable summary statistics because its sample mean and variance is meaningless in neural networks due to permutation symmetry. In this paper, we first show that the role of permutations can be meaningfully quantified by a number of transpositions metric. We then show that the recently proposed rebasin method allows us to summarize HMC samples into a compact representation that provides a meaningful explicit uncertainty estimate for each weight in a neural network, thus unifying sampling methods with variational inference. We show that this compact representation allows us to compare trained BNNs directly in weight space across sampling methods and variational inference, and to efficiently prune neural networks trained without explicit Bayesian frameworks by exploiting uncertainty estimates from HMC.
Authors: Zhiyuan Wu, Tianliu He, Sheng Sun, Yuwei Wang, Min Liu, Bo Gao, Xuefeng Jiang
Federated Learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data. Mainstream FL methodologies overlook the dynamic nature of real-world data, particularly its tendency to grow in volume and diversify in classes over time. This oversight results in FL methods suffering from catastrophic forgetting, where models inadvertently discard previously learned information upon assimilating new data. In response to this challenge, we propose a novel Federated Class-Incremental Learning (FCIL) method, named FCIL with New-Class Augmented Self-Distillation (FedNASD). FedNASD combines new class scores, which are inferred from current models, with historical models' predictions. Based on the combined past and present knowledge, it incorporates self-distillation over models on clients, aiming to achieve effective knowledge transfer from historical models to current models. Theoretical analysis demonstrates that FedNASD is equivalent to modeling old class scores as conditional probabilities in the absence of new classes. Additionally, it reconciles the predictions of new classes with current models to refine the conditional probabilities of historical scores where new classes do not exist. Empirical experiments demonstrate the superiority of FedNASD over four baseline algorithms in reducing the average forgetting rate and boosting global accuracy.
Authors: Guangji Bai, Zheng Chai, Chen Ling, Shiyu Wang, Jiaying Lu, Nan Zhang, Tingwei Shi, Ziyang Yu, Mengdan Zhu, Yifei Zhang, Carl Yang, Yue Cheng, Liang Zhao
The burgeoning field of Large Language Models (LLMs), exemplified by sophisticated models like OpenAI's ChatGPT, represents a significant advancement in artificial intelligence. These models, however, bring forth substantial challenges in the high consumption of computational, memory, energy, and financial resources, especially in environments with limited resource capabilities. This survey aims to systematically address these challenges by reviewing a broad spectrum of techniques designed to enhance the resource efficiency of LLMs. We categorize methods based on their optimization focus: computational, memory, energy, financial, and network resources and their applicability across various stages of an LLM's lifecycle, including architecture design, pretraining, finetuning, and system design. Additionally, the survey introduces a nuanced categorization of resource efficiency techniques by their specific resource types, which uncovers the intricate relationships and mappings between various resources and corresponding optimization techniques. A standardized set of evaluation metrics and datasets is also presented to facilitate consistent and fair comparisons across different models and techniques. By offering a comprehensive overview of the current sota and identifying open research avenues, this survey serves as a foundational reference for researchers and practitioners, aiding them in developing more sustainable and efficient LLMs in a rapidly evolving landscape.
Authors: Honghao Wei, Xiyue Peng, Xin Liu, Arnob Ghosh
We propose a Safe Adversarial Trained Actor Critic (SATAC) algorithm for offline reinforcement learning (RL) with general function approximation in the presence of limited data coverage. SATAC operates as a two-player Stackelberg game featuring a refined objective function. The actor (leader player) optimizes the policy against two adversarially trained value critics (follower players), who focus on scenarios where the actor's performance is inferior to the behavior policy. Our framework provides both theoretical guarantees and a robust deep-RL implementation. Theoretically, we demonstrate that when the actor employs a no-regret optimization oracle, SATAC achieves two guarantees: (i) For the first time in the offline RL setting, we establish that SATAC can produce a policy that outperforms the behavior policy while maintaining the same level of safety, which is critical to designing an algorithm for offline RL. (ii) We demonstrate that the algorithm guarantees policy improvement across a broad range of hyperparameters, indicating its practical robustness. Additionally, we offer a practical version of SATAC and compare it with existing state-of-the-art offline safe-RL algorithms in continuous control environments. SATAC outperforms all baselines across a range of tasks, thus validating the theoretical performance.
Authors: Razieh Rezaei, Alireza Dizaji, Ashkan Khakzar, Anees Kazi, Nassir Navab, Daniel Rueckert
Neural networks are increasingly finding their way into the realm of graphs and modeling relationships between features. Concurrently graph neural network explanation approaches are being invented to uncover relationships between the nodes of the graphs. However, there is a disparity between the existing attribution methods, and it is unclear which attribution to trust. Therefore research has introduced evaluation experiments that assess them from different perspectives. In this work, we assess attribution methods from a perspective not previously explored in the graph domain: retraining. The core idea is to retrain the network on important (or not important) relationships as identified by the attributions and evaluate how networks can generalize based on these relationships. We reformulate the retraining framework to sidestep issues lurking in the previous formulation and propose guidelines for correct analysis. We run our analysis on four state-of-the-art GNN attribution methods and five synthetic and real-world graph classification datasets. The analysis reveals that attributions perform variably depending on the dataset and the network. Most importantly, we observe that the famous GNNExplainer performs similarly to an arbitrary designation of edge importance. The study concludes that the retraining evaluation cannot be used as a generalized benchmark and recommends it as a toolset to evaluate attributions on a specifically addressed network, dataset, and sparsity.
Authors: Yulin Shao, Chenghong Bian, Li Yang, Qianqian Yang, Zhaoyang Zhang, Deniz Gunduz
Acquisition and processing of point clouds (PCs) is a crucial enabler for many emerging applications reliant on 3D spatial data, such as robot navigation, autonomous vehicles, and augmented reality. In most scenarios, PCs acquired by remote sensors must be transmitted to an edge server for fusion, segmentation, or inference. Wireless transmission of PCs not only puts on increased burden on the already congested wireless spectrum, but also confronts a unique set of challenges arising from the irregular and unstructured nature of PCs. In this paper, we meticulously delineate these challenges and offer a comprehensive examination of existing solutions while candidly acknowledging their inherent limitations. In response to these intricacies, we proffer four pragmatic solution frameworks, spanning advanced techniques, hybrid schemes, and distributed data aggregation approaches. In doing so, our goal is to chart a path toward efficient, reliable, and low-latency wireless PC transmission.
Authors: Hongcheng Liu, Jindong Tong
We study the sample complexity of sample average approximation (SAA) and its simple variations, referred to as the regularized SAA (RSAA), in solving convex and strongly convex stochastic programming (SP) problems under heavy-tailed-ness, non-Lipschitz-ness, and/or high dimensionality. The presence of such irregularities underscores critical vacua in the literature. In response, this paper presents three sets of results: First, we show that the (R)SAA is effective even if the objective function is not necessarily Lipschitz and the underlying distribution admits some bounded central moments only at (near-)optimal solutions. Second, when the SP's objective function is the sum of a smooth term and a Lipschitz term, we prove that the (R)SAA's sample complexity is completely independent from any complexity measures (e.g., the covering number) of the feasible region. Third, we explicate the (R)SAA's sample complexities with regard to the dependence on dimensionality $d$: When some $p$th ($p\geq 2$) central moment of the underlying distribution is bounded, we show that the required sample size grows at a rate no worse than $\mathcal O\left(p d^{2/p}\right)$ under any one of the three structural assumptions: (i) strong convexity w.r.t. the $q$-norm ($q\geq 1$); (ii) the combination of restricted strong convexity and sparsity; and (iii) a dimension-insensitive $q$-norm of an optimal solution. In both cases of (i) and (iii), it is further required that $p\leq q/(q-1)$. As a direct implication, the (R)SAA's complexity becomes (poly-)logarithmic in $d$, whenever $p\geq c\cdot \ln d$ is admissible for some constant $c>0$. These new results deviate from the SAA's typical sample complexities that grow polynomially with $d$. Part of our proof is based on the average-replace-one (RO) stability, which appears to be novel for the (R)SAA's analyses.
Authors: Haodong Li, Gelei Deng, Yi Liu, Kailong Wang, Yuekang Li, Tianwei Zhang, Yang Liu, Guoai Xu, Guosheng Xu, Haoyu Wang
Pre-training, which utilizes extensive and varied datasets, is a critical factor in the success of Large Language Models (LLMs) across numerous applications. However, the detailed makeup of these datasets is often not disclosed, leading to concerns about data security and potential misuse. This is particularly relevant when copyrighted material, still under legal protection, is used inappropriately, either intentionally or unintentionally, infringing on the rights of the authors.
In this paper, we introduce a detailed framework designed to detect and assess the presence of content from potentially copyrighted books within the training datasets of LLMs. This framework also provides a confidence estimation for the likelihood of each content sample's inclusion. To validate our approach, we conduct a series of simulated experiments, the results of which affirm the framework's effectiveness in identifying and addressing instances of content misuse in LLM training processes. Furthermore, we investigate the presence of recognizable quotes from famous literary works within these datasets. The outcomes of our study have significant implications for ensuring the ethical use of copyrighted materials in the development of LLMs, highlighting the need for more transparent and responsible data management practices in this field.
Authors: Samuel Schmidgall, Ji Woong Kim, Alan Kuntz, Ahmed Ezzat Ghazi, Axel Krieger
The dominant paradigm for end-to-end robot learning focuses on optimizing task-specific objectives that solve a single robotic problem such as picking up an object or reaching a target position. However, recent work on high-capacity models in robotics has shown promise toward being trained on large collections of diverse and task-agnostic datasets of video demonstrations. These models have shown impressive levels of generalization to unseen circumstances, especially as the amount of data and the model complexity scale. Surgical robot systems that learn from data have struggled to advance as quickly as other fields of robot learning for a few reasons: (1) there is a lack of existing large-scale open-source data to train models, (2) it is challenging to model the soft-body deformations that these robots work with during surgery because simulation cannot match the physical and visual complexity of biological tissue, and (3) surgical robots risk harming patients when tested in clinical trials and require more extensive safety measures. This perspective article aims to provide a path toward increasing robot autonomy in robot-assisted surgery through the development of a multi-modal, multi-task, vision-language-action model for surgical robots. Ultimately, we argue that surgical robots are uniquely positioned to benefit from general-purpose models and provide three guiding actions toward increased autonomy in robot-assisted surgery.
Authors: Wiem Haj Ammar, Aicha Boujnah, Antoine Baron, Aimen Boubaker, Adel Kalboussi, Kamal Lmimouni, Sebastien Pecqueur
Identifying relevant machine-learning features for multi-sensing platforms is both an applicative limitation to recognize environments and a necessity to interpret the physical relevance of transducers' complementarity in their information processing. Particularly for long acquisitions, feature extraction must be fully automatized without human intervention and resilient to perturbations without increasing significantly the computational cost of a classifier. In this study, we investigate on the relative resistance and current modulation of a 24-dimensional conductimetric electronic nose, which uses the exponential moving average as a floating reference in a low-cost information descriptor for environment recognition. In particular, we identified that depending on the structure of a linear classifier, the 'modema' descriptor is optimized for different material sensing elements' contributions to classify information patterns. The low-pass filtering optimization leads to opposite behaviors between unsupervised and supervised learning: the latter one favors longer integration of the reference, allowing to recognize five different classes over 90%, while the first one prefers using the latest events as its reference to clusterize patterns by environment nature. Its electronic implementation shall greatly diminish the computational requirements of conductimetric electronic noses for on-board environment recognition without human supervision.
Authors: Mohamed Elmahallawy, Tie Luo, Khaled Ramadan
Space AI has become increasingly important and sometimes even necessary for government, businesses, and society. An active research topic under this mission is integrating federated learning (FL) with satellite communications (SatCom) so that numerous low Earth orbit (LEO) satellites can collaboratively train a machine learning model. However, the special communication environment of SatCom leads to a very slow FL training process up to days and weeks. This paper proposes NomaFedHAP, a novel FL-SatCom approach tailored to LEO satellites, that (1) utilizes high-altitude platforms (HAPs) as distributed parameter servers (PS) to enhance satellite visibility, and (2) introduces non-orthogonal multiple access (NOMA) into LEO to enable fast and bandwidth-efficient model transmissions. In addition, NomaFedHAP includes (3) a new communication topology that exploits HAPs to bridge satellites among different orbits to mitigate the Doppler shift, and (4) a new FL model aggregation scheme that optimally balances models between different orbits and shells. Moreover, we (5) derive a closed-form expression of the outage probability for satellites in near and far shells, as well as for the entire system. Our extensive simulations have validated the mathematical analysis and demonstrated the superior performance of NomaFedHAP in achieving fast and efficient FL model convergence with high accuracy as compared to the state-of-the-art.
Authors: Kazuki Nakajima, Takeaki Uno
Hypergraphs are a representation of complex systems involving interactions among more than two entities and allow to investigation of higher-order structure and dynamics in real-world complex systems. Community structure is a common property observed in empirical networks in various domains. Stochastic block models have been employed to investigate community structure in networks. Node attribute data, often accompanying network data, has been found to potentially enhance the learning of community structure in dyadic networks. In this study, we develop a statistical framework that incorporates node attribute data into the learning of community structure in a hypergraph, employing a stochastic block model. We demonstrate that our model, which we refer to as HyperNEO, enhances the learning of community structure in synthetic and empirical hypergraphs when node attributes are sufficiently associated with the communities. Furthermore, we found that applying a dimensionality reduction method, UMAP, to the learned representations obtained using stochastic block models, including our model, maps nodes into a two-dimensional vector space while largely preserving community structure in empirical hypergraphs. We expect that our framework will broaden the investigation and understanding of higher-order community structure in real-world complex systems.
Authors: Xin Chen, Jason M. Klusowski
This paper introduces an iterative algorithm designed to train additive models with favorable memory storage and computational requirements. The algorithm can be viewed as the functional counterpart of stochastic gradient descent, applied to the coefficients of a truncated basis expansion of the component functions. We show that the resulting estimator satisfies an oracle inequality that allows for model mispecification. In the well-specified setting, by choosing the learning rate carefully across three distinct stages of training, we prove that its risk is minimax optimal in terms of the dependence on the dimensionality of the data and the size of the training sample.
Authors: Hamish Haggerty, Rohitash Chandra
Cancer diagnosis is a well-studied problem in machine learning since early detection of cancer is often the determining factor in prognosis. Supervised deep learning achieves excellent results in cancer image classification, usually through transfer learning. However, these models require large amounts of labelled data and for several types of cancer, large labelled datasets do not exist. In this paper, we demonstrate that a model pre-trained using a self-supervised learning algorithm known as Barlow Twins can outperform the conventional supervised transfer learning pipeline. We juxtapose two base models: i) pretrained in a supervised fashion on ImageNet; ii) pretrained in a self-supervised fashion on ImageNet. Both are subsequently fine tuned on a small labelled skin lesion dataset and evaluated on a large test set. We achieve a mean test accuracy of 70\% for self-supervised transfer in comparison to 66\% for supervised transfer. Interestingly, boosting performance further is possible by self-supervised pretraining a second time (on unlabelled skin lesion images) before subsequent fine tuning. This hints at an alternative path to collecting more labelled data in settings where this is challenging - namely just collecting more unlabelled images. Our framework is applicable to cancer image classification models in the low-labelled data regime.
Authors: Kiran Voderhobli Holla, Chaithanya Kumar, Aryan Singh
This paper describes the architecture and systems built towards solving the SemEval 2023 Task 2: MultiCoNER II (Multilingual Complex Named Entity Recognition) [1]. We evaluate two approaches (a) a traditional Conditional Random Fields model and (b) a Large Language Model (LLM) fine-tuned with a customized head and compare the two approaches. The novel ideas explored are: 1) Decaying auxiliary loss (with residual) - where we train the model on an auxiliary task of Coarse-Grained NER and include this task as a part of the loss function 2) Triplet token blending - where we explore ways of blending the embeddings of neighboring tokens in the final NER layer prior to prediction 3) Task-optimal heads - where we explore a variety of custom heads and learning rates for the final layer of the LLM. We also explore multiple LLMs including GPT-3 and experiment with a variety of dropout and other hyperparameter settings before arriving at our final model which achieves micro & macro f1 of 0.85/0.84 (on dev) and 0.67/0.61 on the test data . We show that while pre-trained LLMs, by themselves, bring about a large improvement in scores as compared to traditional models, we also demonstrate that tangible improvements to the Macro-F1 score can be made by augmenting the LLM with additional feature/loss/model engineering techniques described above.
Authors: Hongjun Zhang
Try to generate new bridge types using generative artificial intelligence technology. Symmetric structured image dataset of three-span beam bridge, arch bridge, cable-stayed bridge and suspension bridge are used . Based on Python programming language, TensorFlow and Keras deep learning platform framework , as well as Wasserstein loss function and Lipschitz constraints, generative adversarial network is constructed and trained. From the obtained low dimensional bridge-type latent space sampling, new bridge types with asymmetric structures can be generated. Generative adversarial network can create new bridge types by organically combining different structural components on the basis of human original bridge types. It has a certain degree of human original ability. Generative artificial intelligence technology can open up imagination space and inspire humanity.
Authors: Hourun Li, Yusheng Zhao, Zhengyang Mao, YiFang Qin, Zhiping Xiao, Jiaqi Feng, Yiyang Gu, Wei Ju, Xiao Luo, Ming Zhao
Intelligent Transportation System (ITS) is vital in improving traffic congestion, reducing traffic accidents, optimizing urban planning, etc. However, due to the complexity of the traffic network, traditional machine learning and statistical methods are relegated to the background. With the advent of the artificial intelligence era, many deep learning frameworks have made remarkable progress in various fields and are now considered effective methods in many areas. As a deep learning method, Graph Neural Networks (GNNs) have emerged as a highly competitive method in the ITS field since 2019 due to their strong ability to model graph-related problems. As a result, more and more scholars pay attention to the applications of GNNs in transportation domains, which have shown excellent performance. However, most of the research in this area is still concentrated on traffic forecasting, while other ITS domains, such as autonomous vehicles and urban planning, still require more attention. This paper aims to review the applications of GNNs in six representative and emerging ITS domains: traffic forecasting, autonomous vehicles, traffic signal control, transportation safety, demand prediction, and parking management. We have reviewed extensive graph-related studies from 2018 to 2023, summarized their methods, features, and contributions, and presented them in informative tables or lists. Finally, we have identified the challenges of applying GNNs to ITS and suggested potential future directions.
Authors: Saurabh Agarwal, K. V. Arya, Yogesh Kumar Meena
Chest X-ray imaging is a critical diagnostic tool for identifying pulmonary diseases. However, manual interpretation of these images is time-consuming and error-prone. Automated systems utilizing convolutional neural networks (CNNs) have shown promise in improving the accuracy and efficiency of chest X-ray image classification. While previous work has mainly focused on using feature maps from the final convolution layer, there is a need to explore the benefits of leveraging additional layers for improved disease classification. Extracting robust features from limited medical image datasets remains a critical challenge. In this paper, we propose a novel deep learning-based multilayer multimodal fusion model that emphasizes extracting features from different layers and fusing them. Our disease detection model considers the discriminatory information captured by each layer. Furthermore, we propose the fusion of different-sized feature maps (FDSFM) module to effectively merge feature maps from diverse layers. The proposed model achieves a significantly higher accuracy of 97.21% and 99.60% for both three-class and two-class classifications, respectively. The proposed multilayer multimodal fusion model, along with the FDSFM module, holds promise for accurate disease classification and can also be extended to other disease classifications in chest X-ray images.
Authors: Brian B. Moser, Arundhati S. Shanbhag, Federico Raue, Stanislav Frolov, Sebastian Palacio, Andreas Dengel
Diffusion Models (DMs) represent a significant advancement in image Super-Resolution (SR), aligning technical image quality more closely with human preferences and expanding SR applications. DMs address critical limitations of previous methods, enhancing overall realism and details in SR images. However, DMs suffer from color-shifting issues, and their high computational costs call for efficient sampling alternatives, underscoring the challenge of balancing computational efficiency and image quality. This survey gives an overview of DMs applied to image SR and offers a detailed analysis that underscores the unique characteristics and methodologies within this domain, distinct from broader existing reviews in the field. It presents a unified view of DM fundamentals and explores research directions, including alternative input domains, conditioning strategies, guidance, corruption spaces, and zero-shot methods. This survey provides insights into the evolution of image SR with DMs, addressing current trends, challenges, and future directions in this rapidly evolving field.
Authors: Dayananda Ubrangala, Juhi Sharma, Sharath Kumar Rangappa, Kiran R, Ravi Prasad Kondapalli, Laurent Boué
String matching algorithms in the presence of abbreviations, such as in Stock Keeping Unit (SKU) product catalogs, remains a relatively unexplored topic. In this paper, we present a unified architecture for SKU search that provides both a real-time suggestion system (based on a Trie data structure) as well as a lower latency search system (making use of character level TF-IDF in combination with language model vector embeddings) where users initiate the search process explicitly. We carry out ablation studies that justify designing a complex search system composed of multiple components to address the delicate trade-off between speed and accuracy. Using SKU search in the Dynamics CRM as an example, we show how our system vastly outperforms, in all aspects, the results provided by the default search engine. Finally, we show how SKU descriptions may be enhanced via generative text models (using gpt-3.5-turbo) so that the consumers of the search results may get more context and a generally better experience when presented with the results of their SKU search.
Authors: Shi Yin, Xudong Zhu, Tianyu Gao, Haochong Zhang, Feng Wu, Lixin He
Deep learning for Hamiltonian regression of quantum systems in material research necessitates satisfying the covariance laws, among which achieving SO(3)-equivariance without sacrificing the expressiveness of networks remains an elusive challenge due to the restriction to non-linear mappings on guaranteeing theoretical equivariance. To alleviate the covariance-expressiveness dilemma, we propose a hybrid framework with two cascaded regression stages. The first stage, with a theoretically-guaranteed covariant neural network modeling symmetry properties of 3D atom systems, yields theoretically covariant features and baseline Hamiltonian predictions, assisting the second stage in learning covariance. Meanwhile, the second stage, powered by a non-linear 3D graph Transformer network we propose for structural modeling of 3D atomic systems, refines the first stage's output as a fine-grained prediction of Hamiltonians with better expressiveness capability. The combination of a theoretically covariant yet inevitably less expressive model with a highly expressive non-linear network enables precise, generalizable predictions while maintaining robust covariance under coordinate transformations. Our method achieves state-of-the-art performance in Hamiltonian prediction for electronic structure calculations, confirmed through experiments on five crystalline material databases.
Authors: Wenjie Pei, Weina Xu, Zongze Wu, Weichao Li, Jinfan Wang, Guangming Lu, Xiangrong Wang
The crux of graph classification lies in the effective representation learning for the entire graph. Typical graph neural networks focus on modeling the local dependencies when aggregating features of neighboring nodes, and obtain the representation for the entire graph by aggregating node features. Such methods have two potential limitations: 1) the global node saliency w.r.t. graph classification is not explicitly modeled, which is crucial since different nodes may have different semantic relevance to graph classification; 2) the graph representation directly aggregated from node features may have limited effectiveness to reflect graph-level information. In this work, we propose the Saliency-Aware Regularized Graph Neural Network (SAR-GNN) for graph classification, which consists of two core modules: 1) a traditional graph neural network serving as the backbone for learning node features and 2) the Graph Neural Memory designed to distill a compact graph representation from node features of the backbone. We first estimate the global node saliency by measuring the semantic similarity between the compact graph representation and node features. Then the learned saliency distribution is leveraged to regularize the neighborhood aggregation of the backbone, which facilitates the message passing of features for salient nodes and suppresses the less relevant nodes. Thus, our model can learn more effective graph representation. We demonstrate the merits of SAR-GNN by extensive experiments on seven datasets across various types of graph data. Code will be released.
Authors: Ziyue Yu, Jiayi Wang, Wuman Luo, Rita Tse, Giovanni Pau
Patient representation learning based on electronic health records (EHR) is a critical task for disease prediction. This task aims to effectively extract useful information on dynamic features. Although various existing works have achieved remarkable progress, the model performance can be further improved by fully extracting the trends, variations, and the correlation between the trends and variations in dynamic features. In addition, sparse visit records limit the performance of deep learning models. To address these issues, we propose the Multi-perspective Patient Representation Extractor (MPRE) for disease prediction. Specifically, we propose Frequency Transformation Module (FTM) to extract the trend and variation information of dynamic features in the time-frequency domain, which can enhance the feature representation. In the 2D Multi-Extraction Network (2D MEN), we form the 2D temporal tensor based on trend and variation. Then, the correlations between trend and variation are captured by the proposed dilated operation. Moreover, we propose the First-Order Difference Attention Mechanism (FODAM) to calculate the contributions of differences in adjacent variations to the disease diagnosis adaptively. To evaluate the performance of MPRE and baseline methods, we conduct extensive experiments on two real-world public datasets. The experiment results show that MPRE outperforms state-of-the-art baseline methods in terms of AUROC and AUPRC.
Authors: Dongwook Kim, Juyeon Park, Hee Cheol Chung, Seonghyun Jeong
Probabilistic mixture models are acknowledged as a valuable tool for unsupervised outlier detection owing to their interpretability and intuitive grounding in statistical principles. Within this framework, Dirichlet process mixture models emerge as a compelling alternative to conventional finite mixture models for both clustering and outlier detection tasks. However, despite their evident advantages, the widespread adoption of Dirichlet process mixture models in unsupervised outlier detection has been hampered by challenges related to computational inefficiency and sensitivity to outliers during the construction of detectors. To tackle these challenges, we propose a novel outlier detection method based on ensembles of Dirichlet process Gaussian mixtures. The proposed method is a fully unsupervised algorithm that capitalizes on random subspace and subsampling ensembles, not only ensuring efficient computation but also enhancing the robustness of the resulting outlier detector. Moreover, the proposed method leverages variational inference for Dirichlet process mixtures to ensure efficient and fast computation. Empirical studies with benchmark datasets demonstrate that our method outperforms existing approaches for unsupervised outlier detection.
Authors: Qin Yang
In recent years, edge computing has served as a paradigm that enables many future technologies like AI, Robotics, IoT, and high-speed wireless sensor networks (like 5G) by connecting cloud computing facilities and services to the end users. Especially in medical and healthcare applications, it provides remote patient monitoring and increases voluminous multimedia. From the robotics angle, robot-assisted therapy (RAT) is an active-assistive robotic technology in rehabilitation robotics, attracting many researchers to study and benefit people with disability like autism spectrum disorder (ASD) children. However, the main challenge of RAT is that the model capable of detecting the affective states of ASD people exists and can recall individual preferences. Moreover, involving expert diagnosis and recommendations to guide robots in updating the therapy approach to adapt to different statuses and scenarios is a crucial part of the ASD therapy process. This paper proposes the architecture of edge cognitive computing by combining human experts and assisted robots collaborating in the same framework to help ASD patients with long-term support. By integrating the real-time computing and analysis of a new cognitive robotic model for ASD therapy, the proposed architecture can achieve a seamless remote diagnosis, round-the-clock symptom monitoring, emergency warning, therapy alteration, and advanced assistance.
Authors: Shuang Li, Ziyuan Pu, Zhiyong Cui, Seunghyeon Lee, Xiucheng Guo, Dong Ngoduy
Highway traffic crashes exert a considerable impact on both transportation systems and the economy. In this context, accurate and dependable emergency responses are crucial for effective traffic management. However, the influence of crashes on traffic status varies across diverse factors and may be biased due to selection bias. Therefore, there arises a necessity to accurately estimate the heterogeneous causal effects of crashes, thereby providing essential insights to facilitate individual-level emergency decision-making. This paper proposes a novel causal machine learning framework to estimate the causal effect of different types of crashes on highway speed. The Neyman-Rubin Causal Model (RCM) is employed to formulate this problem from a causal perspective. The Conditional Shapley Value Index (CSVI) is proposed based on causal graph theory to filter adverse variables, and the Structural Causal Model (SCM) is then adopted to define the statistical estimand for causal effects. The treatment effects are estimated by Doubly Robust Learning (DRL) methods, which combine doubly robust causal inference with classification and regression machine learning models. Experimental results from 4815 crashes on Highway Interstate 5 in Washington State reveal the heterogeneous treatment effects of crashes at varying distances and durations. The rear-end crashes cause more severe congestion and longer durations than other types of crashes, and the sideswipe crashes have the longest delayed impact. Additionally, the findings show that rear-end crashes affect traffic greater at night, while crash to objects has the most significant influence during peak hours. Statistical hypothesis tests, error metrics based on matched "counterfactual outcomes", and sensitive analyses are employed for assessment, and the results validate the accuracy and effectiveness of our method.
Authors: Jinglong Luo, Yehong Zhang, Jiaqi Zhang, Xin Mu, Hui Wang, Yue Yu, Zenglin Xu
With the growing use of large language models hosted on cloud platforms to offer inference services, privacy concerns are escalating, especially concerning sensitive data like investment plans and bank account details. Secure Multi-Party Computing (SMPC) emerges as a promising solution to protect the privacy of inference data and model parameters. However, the application of SMPC in Privacy-Preserving Inference (PPI) for large language models, particularly those based on the Transformer architecture, often leads to considerable slowdowns or declines in performance. This is largely due to the multitude of nonlinear operations in the Transformer architecture, which are not well-suited to SMPC and are difficult to circumvent or optimize effectively. To address this concern, we introduce an advanced optimization framework called SecFormer, designed to strike an optimal balance between performance and efficiency in PPI for Transformer models. By implementing knowledge distillation techniques, we successfully eliminate the high-cost exponential and maximum operations in PPI without sacrificing model performance. Additionally, we have developed a suite of efficient SMPC protocols that utilize segmented polynomials and Goldschmidt's method to handle other complex nonlinear functions within PPI, such as GeLU, LayerNorm, and Softmax. Our extensive experiments reveal that SecFormer outperforms MPCFormer in performance, showing improvements of $5.6\%$ and $24.2\%$ for BERT$_{\text{BASE}}$ and BERT$_{\text{LARGE}}$, respectively. In terms of efficiency, SecFormer is 3.4 and 3.2 times faster than Puma, demonstrating its effectiveness and speed.
Authors: Venkataraman Natarajan Iyer
Federated Learning (FL) is a machine-learning approach enabling collaborative model training across multiple decentralized edge devices that hold local data samples, all without exchanging these samples. This collaborative process occurs under the supervision of a central server orchestrating the training or via a peer-to-peer network. The significance of FL is particularly pronounced in industries such as healthcare and finance, where data privacy holds paramount importance. However, training a model under the Federated learning setting brings forth several challenges, with one of the most prominent being the heterogeneity of data distribution among the edge devices. The data is typically non-independently and non-identically distributed (non-IID), thereby presenting challenges to model convergence. This report delves into the issues arising from non-IID and heterogeneous data and explores current algorithms designed to address these challenges.
Authors: AmirEhsan Khorashadizadeh, Valentin Debarnot, Tianlin Liu, Ivan Dokmanić
Deep learning is the current de facto state of the art in tomographic imaging. A common approach is to feed the result of a simple inversion, for example the backprojection, to a convolutional neural network (CNN) which then computes the reconstruction. Despite strong results on 'in-distribution' test data similar to the training data, backprojection from sparse-view data delocalizes singularities, so these approaches require a large receptive field to perform well. As a consequence, they overfit to certain global structures which leads to poor generalization on out-of-distribution (OOD) samples. Moreover, their memory complexity and training time scale unfavorably with image resolution, making them impractical for application at realistic clinical resolutions, especially in 3D: a standard U-Net requires a substantial 140GB of memory and 2600 seconds per epoch on a research-grade GPU when training on 1024x1024 images. In this paper, we introduce GLIMPSE, a local processing neural network for computed tomography which reconstructs a pixel value by feeding only the measurements associated with the neighborhood of the pixel to a simple MLP. While achieving comparable or better performance with successful CNNs like the U-Net on in-distribution test data, GLIMPSE significantly outperforms them on OOD samples while maintaining a memory footprint almost independent of image resolution; 5GB memory suffices to train on 1024x1024 images. Further, we built GLIMPSE to be fully differentiable, which enables feats such as recovery of accurate projection angles if they are out of calibration.
Authors: Tom Lippincott
We introduce a graph-aware autoencoder ensemble framework, with associated formalisms and tooling, designed to facilitate deep learning for scholarship in the humanities. By composing sub-architectures to produce a model isomorphic to a humanistic domain we maintain interpretability while providing function signatures for each sub-architectural choice, allowing both traditional and computational researchers to collaborate without disrupting established practices. We illustrate a practical application of our approach to a historical study of the American post-Atlantic slave trade, and make several specific technical contributions: a novel hybrid graph-convolutional autoencoder mechanism, batching policies for common graph topologies, and masking techniques for particular use-cases. The effectiveness of the framework for broadening participation of diverse domains is demonstrated by a growing suite of two dozen studies, both collaborations with humanists and established tasks from machine learning literature, spanning a variety of fields and data modalities. We make performance comparisons of several different architectural choices and conclude with an ambitious list of imminent next steps for this research.
Authors: Bálint Máté, François Fleuret
We consider the problem of sampling discrete field configurations $\phi$ from the Boltzmann distribution $[d\phi] Z^{-1} e^{-S[\phi]}$, where $S$ is the lattice-discretization of the continuous Euclidean action $\mathcal S$ of some quantum field theory. Since such densities arise as the approximation of the underlying functional density $[\mathcal D\phi(x)] \mathcal Z^{-1} e^{-\mathcal S[\phi(x)]}$, we frame the task as an instance of operator learning. In particular, we propose to approximate a time-dependent operator $\mathcal V_t$ whose time integral provides a mapping between the functional distributions of the free theory $[\mathcal D\phi(x)] \mathcal Z_0^{-1} e^{-\mathcal S_{0}[\phi(x)]}$ and of the target theory $[\mathcal D\phi(x)]\mathcal Z^{-1}e^{-\mathcal S[\phi(x)]}$. Whenever a particular lattice is chosen, the operator $\mathcal V_t$ can be discretized to a finite dimensional, time-dependent vector field $V_t$ which in turn induces a continuous normalizing flow between finite dimensional distributions over the chosen lattice. This flow can then be trained to be a diffeormorphism between the discretized free and target theories $[d\phi] Z_0^{-1} e^{-S_{0}[\phi]}$, $[d\phi] Z^{-1}e^{-S[\phi]}$. We run experiments on the $\phi^4$-theory to explore to what extent such operator-based flow architectures generalize to lattice sizes they were not trained on and show that pretraining on smaller lattices can lead to speedup over training only a target lattice size.
Authors: Zhaonan Qu, Kaixiang Lin, Zhaojian Li, Jiayu Zhou, Zhengyuan Zhou
Federated learning (FL) learns a model jointly from a set of participating devices without sharing each other's privately held data. The characteristics of non-i.i.d. data across the network, low device participation, high communication costs, and the mandate that data remain private bring challenges in understanding the convergence of FL algorithms, particularly regarding how convergence scales with the number of participating devices. In this paper, we focus on Federated Averaging (FedAvg), one of the most popular and effective FL algorithms in use today, as well as its Nesterov accelerated variant, and conduct a systematic study of how their convergence scale with the number of participating devices under non-i.i.d. data and partial participation in convex settings. We provide a unified analysis that establishes convergence guarantees for FedAvg under strongly convex, convex, and overparameterized strongly convex problems. We show that FedAvg enjoys linear speedup in each case, although with different convergence rates and communication efficiencies. For strongly convex and convex problems, we also characterize the corresponding convergence rates for the Nesterov accelerated FedAvg algorithm, which are the first linear speedup guarantees for momentum variants of FedAvg in convex settings. Empirical studies of the algorithms in various settings have supported our theoretical results.
Authors: Pasquale Cascarano, Patrizio Frosini, Nicola Quercioli, Amir Saki
Group equivariant non-expansive operators have been recently proposed as basic components in topological data analysis and deep learning. In this paper we study some geometric properties of the spaces of group equivariant operators and show how a space $\mathcal{F}$ of group equivariant non-expansive operators can be endowed with the structure of a Riemannian manifold, so making available the use of gradient descent methods for the minimization of cost functions on $\mathcal{F}$. As an application of this approach, we also describe a procedure to select a finite set of representative group equivariant non-expansive operators in the considered manifold.
Authors: Haihao Lu, Jinwen Yang
There is a recent interest on first-order methods for linear programming (LP). In this paper,we propose a stochastic algorithm using variance reduction and restarts for solving sharp primal-dual problems such as LP. We show that the proposed stochastic method exhibits a linear convergence rate for solving sharp instances with a high probability. In addition, we propose an efficient coordinate-based stochastic oracle for unconstrained bilinear problems, which has $\mathcal O(1)$ per iteration cost and improves the complexity of the existing deterministic and stochastic algorithms. Finally, we show that the obtained linear convergence rate is nearly optimal (upto $\log$ terms) for a wide class of stochastic primal dual methods.
Authors: Xiao Han, Leye Wang, Junjie Wu, Xiao Fang
Vertical Federated learning (VFL) is a promising paradigm for predictive analytics, empowering an organization (i.e., task party) to enhance its predictive models through collaborations with multiple data suppliers (i.e., data parties) in a decentralized and privacy-preserving way. Despite the fast-growing interest in VFL, the lack of effective and secure tools for assessing the value of data owned by data parties hinders the application of VFL in business contexts. In response, we propose FedValue, a privacy-preserving, task-specific but model-free data valuation method for VFL, which consists of a data valuation metric and a federated computation method. Specifically, we first introduce a novel data valuation metric, namely MShapley-CMI. The metric evaluates a data party's contribution to a predictive analytics task without the need of executing a machine learning model, making it well-suited for real-world applications of VFL. Next, we develop an innovative federated computation method that calculates the MShapley-CMI value for each data party in a privacy-preserving manner. Extensive experiments conducted on six public datasets validate the efficacy of FedValue for data valuation in the context of VFL. In addition, we illustrate the practical utility of FedValue with a case study involving federated movie recommendations.
Authors: Mason A. Porter
I give a short introduction to data ethics. I begin with some background information and societal context for data ethics. I then discuss data ethics in mathematical-science education and indicate some available course material. I briefly highlight a few efforts -- at my home institution and elsewhere -- on data ethics, society, and social good. I then discuss open data in research, research replicability and some other ethical issues in research, and the tension between privacy and open data and code, and a few controversial studies and reactions to studies. I then discuss ethical principles, institutional review boards, and a few other considerations in the scientific use of human data. Finally, I briefly survey a variety of research and lay articles that are relevant to data ethics and data privacy. I conclude with a brief summary.
My focal audience is mathematicians, but I hope that this chapter will also be useful to others. I am not an expert about data ethics, and this chapter provides only a starting point on this wide-ranging topic. I encourage you to examine the resources that I discuss and to reflect carefully on data ethics, its role in mathematics education, and the societal implications of data and data analysis. As data and technology continue to evolve, I hope that such careful reflection will continue throughout your life.
Authors: Luhao Zhang, Jincheng Yang, Rui Gao
We present an elementary yet general proof of duality for Wasserstein distributionally robust optimization. The duality holds for any arbitrary Kantorovich transport cost, measurable loss function, and nominal probability distribution, provided that an interchangeability principle holds, which is equivalent to certain measurability conditions. To illustrate the broader applicability of our approach, we provide a rigorous treatment of duality results in distributionally robust Markov decision processes and distributionally robust multistage stochastic programming. Furthermore, we extend the result to other problems including infinity-Wasserstein distributionally robust optimization, risk-averse optimization, and globalized distributionally robust counterpart.
Authors: Udai Nagpal, Krishan Nagpal
This paper describes an approach to simultaneously identify clusters and estimate cluster-specific regression parameters from the given data. Such an approach can be useful in learning the relationship between input and output when the regression parameters for estimating output are different in different regions of the input space. Variational Inference (VI), a machine learning approach to obtain posterior probability densities using optimization techniques, is used to identify clusters of explanatory variables and regression parameters for each cluster. From these results, one can obtain both the expected value and the full distribution of predicted output. Other advantages of the proposed approach include the elegant theoretical solution and clear interpretability of results. The proposed approach is well-suited for financial forecasting where markets have different regimes (or clusters) with different patterns and correlations of market changes in each regime. In financial applications, knowledge about such clusters can provide useful insights about portfolio performance and identify the relative importance of variables in different market regimes. An illustrative example of predicting one-day S&P change is considered to illustrate the approach and compare the performance of the proposed approach with standard regression without clusters. Due to the broad applicability of the problem, its elegant theoretical solution, and the computational efficiency of the proposed algorithm, the approach may be useful in a number of areas extending beyond the financial domain.
Authors: Lingyu Feng, Ting Gao, Min Dai, Jinqiao Duan
Multiscale stochastic dynamical systems have been widely adopted to a variety of scientific and engineering problems due to their capability of depicting complex phenomena in many real world applications. This work is devoted to investigating the effective dynamics for slow-fast stochastic dynamical systems. Given observation data on a short-term period satisfying some unknown slow-fast stochastic systems, we propose a novel algorithm including a neural network called Auto-SDE to learn invariant slow manifold. Our approach captures the evolutionary nature of a series of time-dependent autoencoder neural networks with the loss constructed from a discretized stochastic differential equation. Our algorithm is also validated to be accurate, stable and effective through numerical experiments under various evaluation metrics.
Authors: Shurui Gui, Hao Yuan, Jie Wang, Qicheng Lao, Kang Li, Shuiwang Ji
We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms. While most current methods focus on explaining graph nodes, edges, or features, we argue that, as the inherent functional mechanism of GNNs, message flows are more natural for performing explainability. To this end, we propose a novel method here, known as FlowX, to explain GNNs by identifying important message flows. To quantify the importance of flows, we propose to follow the philosophy of Shapley values from cooperative game theory. To tackle the complexity of computing all coalitions' marginal contributions, we propose a flow sampling scheme to compute Shapley value approximations as initial assessments of further training. We then propose an information-controlled learning algorithm to train flow scores toward diverse explanation targets: necessary or sufficient explanations. Experimental studies on both synthetic and real-world datasets demonstrate that our proposed FlowX and its variants lead to improved explainability of GNNs. The code is available at https://github.com/divelab/DIG.
Authors: Joshua Cutler, Mateo Díaz, Dmitriy Drusvyatskiy
We analyze a stochastic approximation algorithm for decision-dependent problems, wherein the data distribution used by the algorithm evolves along the iterate sequence. The primary examples of such problems appear in performative prediction and its multiplayer extensions. We show that under mild assumptions, the deviation between the average iterate of the algorithm and the solution is asymptotically normal, with a covariance that clearly decouples the effects of the gradient noise and the distributional shift. Moreover, building on the work of H\'ajek and Le Cam, we show that the asymptotic performance of the algorithm with averaging is locally minimax optimal.
Authors: Chulin Xie, Pin-Yu Chen, Qinbin Li, Arash Nourian, Ce Zhang, Bo Li
Federated learning (FL) enables distributed resource-constrained devices to jointly train shared models while keeping the training data local for privacy purposes. Vertical FL (VFL), which allows each client to collect partial features, has attracted intensive research efforts recently. We identified the main challenges that existing VFL frameworks are facing: the server needs to communicate gradients with the clients for each training step, incurring high communication cost that leads to rapid consumption of privacy budgets. To address these challenges, in this paper, we introduce a VFL framework with multiple heads (VIM), which takes the separate contribution of each client into account, and enables an efficient decomposition of the VFL optimization objective to sub-objectives that can be iteratively tackled by the server and the clients on their own. In particular, we propose an Alternating Direction Method of Multipliers (ADMM)-based method to solve our optimization problem, which allows clients to conduct multiple local updates before communication, and thus reduces the communication cost and leads to better performance under differential privacy (DP). We provide the user-level DP mechanism for our framework to protect user privacy. Moreover, we show that a byproduct of VIM is that the weights of learned heads reflect the importance of local clients. We conduct extensive evaluations and show that on four vertical FL datasets, VIM achieves significantly higher performance and faster convergence compared with the state-of-the-art. We also explicitly evaluate the importance of local clients and show that VIM enables functionalities such as client-level explanation and client denoising. We hope this work will shed light on a new way of effective VFL training and understanding.
Authors: Xiaoyuan Liu, Tianneng Shi, Chulin Xie, Qinbin Li, Kangping Hu, Haoyu Kim, Xiaojun Xu, The-Anh Vu-Le, Zhen Huang, Arash Nourian, Bo Li, Dawn Song
Federated Learning (FL) has become a practical and widely adopted distributed learning paradigm. However, the lack of a comprehensive and standardized solution covering diverse use cases makes it challenging to use in practice. In addition, selecting an appropriate FL framework for a specific use case can be a daunting task. In this work, we present UniFed, the first unified platform for standardizing existing open-source FL frameworks. The platform streamlines the end-to-end workflow for distributed experimentation and deployment, encompassing 11 popular open-source FL frameworks. In particular, to address the substantial variations in workflows and data formats, UniFed introduces a configuration-based schema-enforced task specification, offering 20 editable fields. UniFed also provides functionalities such as distributed execution management, logging, and data analysis.
With UniFed, we evaluate and compare 11 popular FL frameworks from the perspectives of functionality, privacy protection, and performance, through conducting developer surveys and code-level investigation. We collect 15 diverse FL scenario setups (e.g., horizontal and vertical settings) for FL framework evaluation. This comprehensive evaluation allows us to analyze both model and system performance, providing detailed comparisons and offering recommendations for framework selection. UniFed simplifies the process of selecting and utilizing the appropriate FL framework for specific use cases, while enabling standardized distributed experimentation and deployment. Our results and analysis based on experiments with up to 178 distributed nodes provide valuable system design and deployment insights, aiming to empower practitioners in their pursuit of effective FL solutions.
Authors: Benjamin Dufée, Bérenger Hug, Etienne Mémin, Gilles Tissot
A methodological framework for ensemble-based estimation and simulation of high dimensional dynamical systems such as the oceanic or atmospheric flows is proposed. To that end, the dynamical system is embedded in a family of reproducing kernel Hilbert spaces (RKHS) with kernel functions driven by the dynamics. In the RKHS family, the Koopman and Perron-Frobenius operators are unitary and uniformly continuous. This property warrants they can be expressed in exponential series of diagonalizable bounded evolution operators defined from their infinitesimal generators. Access to Lyapunov exponents and to exact ensemble based expressions of the tangent linear dynamics are directly available as well. The RKHS family enables us the devise of strikingly simple ensemble data assimilation methods for trajectory reconstructions in terms of constant-in-time linear combinations of trajectory samples. Such an embarrassingly simple strategy is made possible through a fully justified superposition principle ensuing from several fundamental theorems.
Authors: Kerem Ozfatura, Emre Ozfatura, Alptekin Kupcu, Deniz Gunduz
The increasing popularity of the federated learning (FL) framework due to its success in a wide range of collaborative learning tasks also induces certain security concerns. Among many vulnerabilities, the risk of Byzantine attacks is of particular concern, which refers to the possibility of malicious clients participating in the learning process. Hence, a crucial objective in FL is to neutralize the potential impact of Byzantine attacks and to ensure that the final model is trustable. It has been observed that the higher the variance among the clients' models/updates, the more space there is for Byzantine attacks to be hidden. As a consequence, by utilizing momentum, and thus, reducing the variance, it is possible to weaken the strength of known Byzantine attacks. The centered clipping (CC) framework has further shown that the momentum term from the previous iteration, besides reducing the variance, can be used as a reference point to neutralize Byzantine attacks better. In this work, we first expose vulnerabilities of the CC framework, and introduce a novel attack strategy that can circumvent the defences of CC and other robust aggregators and reduce their test accuracy up to %33 on best-case scenarios in image classification tasks. Then, we propose a new robust and fast defence mechanism that is effective against the proposed and other existing Byzantine attacks.
Authors: Ruihan Yang, Stephan Mandt
This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. The approach relies on the transform coding paradigm, where an image is mapped into a latent space for entropy coding and, from there, mapped back to the data space for reconstruction. In contrast to VAE-based neural compression, where the (mean) decoder is a deterministic neural network, our decoder is a conditional diffusion model. Our approach thus introduces an additional ``content'' latent variable on which the reverse diffusion process is conditioned and uses this variable to store information about the image. The remaining ``texture'' variables characterizing the diffusion process are synthesized at decoding time. We show that the model's performance can be tuned toward perceptual metrics of interest. Our extensive experiments involving multiple datasets and image quality assessment metrics show that our approach yields stronger reported FID scores than the GAN-based model, while also yielding competitive performance with VAE-based models in several distortion metrics. Furthermore, training the diffusion with $\mathcal{X}$-parameterization enables high-quality reconstructions in only a handful of decoding steps, greatly affecting the model's practicality. Our code is available at: \url{https://github.com/buggyyang/CDC_compression}
Authors: Abhay Shastry, Abhijith Jayakumar, Apoorva Patel, Chiranjib Bhattacharyya
Quantum kernel methods are a candidate for quantum speed-ups in supervised machine learning. The number of quantum measurements N required for a reasonable kernel estimate is a critical resource, both from complexity considerations and because of the constraints of near-term quantum hardware. We emphasize that for classification tasks, the aim is reliable classification and not precise kernel evaluation, and demonstrate that the former is far more resource efficient. Furthermore, it is shown that the accuracy of classification is not a suitable performance metric in the presence of noise and we motivate a new metric that characterizes the reliability of classification. We then obtain a bound for N which ensures, with high probability, that classification errors over a dataset are bounded by the margin errors of an idealized quantum kernel classifier. Using chance constraint programming and the subgaussian bounds of quantum kernel distributions, we derive several Shot-frugal and Robust (ShofaR) programs starting from the primal formulation of the Support Vector Machine. This significantly reduces the number of quantum measurements needed and is robust to noise by construction. Our strategy is applicable to uncertainty in quantum kernels arising from any source of unbiased noise.
Authors: Tim Dockhorn, Tianshi Cao, Arash Vahdat, Karsten Kreis
While modern machine learning models rely on increasingly large training datasets, data is often limited in privacy-sensitive domains. Generative models trained with differential privacy (DP) on sensitive data can sidestep this challenge, providing access to synthetic data instead. We build on the recent success of diffusion models (DMs) and introduce Differentially Private Diffusion Models (DPDMs), which enforce privacy using differentially private stochastic gradient descent (DP-SGD). We investigate the DM parameterization and the sampling algorithm, which turn out to be crucial ingredients in DPDMs, and propose noise multiplicity, a powerful modification of DP-SGD tailored to the training of DMs. We validate our novel DPDMs on image generation benchmarks and achieve state-of-the-art performance in all experiments. Moreover, on standard benchmarks, classifiers trained on DPDM-generated synthetic data perform on par with task-specific DP-SGD-trained classifiers, which has not been demonstrated before for DP generative models. Project page and code: https://nv-tlabs.github.io/DPDM.
Authors: Ziyu Shu, Alireza Entezari
Background and Objective: The success of neural networks in a number of image processing tasks has motivated their application in image reconstruction problems in computed tomography (CT). While progress has been made in this area, the lack of stability and theoretical guarantees for accuracy, together with the scarcity of high-quality training data for specific imaging domains pose challenges for many CT applications. In this paper, we present a framework for iterative reconstruction (IR) in CT that leverages the hierarchical structure of neural networks, without the need for training. Our framework incorporates this structural information as a deep image prior (DIP), and uses a novel residual back projection (RBP) connection that forms the basis for our iterations.
Methods: We propose using an untrained U-net in conjunction with a novel residual back projection to minimize an objective function and achieve high-accuracy reconstruction. In each iteration, the weights of the untrained U-net are optimized, and the output of the U-net in the current iteration is used to update the input of the U-net in the next iteration through the aforementioned RBP connection.
Results: Experimental results demonstrate that the RBP-DIP framework offers improvements over other state-of-the-art conventional IR methods, as well as pre-trained and untrained models with similar network structures under multiple conditions. These improvements are particularly significant in the few-view, limited-angle, and low-dose imaging configurations.
Conclusions: Applying to both parallel and fan beam X-ray imaging, our framework shows significant improvement under multiple conditions. Furthermore, the proposed framework requires no training data and can be adjusted on-demand to adapt to different conditions (e.g. noise level, geometry, and imaged object).
Authors: Khai Nguyen, Tongzheng Ren, Nhat Ho
Sliced Wasserstein (SW) distance suffers from redundant projections due to independent uniform random projecting directions. To partially overcome the issue, max K sliced Wasserstein (Max-K-SW) distance ($K\geq 1$), seeks the best discriminative orthogonal projecting directions. Despite being able to reduce the number of projections, the metricity of Max-K-SW cannot be guaranteed in practice due to the non-optimality of the optimization. Moreover, the orthogonality constraint is also computationally expensive and might not be effective. To address the problem, we introduce a new family of SW distances, named Markovian sliced Wasserstein (MSW) distance, which imposes a first-order Markov structure on projecting directions. We discuss various members of MSW by specifying the Markov structure including the prior distribution, the transition distribution, and the burning and thinning technique. Moreover, we investigate the theoretical properties of MSW including topological properties (metricity, weak convergence, and connection to other distances), statistical properties (sample complexity, and Monte Carlo estimation error), and computational properties (computational complexity and memory complexity). Finally, we compare MSW distances with previous SW variants in various applications such as gradient flows, color transfer, and deep generative modeling to demonstrate the favorable performance of MSW.
Authors: Luca Sciullo, Alberto De Marchi, Angelo Trotta, Federico Montori, Luciano Bononi, Marco Di Felice
Complex IoT ecosystems often require the usage of Digital Twins (DTs) of their physical assets in order to perform predictive analytics and simulate what-if scenarios. DTs are able to replicate IoT devices and adapt over time to their behavioral changes. However, DTs in IoT are typically tailored to a specific use case, without the possibility to seamlessly adapt to different scenarios. Further, the fragmentation of IoT poses additional challenges on how to deploy DTs in heterogeneous scenarios characterized by the usage of multiple data formats and IoT network protocols. In this paper, we propose the Relativistic Digital Twin (RDT) framework, through which we automatically generate general-purpose DTs of IoT entities and tune their behavioral models over time by constantly observing their real counterparts. The framework relies on the object representation via the Web of Things (WoT), to offer a standardized interface to each of the IoT devices as well as to their DTs. To this purpose, we extended the W3C WoT standard in order to encompass the concept of behavioral model and define it in the Thing Description (TD) through a new vocabulary. Finally, we evaluated the RDT framework over two disjoint use cases to assess its correctness and learning performance, i.e., the DT of a simulated smart home scenario with the capability of forecasting the indoor temperature, and the DT of a real-world drone with the capability of forecasting its trajectory in an outdoor scenario. Experiments show that the generated DT can estimate the behavior of its real counterpart after an observation stage, regardless of the considered scenario.
Authors: Gaël Gendron, Michael Witbrock, Gillian Dobbie
Deep Learning models have shown success in a large variety of tasks by extracting correlation patterns from high-dimensional data but still struggle when generalizing out of their initial distribution. As causal engines aim to learn mechanisms independent from a data distribution, combining Deep Learning with Causality can have a great impact on the two fields. In this paper, we further motivate this assumption. We perform an extensive overview of the theories and methods for Causality from different perspectives, with an emphasis on Deep Learning and the challenges met by the two domains. We show early attempts to bring the fields together and the possible perspectives for the future. We finish by providing a large variety of applications for techniques from Causality.
Authors: Yingzhou Lu, Minjie Shen, Huazheng Wang, Xiao Wang, Capucine van Rechem, Wenqi Wei
Machine learning heavily relies on data, but real-world applications often encounter various data-related issues. These include data of poor quality, insufficient data points leading to under-fitting of machine learning models, and difficulties in data access due to concerns surrounding privacy, safety, and regulations. In light of these challenges, the concept of synthetic data generation emerges as a promising alternative that allows for data sharing and utilization in ways that real-world data cannot facilitate. This paper presents a comprehensive systematic review of existing studies that employ machine learning models for the purpose of generating synthetic data. The review encompasses various perspectives, starting with the applications of synthetic data generation, spanning computer vision, speech, natural language processing, healthcare, and business domains. Additionally, it explores different machine learning methods, with particular emphasis on neural network architectures and deep generative models. The paper also addresses the crucial aspects of privacy and fairness concerns related to synthetic data generation. Furthermore, this study identifies the challenges and opportunities prevalent in this emerging field, shedding light on the potential avenues for future research. By delving into the intricacies of synthetic data generation, this paper aims to contribute to the advancement of knowledge and inspire further exploration in synthetic data generation.
Authors: Stephen Pasteris, Fabio Vitale, Mark Herbster, Claudio Gentile, Andre' Panisson
We investigate the problem of online collaborative filtering under no-repetition constraints, whereby users need to be served content in an online fashion and a given user cannot be recommended the same content item more than once. We start by designing and analyzing an algorithm that works under biclustering assumptions on the user-item preference matrix, and show that this algorithm exhibits an optimal regret guarantee, while being fully adaptive, in that it is oblivious to any prior knowledge about the sequence of users, the universe of items, as well as the biclustering parameters of the preference matrix. We then propose a more robust version of this algorithm which operates with general matrices. Also this algorithm is parameter free, and we prove regret guarantees that scale with the amount by which the preference matrix deviates from a biclustered structure. To our knowledge, these are the first results on online collaborative filtering that hold at this level of generality and adaptivity under no-repetition constraints. Finally, we complement our theoretical findings with simple experiments on real-world datasets aimed at both validating the theory and empirically comparing to standard baselines. This comparison shows the competitive advantage of our approach over these baselines.
Authors: Jigyasa Nigam, Sergey N. Pozdnyakov, Kevin K. Huguenin-Dumittan, Michele Ceriotti
In this paper, we address the challenge of obtaining a comprehensive and symmetric representation of point particle groups, such as atoms in a molecule, which is crucial in physics and theoretical chemistry. The problem has become even more important with the widespread adoption of machine-learning techniques in science, as it underpins the capacity of models to accurately reproduce physical relationships while being consistent with fundamental symmetries and conservation laws. However, some of the descriptors that are commonly used to represent point clouds -- most notably those based on discretized correlations of the neighbor density, that underpin most of the existing ML models of matter at the atomic scale -- are unable to distinguish between special arrangements of particles in three dimensions. This makes it impossible to machine learn their properties. Atom-density correlations are provably complete in the limit in which they simultaneously describe the mutual relationship between all atoms, which is impractical. We present a novel approach to construct descriptors of \emph{finite} correlations based on the relative arrangement of particle triplets, which can be employed to create symmetry-adapted models with universal approximation capabilities, which have the resolution of the neighbor discretization as the sole convergence parameter. Our strategy is demonstrated on a class of atomic arrangements that are specifically built to defy a broad class of conventional symmetric descriptors, showcasing its potential for addressing their limitations.
Authors: Ronghua Shang, Songling Zhu, Yinan Wu, Weitong Zhang, Licheng Jiao, Songhua Xu
Model compression plays a vital role in the practical deployment of deep neural networks (DNNs), and evolutionary multi-objective (EMO) pruning is an essential tool in balancing the compression rate and performance of the DNNs. However, due to its population-based nature, EMO pruning suffers from the complex optimization space and the resource-intensive structure verification process, especially in complex networks. To this end, a multi-objective complex network pruning framework based on divide-and-conquer and global performance impairment ranking (EMO-DIR) is proposed in this paper. Firstly, a divide-and-conquer EMO network pruning method is proposed, which decomposes the complex task of EMO pruning on the entire network into easier sub-tasks on multiple sub-networks. On the one hand, this decomposition narrows the pruning optimization space and decreases the optimization difficulty; on the other hand, the smaller network structure converges faster, so the proposed algorithm consumes lower computational resources. Secondly, a sub-network training method based on cross-network constraints is designed, which could bridge independent EMO pruning sub-tasks, allowing them to collaborate better and improving the overall performance of the pruned network. Finally, a multiple sub-networks joint pruning method based on EMO is proposed. This method combines the Pareto Fronts from EMO pruning results on multiple sub-networks through global performance impairment ranking to design a joint pruning scheme. The rich experiments on CIFAR-10/100 and ImageNet-100/1k are conducted. The proposed algorithm achieves a comparable performance with the state-of-the-art pruning methods.
Authors: Abhishek Sharma, Sonali Parbhoo, Omer Gottesman, Finale Doshi-Velez
Decision-focused (DF) model-based reinforcement learning has recently been introduced as a powerful algorithm that can focus on learning the MDP dynamics that are most relevant for obtaining high returns. While this approach increases the agent's performance by directly optimizing the reward, it does so by learning less accurate dynamics from a maximum likelihood perspective. We demonstrate that when the reward function is defined by preferences over multiple objectives, the DF model may be sensitive to changes in the objective preferences.In this work, we develop the robust decision-focused (RDF) algorithm, which leverages the non-identifiability of DF solutions to learn models that maximize expected returns while simultaneously learning models that transfer to changes in the preference over multiple objectives. We demonstrate the effectiveness of RDF on two synthetic domains and two healthcare simulators, showing that it significantly improves the robustness of DF model learning to changes in the reward function without compromising training-time return.
Authors: Sicen Guo, Jiahang Li, Yi Feng, Dacheng Zhou, Denghuang Zhang, Chen Chen, Shuai Su, Xingyi Zhu, Qijun Chen, Rui Fan
In the nascent domain of urban digital twins (UDT), the prospects for leveraging cutting-edge deep learning techniques are vast and compelling. Particularly within the specialized area of intelligent road inspection (IRI), a noticeable gap exists, underscored by the current dearth of dedicated research efforts and the lack of large-scale well-annotated datasets. To foster advancements in this burgeoning field, we have launched an online open-source benchmark suite, referred to as UDTIRI. Along with this article, we introduce the road pothole detection task, the first online competition published within this benchmark suite. This task provides a well-annotated dataset, comprising 1,000 RGB images and their pixel/instance-level ground-truth annotations, captured in diverse real-world scenarios under different illumination and weather conditions. Our benchmark provides a systematic and thorough evaluation of state-of-the-art object detection, semantic segmentation, and instance segmentation networks, developed based on either convolutional neural networks or Transformers. We anticipate that our benchmark will serve as a catalyst for the integration of advanced UDT techniques into IRI. By providing algorithms with a more comprehensive understanding of diverse road conditions, we seek to unlock their untapped potential and foster innovation in this critical domain.
Authors: Khai Nguyen, Nhat Ho
The sliced Wasserstein (SW) distance has been widely recognized as a statistically effective and computationally efficient metric between two probability measures. A key component of the SW distance is the slicing distribution. There are two existing approaches for choosing this distribution. The first approach is using a fixed prior distribution. The second approach is optimizing for the best distribution which belongs to a parametric family of distributions and can maximize the expected distance. However, both approaches have their limitations. A fixed prior distribution is non-informative in terms of highlighting projecting directions that can discriminate two general probability measures. Doing optimization for the best distribution is often expensive and unstable. Moreover, designing the parametric family of the candidate distribution could be easily misspecified. To address the issues, we propose to design the slicing distribution as an energy-based distribution that is parameter-free and has the density proportional to an energy function of the projected one-dimensional Wasserstein distance. We then derive a novel sliced Wasserstein metric, energy-based sliced Waserstein (EBSW) distance, and investigate its topological, statistical, and computational properties via importance sampling, sampling importance resampling, and Markov Chain methods. Finally, we conduct experiments on point-cloud gradient flow, color transfer, and point-cloud reconstruction to show the favorable performance of the EBSW.
Authors: Francesco Alemanno, Luca Camanzi, Gianluca Manzan, Daniele Tantari
While Hopfield networks are known as paradigmatic models for memory storage and retrieval, modern artificial intelligence systems mainly stand on the machine learning paradigm. We show that it is possible to formulate a teacher-student self-supervised learning problem with Boltzmann machines in terms of a suitable generalization of the Hopfield model with structured patterns, where the spin variables are the machine weights and patterns correspond to the training set's examples. We analyze the learning performance by studying the phase diagram in terms of the training set size, the dataset noise and the inference temperature (i.e. the weight regularization). With a small but informative dataset the machine can learn by memorization. With a noisy dataset, an extensive number of examples above a critical threshold is needed. In this regime the memory storage limits of the system becomes an opportunity for the occurrence of a learning regime in which the system can generalize.
Authors: Sungwoo Kang, Jong-Kook Kim
Despite the efficient market hypothesis, many studies suggest the existence of inefficiencies in the stock market leading to the development of techniques to gain above-market returns. Systematic trading has undergone significant advances in recent decades with deep learning schemes emerging as a powerful tool for analyzing and predicting market behavior. In this paper, a method is proposed that is inspired by how professional technical analysts trade. This scheme looks at stock prices of the previous 600 days and predicts whether the stock price will rise or fall 10% or 20% within the next D days. Plus, the proposed method uses the Resnet's (a deep learning model) skip connections and logits to increase the probability of the prediction. The model was trained and tested using historical data from both the Korean and US stock markets. We show that using the period label of 5 gives the best result. On Korea market it achieved a profit more than 39% above the market return, and a profit more than 40% above the market return on the US market.
Authors: Song Wei, Hanyu Zhang, Ronald Moore, Rishikesan Kamaleswaran, Yao Xie
We present a Transfer Causal Learning (TCL) framework when target and source domains share the same covariate/feature spaces, aiming to improve causal effect estimation accuracy in limited data. Limited data is very common in medical applications, where some rare medical conditions, such as sepsis, are of interest. Our proposed method, named \texttt{$\ell_1$-TCL}, incorporates $\ell_1$ regularized TL for nuisance models (e.g., propensity score model); the TL estimator of the nuisance parameters is plugged into downstream average causal/treatment effect estimators (e.g., inverse probability weighted estimator). We establish non-asymptotic recovery guarantees for the \texttt{$\ell_1$-TCL} with generalized linear model (GLM) under the sparsity assumption in the high-dimensional setting, and demonstrate the empirical benefits of \texttt{$\ell_1$-TCL} through extensive numerical simulation for GLM and recent neural network nuisance models. Our method is subsequently extended to real data and generates meaningful insights consistent with medical literature, a case where all baseline methods fail.
Authors: Sohyun An, Hayeon Lee, Jaehyeong Jo, Seanie Lee, Sung Ju Hwang
Existing NAS methods suffer from either an excessive amount of time for repetitive sampling and training of many task-irrelevant architectures. To tackle such limitations of existing NAS methods, we propose a paradigm shift from NAS to a novel conditional Neural Architecture Generation (NAG) framework based on diffusion models, dubbed DiffusionNAG. Specifically, we consider the neural architectures as directed graphs and propose a graph diffusion model for generating them. Moreover, with the guidance of parameterized predictors, DiffusionNAG can flexibly generate task-optimal architectures with the desired properties for diverse tasks, by sampling from a region that is more likely to satisfy the properties. This conditional NAG scheme is significantly more efficient than previous NAS schemes which sample the architectures and filter them using the property predictors. We validate the effectiveness of DiffusionNAG through extensive experiments in two predictor-based NAS scenarios: Transferable NAS and Bayesian Optimization (BO)-based NAS. DiffusionNAG achieves superior performance with speedups of up to 20 times when compared to the baselines on Transferable NAS benchmarks. Furthermore, when integrated into a BO-based algorithm, DiffusionNAG outperforms existing BO-based NAS approaches, particularly in the large MobileNetV3 search space on the ImageNet 1K dataset.
Authors: Sushma Kumari, Vladimir G. Pestov
We continue to investigate the $k$ nearest neighbour learning rule in separable metric spaces. Thanks to the results of C\'erou and Guyader (2006) and Preiss (1983), this rule is known to be universally consistent in every metric space $X$ that is sigma-finite dimensional in the sense of Nagata. Here we show that the rule is strongly universally consistent in such spaces in the absence of ties. Under the tie-breaking strategy applied by Devroye, Gy\"{o}rfi, Krzy\.{z}ak, and Lugosi (1994) in the Euclidean setting, we manage to show the strong universal consistency in non-Archimedian metric spaces (that is, those of Nagata dimension zero). Combining the theorem of C\'erou and Guyader with results of Assouad and Quentin de Gromard (2006), one deduces that the $k$-NN rule is universally consistent in metric spaces having finite dimension in the sense of de Groot. In particular, the $k$-NN rule is universally consistent in the Heisenberg group which is not sigma-finite dimensional in the sense of Nagata as follows from an example independently constructed by Kor\'anyi and Reimann (1995) and Sawyer and Wheeden (1992).
Authors: Hyojun Go, JinYoung Kim, Yunsung Lee, Seunghyun Lee, Shinhyeok Oh, Hyeongdon Moon, Seungtaek Choi
Diffusion-based generative models have achieved remarkable success in various domains. It trains a shared model on denoising tasks that encompass different noise levels simultaneously, representing a form of multi-task learning (MTL). However, analyzing and improving diffusion models from an MTL perspective remains under-explored. In particular, MTL can sometimes lead to the well-known phenomenon of negative transfer, which results in the performance degradation of certain tasks due to conflicts between tasks. In this paper, we first aim to analyze diffusion training from an MTL standpoint, presenting two key observations: (O1) the task affinity between denoising tasks diminishes as the gap between noise levels widens, and (O2) negative transfer can arise even in diffusion training. Building upon these observations, we aim to enhance diffusion training by mitigating negative transfer. To achieve this, we propose leveraging existing MTL methods, but the presence of a huge number of denoising tasks makes this computationally expensive to calculate the necessary per-task loss or gradient. To address this challenge, we propose clustering the denoising tasks into small task clusters and applying MTL methods to them. Specifically, based on (O2), we employ interval clustering to enforce temporal proximity among denoising tasks within clusters. We show that interval clustering can be solved using dynamic programming, utilizing signal-to-noise ratio, timestep, and task affinity for clustering objectives. Through this, our approach addresses the issue of negative transfer in diffusion models by allowing for efficient computation of MTL methods. We validate the efficacy of proposed clustering and its integration with MTL methods through various experiments, demonstrating 1) improved generation quality and 2) faster training convergence of diffusion models.
Authors: Zhijing Jin, Jiarui Liu, Zhiheng Lyu, Spencer Poff, Mrinmaya Sachan, Rada Mihalcea, Mona Diab, Bernhard Schölkopf
Causal inference is one of the hallmarks of human intelligence. While the field of CausalNLP has attracted much interest in the recent years, existing causal inference datasets in NLP primarily rely on discovering causality from empirical knowledge (e.g., commonsense knowledge). In this work, we propose the first benchmark dataset to test the pure causal inference skills of large language models (LLMs). Specifically, we formulate a novel task Corr2Cause, which takes a set of correlational statements and determines the causal relationship between the variables. We curate a large-scale dataset of more than 200K samples, on which we evaluate seventeen existing LLMs. Through our experiments, we identify a key shortcoming of LLMs in terms of their causal inference skills, and show that these models achieve almost close to random performance on the task. This shortcoming is somewhat mitigated when we try to re-purpose LLMs for this skill via finetuning, but we find that these models still fail to generalize -- they can only perform causal inference in in-distribution settings when variable names and textual expressions used in the queries are similar to those in the training set, but fail in out-of-distribution settings generated by perturbing these queries. Corr2Cause is a challenging task for LLMs, and would be helpful in guiding future research on improving LLMs' pure reasoning skills and generalizability. Our data is at https://huggingface.co/datasets/causalnlp/corr2cause. Our code is at https://github.com/causalNLP/corr2cause.
Authors: Jiawei Zhao, Yifei Zhang, Beidi Chen, Florian Schäfer, Anima Anandkumar
The theory of greedy low-rank learning (GLRL) aims to explain the impressive generalization capabilities of deep learning. It proves that stochastic gradient-based training implicitly regularizes neural networks towards low-rank solutions through a gradual increase of the rank during training. However, there is a gap between theory and practice since GLRL requires an infinitesimal initialization of the weights, which is not practical due to the fact that it is a saddle point. In this work, we remove the assumption of infinitesimal initialization by focusing on cumulative weight updates. We prove the cumulative weight updates follow an incremental low-rank trajectory for arbitrary orthogonal initialization of weights in a three-layer linear network. Empirically, we demonstrate that our theory holds on a broad range of neural networks (e.g., transformers) and standard training algorithms (e.g., SGD, Adam). However, existing training algorithms do not exploit the low-rank property to improve computational efficiency as the networks are not parameterized in low-rank. To remedy this, we design a new training algorithm Incremental Low-Rank Learning (InRank), which explicitly expresses cumulative weight updates as low-rank matrices while incrementally augmenting their ranks during training. We evaluate InRank on GPT-2, and our results indicate that InRank achieves comparable prediction performance as the full-rank counterpart while requiring at most 33% of the total ranks throughout training. We also propose an efficient version of InRank that achieves a reduction of 37% in total training time and 36% in model size when training GPT-medium on WikiText-103 from scratch.
Authors: Keshav Motwani, Daniela Witten
Recent work has focused on the very common practice of prediction-based inference: that is, (i) using a pre-trained machine learning model to predict an unobserved response variable, and then (ii) conducting inference on the association between that predicted response and some covariates. As pointed out by Wang et al. (2020), applying a standard inferential approach in (ii) does not accurately quantify the association between the unobserved (as opposed to the predicted) response and the covariates. In recent work, Wang et al. (2020) and Angelopoulos et al. (2023) propose corrections to step (ii) in order to enable valid inference on the association between the unobserved response and the covariates. Here, we show that the method proposed by Angelopoulos et al. (2023) successfully controls the type 1 error rate and provides confidence intervals with correct nominal coverage, regardless of the quality of the pre-trained machine learning model used to predict the unobserved response. However, the method proposed by Wang et al. (2020) provides valid inference only under very strong conditions that rarely hold in practice: for instance, if the machine learning model perfectly estimates the true regression function in the study population of interest.
Authors: Yuwei Luo, Mohsen Bayati
This paper is motivated by recent research in the $d$-dimensional stochastic linear bandit literature, which has revealed an unsettling discrepancy: algorithms like Thompson sampling and Greedy demonstrate promising empirical performance, yet this contrasts with their pessimistic theoretical regret bounds. The challenge arises from the fact that while these algorithms may perform poorly in certain problem instances, they generally excel in typical instances. To address this, we propose a new data-driven technique that tracks the geometric properties of the uncertainty ellipsoid around the main problem parameter. This methodology enables us to formulate an instance-dependent frequentist regret bound, which incorporates the geometric information, for a broad class of base algorithms, including Greedy, OFUL, and Thompson sampling. This result allows us to identify and ``course-correct" problem instances in which the base algorithms perform poorly. The course-corrected algorithms achieve the minimax optimal regret of order $\tilde{\mathcal{O}}(d\sqrt{T})$ for a $T$-period decision-making scenario, effectively maintaining the desirable attributes of the base algorithms, including their empirical efficacy. We present simulation results to validate our findings using synthetic and real data.
Authors: Weiming Zhuang, Chen Chen, Lingjuan Lyu
The intersection of the Foundation Model (FM) and Federated Learning (FL) provides mutual benefits, presents a unique opportunity to unlock new possibilities in AI research, and address critical challenges in AI and real-world applications. FL expands the availability of data for FMs and enables computation sharing, distributing the training process and reducing the burden on FL participants. It promotes collaborative FM development, democratizing the process and fostering inclusivity and innovation. On the other hand, FM, with its enormous size, pre-trained knowledge, and exceptional performance, serves as a robust starting point for FL, facilitating faster convergence and better performance under non-iid data. Additionally, leveraging FM to generate synthetic data enriches data diversity, reduces overfitting, and preserves privacy. By examining the interplay between FL and FM, this paper aims to deepen the understanding of their synergistic relationship, highlighting the motivations, challenges, and future directions. Through an exploration of the challenges faced by FL and FM individually and their interconnections, we aim to inspire future research directions that can further enhance both fields, driving advancements and propelling the development of privacy-preserving and scalable AI systems.
Authors: Kamyar Dobakhti, Jafar Ghazanfarian
The real power of artificial intelligence appears in reinforcement learning, which is computationally and physically more sophisticated due to its dynamic nature. Rotation and injection are some of the proven ways in active flow control for drag reduction on blunt bodies. In this paper, rotation will be added to the cylinder alongside the deep reinforcement learning (DRL) algorithm, which uses multiple controlled jets to reach the maximum possible drag suppression. Characteristics of the DRL code, including controlling parameters, their limitations, and optimization of the DRL network for use with rotation will be presented. This work will focus on optimizing the number and positions of the jets, the sensors location, and the maximum allowed flow rate to jets in the form of the maximum allowed flow rate of each actuation and the total number of them per episode. It is found that combining the rotation and DRL is promising since it suppresses the vortex shedding, stabilizes the Karman vortex street, and reduces the drag coefficient by up to 49.75%. Also, it will be shown that having more sensors at more locations is not always a good choice and the sensor number and location should be determined based on the need of the user and corresponding configuration. Also, allowing the agent to have access to higher flow rates, mostly reduces the performance, except when the cylinder rotates. In all cases, the agent can keep the lift coefficient at a value near zero, or stabilize it at a smaller number.
Authors: Guanyi Wang, Mengqi Lou, Ashwin Pananjady
We study a principal component analysis problem under the spiked Wishart model in which the structure in the signal is captured by a class of union-of-subspace models. This general class includes vanilla sparse PCA as well as its variants with graph sparsity. With the goal of studying these problems under a unified statistical and computational lens, we establish fundamental limits that depend on the geometry of the problem instance, and show that a natural projected power method exhibits local convergence to the statistically near-optimal neighborhood of the solution. We complement these results with end-to-end analyses of two important special cases given by path and tree sparsity in a general basis, showing initialization methods and matching evidence of computational hardness. Overall, our results indicate that several of the phenomena observed for vanilla sparse PCA extend in a natural fashion to its structured counterparts.
Authors: Jason Liang, Hormoz Shahrzad, Risto Miikkulainen
Many evolutionary algorithms (EAs) take advantage of parallel evaluation of candidates. However, if evaluation times vary significantly, many worker nodes (i.e.,\ compute clients) are idle much of the time, waiting for the next generation to be created. Evolutionary neural architecture search (ENAS), a class of EAs that optimizes the architecture and hyperparameters of deep neural networks, is particularly vulnerable to this issue. This paper proposes a generic asynchronous evaluation strategy (AES) that is then adapted to work with ENAS. AES increases throughput by maintaining a queue of up to $K$ individuals ready to be sent to the workers for evaluation and proceeding to the next generation as soon as $M<<K$ individuals have been evaluated. A suitable value for $M$ is determined experimentally, balancing diversity and efficiency. To showcase the generality and power of AES, it was first evaluated in eight-line sorting network design (a single-population optimization task with limited evaluation-time variability), achieving an over two-fold speedup. Next, it was evaluated in 11-bit multiplexer design (a single-population discovery task with extended variability), where a 14-fold speedup was observed. It was then scaled up to ENAS for image captioning (a multi-population open-ended-optimization task), resulting in an over two-fold speedup. In all problems, a multifold performance improvement was observed, suggesting that AES is a promising method for parallelizing the evolution of complex systems with long and variable evaluation times, such as those in ENAS.
Authors: Siyuan Shan, Yang Li, Amartya Banerjee, Junier B. Oliva
Voice conversion (VC) aims at altering a person's voice to make it sound similar to the voice of another person while preserving linguistic content. Existing methods suffer from a dilemma between content intelligibility and speaker similarity; i.e., methods with higher intelligibility usually have a lower speaker similarity, while methods with higher speaker similarity usually require plenty of target speaker voice data to achieve high intelligibility. In this work, we propose a novel method \textit{Phoneme Hallucinator} that achieves the best of both worlds. Phoneme Hallucinator is a one-shot VC model; it adopts a novel model to hallucinate diversified and high-fidelity target speaker phonemes based just on a short target speaker voice (e.g. 3 seconds). The hallucinated phonemes are then exploited to perform neighbor-based voice conversion. Our model is a text-free, any-to-any VC model that requires no text annotations and supports conversion to any unseen speaker. Objective and subjective evaluations show that \textit{Phoneme Hallucinator} outperforms existing VC methods for both intelligibility and speaker similarity.
Authors: William Shen, Ge Yang, Alan Yu, Jansen Wong, Leslie Pack Kaelbling, Phillip Isola
Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization. Many robotic tasks, however, require a detailed understanding of 3D geometry, which is often lacking in 2D image features. This work bridges this 2D-to-3D gap for robotic manipulation by leveraging distilled feature fields to combine accurate 3D geometry with rich semantics from 2D foundation models. We present a few-shot learning method for 6-DOF grasping and placing that harnesses these strong spatial and semantic priors to achieve in-the-wild generalization to unseen objects. Using features distilled from a vision-language model, CLIP, we present a way to designate novel objects for manipulation via free-text natural language, and demonstrate its ability to generalize to unseen expressions and novel categories of objects.
Authors: Xin Ding, Yongwei Wang, Zuheng Xu
Continuous Conditional Generative Adversarial Networks (CcGANs) enable generative modeling conditional on continuous scalar variables (termed regression labels). However, they can produce subpar fake images due to limited training data. Although Negative Data Augmentation (NDA) effectively enhances unconditional and class-conditional GANs by introducing anomalies into real training images, guiding the GANs away from low-quality outputs, its impact on CcGANs is limited, as it fails to replicate negative samples that may occur during the CcGAN sampling. We present a novel NDA approach called Dual-NDA specifically tailored for CcGANs to address this problem. Dual-NDA employs two types of negative samples: visually unrealistic images generated from a pre-trained CcGAN and label-inconsistent images created by manipulating real images' labels. Leveraging these negative samples, we introduce a novel discriminator objective alongside a modified CcGAN training algorithm. Empirical analysis on UTKFace and Steering Angle reveals that Dual-NDA consistently enhances the visual fidelity and label consistency of fake images generated by CcGANs, exhibiting a substantial performance gain over the vanilla NDA. Moreover, by applying Dual-NDA, CcGANs demonstrate a remarkable advancement beyond the capabilities of state-of-the-art conditional GANs and diffusion models, establishing a new pinnacle of performance. Our codes can be found at https://github.com/UBCDingXin/Dual-NDA.
Authors: Fumiyuki Kato, Li Xiong, Shun Takagi, Yang Cao, Masatoshi Yoshikawa
Differentially Private Federated Learning (DP-FL) has garnered attention as a collaborative machine learning approach that ensures formal privacy. Most DP-FL approaches ensure DP at the record-level within each silo for cross-silo FL. However, a single user's data may extend across multiple silos, and the desired user-level DP guarantee for such a setting remains unknown. In this study, we present Uldp-FL, a novel FL framework designed to guarantee user-level DP in cross-silo FL where a single user's data may belong to multiple silos. Our proposed algorithm directly ensures user-level DP through per-user weighted clipping, departing from group-privacy approaches. We provide a theoretical analysis of the algorithm's privacy and utility. Additionally, we enhance the utility of the proposed algorithm with an enhanced weighting strategy based on user record distribution and design a novel private protocol that ensures no additional information is revealed to the silos and the server. Experiments on real-world datasets show substantial improvements in our methods in privacy-utility trade-offs under user-level DP compared to baseline methods. To the best of our knowledge, our work is the first FL framework that effectively provides user-level DP in the general cross-silo FL setting.
Authors: Hangyu Zhu, Yuxiang Fan, Zhenping Xie
Federated learning has gained significant attention due to its groundbreaking ability to enable distributed learning while maintaining privacy constraints. However, as a consequence of data heterogeneity among decentralized devices, it inherently experiences significant learning degradation and slow convergence speed. Therefore, it is natural to employ the concept of clustering homogeneous clients into the same group, allowing only the model weights within each group to be aggregated. While most existing clustered federated learning methods employ either model gradients or inference outputs as metrics for client partitioning, with the goal of grouping similar devices together, may still have heterogeneity within each cluster. Moreover, there is a scarcity of research exploring the underlying reasons for determining the appropriate timing for clustering, resulting in the common practice of assigning each client to its own individual cluster, particularly in the context of highly non independent and identically distributed (Non-IID) data. In this paper, we introduce a two-stage decoupling federated learning algorithm with adaptive personalization layers named FedTSDP, where client clustering is performed twice according to inference outputs and model weights, respectively. Hopkins amended sampling is adopted to determine the appropriate timing for clustering and the sampling weight of public unlabeled data. In addition, a simple yet effective approach is developed to adaptively adjust the personalization layers based on varying degrees of data skew. Experimental results show that our proposed method has reliable performance on both IID and non-IID scenarios.
Authors: Debsundar Dey, Suchandan Das, Anik Pal, Santanu Dey, Chandan Kumar Raul, Arghya Chatterjee
The reason behind the remarkable properties of High-Entropy Alloys (HEAs) is rooted in the diverse phases and the crystal structures they contain. In the realm of material informatics, employing machine learning (ML) techniques to classify phases and crystal structures of HEAs has gained considerable significance. In this study, we assembled a new collection of 1345 HEAs with varying compositions to predict phases. Within this collection, there were 705 sets of data that were utilized to predict the crystal structures with the help of thermodynamics and electronic configuration. Our study introduces a methodical framework i.e., the Pearson correlation coefficient that helps in selecting the strongly co-related features to increase the prediction accuracy. This study employed five distinct boosting algorithms to predict phases and crystal structures, offering an enhanced guideline for improving the accuracy of these predictions. Among all these algorithms, XGBoost gives the highest accuracy of prediction (94.05%) for phases and LightGBM gives the highest accuracy of prediction of crystal structure of the phases (90.07%). The quantification of the influence exerted by parameters on the model's accuracy was conducted and a new approach was made to elucidate the contribution of individual parameters in the process of phase prediction and crystal structure prediction.
Authors: Lianke Qin, Aravind Reddy, Zhao Song
Mahalanobis metrics are widely used in machine learning in conjunction with methods like $k$-nearest neighbors, $k$-means clustering, and $k$-medians clustering. Despite their importance, there has not been any prior work on applying sketching techniques to speed up algorithms for Mahalanobis metrics. In this paper, we initiate the study of dimension reduction for Mahalanobis metrics. In particular, we provide efficient data structures for solving the Approximate Distance Estimation (ADE) problem for Mahalanobis distances. We first provide a randomized Monte Carlo data structure. Then, we show how we can adapt it to provide our main data structure which can handle sequences of \textit{adaptive} queries and also online updates to both the Mahalanobis metric matrix and the data points, making it amenable to be used in conjunction with prior algorithms for online learning of Mahalanobis metrics.
Authors: Martin N. P. Nilsson
In the intricate architecture of the mammalian central nervous system, neurons form populations. Axonal bundles communicate between these clusters using spike trains. However, these neuron populations' precise encoding and operations have yet to be discovered. In our analysis, the starting point is a state-of-the-art mechanistic model of a generic neuron endowed with plasticity. From this simple framework emerges a subtle mathematical construct: The representation and manipulation of information can be precisely characterized by an algebra of convex cones. Furthermore, these neuron populations are not merely passive transmitters. They act as operators within this algebraic structure, mirroring the functionality of a low-level programming language. When these populations interconnect, they embody succinct yet potent algebraic expressions. These networks allow them to implement many operations, such as specialization, generalization, novelty detection, dimensionality reduction, inverse modeling, prediction, and associative memory. In broader terms, this work illuminates the potential of matrix embeddings in advancing our understanding in fields like cognitive science and AI. These embeddings enhance the capacity for concept processing and hierarchical description over their vector counterparts.
Authors: Ruigang Zheng, Xiaosheng Zhuang
In this paper, we propose a novel and general framework to construct tight framelet systems on graphs with localized supports based on hierarchical partitions. Our construction provides parametrized graph framelet systems with great generality based on partition trees, by which we are able to find the size of a low-dimensional subspace that best fits the low-rank structure of a family of signals. The orthogonal decomposition of subspaces provides a key ingredient for the definition of "generalized vanishing moments" for graph framelets. In a data-adaptive setting, the graph framelet systems can be learned by solving an optimization problem on Stiefel manifolds with respect to our parameterization. Moreover, such graph framelet systems can be further improved by solving a subsequent optimization problem on Stiefel manifolds, aiming at providing the utmost sparsity for a given family of graph signals. Experimental results show that our learned graph framelet systems perform superiorly in non-linear approximation and denoising tasks.
Authors: Lingyu Feng, Ting Gao, Wang Xiao, Jinqiao Duan
Detecting early warning indicators for abrupt dynamical transitions in complex systems or high-dimensional observation data is essential in many real-world applications, such as brain diseases, natural disasters, financial crises, and engineering reliability. To this end, we develop a novel approach: the directed anisotropic diffusion map that captures the latent evolutionary dynamics in the low-dimensional manifold. Then three effective warning signals (Onsager-Machlup Indicator, Sample Entropy Indicator, and Transition Probability Indicator) are derived through the latent coordinates and the latent stochastic dynamical systems. To validate our framework, we apply this methodology to authentic electroencephalogram (EEG) data. We find that our early warning indicators are capable of detecting the tipping point during state transition. This framework not only bridges the latent dynamics with real-world data but also shows the potential ability for automatic labeling on complex high-dimensional time series.
Authors: Rajesh Kumar, Can Isik, Chilukuri K. Mohan
We present a novel adversarial model for authentication systems that use gait patterns recorded by the inertial measurement unit (IMU) built into smartphones. The attack idea is inspired by and named after the concept of a dictionary attack on knowledge (PIN or password) based authentication systems. In particular, this work investigates whether it is possible to build a dictionary of IMUGait patterns and use it to launch an attack or find an imitator who can actively reproduce IMUGait patterns that match the target's IMUGait pattern. Nine physically and demographically diverse individuals walked at various levels of four predefined controllable and adaptable gait factors (speed, step length, step width, and thigh-lift), producing 178 unique IMUGait patterns. Each pattern attacked a wide variety of user authentication models. The deeper analysis of error rates (before and after the attack) challenges the belief that authentication systems based on IMUGait patterns are the most difficult to spoof; further research is needed on adversarial models and associated countermeasures.
Authors: Vanessa Lopez-Marrero, Patrick R. Johnstone, Gilchan Park, Xihaier Luo
One among several advantages of measure transport methods is that they allow for a unified framework for processing and analysis of data distributed according to a wide class of probability measures. Within this context, we present results from computational studies aimed at assessing the potential of measure transport techniques, specifically, the use of triangular transport maps, as part of a workflow intended to support research in the biological sciences. Scarce data scenarios, which are common in domains such as radiation biology, are of particular interest. We find that when data is scarce, sparse transport maps are advantageous. In particular, statistics gathered from computing series of (sparse) adaptive transport maps, trained on a series of randomly chosen subsets of the set of available data samples, leads to uncovering information hidden in the data. As a result, in the radiation biology application considered here, this approach provides a tool for generating hypotheses about gene relationships and their dynamics under radiation exposure.
Authors: Xiyao Wang, Ruijie Zheng, Yanchao Sun, Ruonan Jia, Wichayaporn Wongkamjan, Huazhe Xu, Furong Huang
Dyna-style model-based reinforcement learning contains two phases: model rollouts to generate sample for policy learning and real environment exploration using current policy for dynamics model learning. However, due to the complex real-world environment, it is inevitable to learn an imperfect dynamics model with model prediction error, which can further mislead policy learning and result in sub-optimal solutions. In this paper, we propose $\texttt{COPlanner}$, a planning-driven framework for model-based methods to address the inaccurately learned dynamics model problem with conservative model rollouts and optimistic environment exploration. $\texttt{COPlanner}$ leverages an uncertainty-aware policy-guided model predictive control (UP-MPC) component to plan for multi-step uncertainty estimation. This estimated uncertainty then serves as a penalty during model rollouts and as a bonus during real environment exploration respectively, to choose actions. Consequently, $\texttt{COPlanner}$ can avoid model uncertain regions through conservative model rollouts, thereby alleviating the influence of model error. Simultaneously, it explores high-reward model uncertain regions to reduce model error actively through optimistic real environment exploration. $\texttt{COPlanner}$ is a plug-and-play framework that can be applied to any dyna-style model-based methods. Experimental results on a series of proprioceptive and visual continuous control tasks demonstrate that both sample efficiency and asymptotic performance of strong model-based methods are significantly improved combined with $\texttt{COPlanner}$.
Authors: Chitu Okoli
Accumulated Local Effects (ALE) is a model-agnostic approach for global explanations of the results of black-box machine learning (ML) algorithms. There are at least three challenges with conducting statistical inference based on ALE: ensuring the reliability of ALE analyses, especially in the context of small datasets; intuitively characterizing a variable's overall effect in ML; and making robust inferences from ML data analysis. In response, we introduce innovative tools and techniques for statistical inference using ALE, establishing bootstrapped confidence intervals tailored to dataset size and introducing ALE effect size measures that intuitively indicate effects on both the outcome variable scale and a normalized scale. Furthermore, we demonstrate how to use these tools to draw reliable statistical inferences, reflecting the flexible patterns ALE adeptly highlights, with implementations available in the 'ale' package in R. This work propels the discourse on ALE and its applicability in ML and statistical analysis forward, offering practical solutions to prevailing challenges in the field.
Authors: Xiaochen Zhu, Xinjian Luo, Yuncheng Wu, Yangfan Jiang, Xiaokui Xiao, Beng Chin Ooi
Split Learning (SL) has emerged as a practical and efficient alternative to traditional federated learning. While previous attempts to attack SL have often relied on overly strong assumptions or targeted easily exploitable models, we seek to develop more practical attacks. We introduce SDAR, a novel attack framework against SL with an honest-but-curious server. SDAR leverages auxiliary data and adversarial regularization to learn a decodable simulator of the client's private model, which can effectively infer the client's private features under the vanilla SL, and both features and labels under the U-shaped SL. We perform extensive experiments in both configurations to validate the effectiveness of our proposed attacks. Notably, in challenging but practical scenarios where existing passive attacks struggle to reconstruct the client's private data effectively, SDAR consistently achieves attack performance comparable to active attacks. On CIFAR-10, at the deep split level of 7, SDAR achieves private feature reconstruction with less than 0.025 mean squared error in both the vanilla and the U-shaped SL, and attains a label inference accuracy of over 98% in the U-shaped setting, while existing attacks fail to produce non-trivial results.
Authors: Yu Sun, Zihui Wu, Yifan Chen, Berthy T. Feng, Katherine L. Bouman
Estimating high-quality images while also quantifying their uncertainty are two desired features in an image reconstruction algorithm for solving ill-posed inverse problems. In this paper, we propose plug-and-play Monte Carlo (PMC) as a principled framework for characterizing the space of possible solutions to a general inverse problem. PMC is able to incorporate expressive score-based generative priors for high-quality image reconstruction while also performing uncertainty quantification via posterior sampling. In particular, we introduce two PMC algorithms which can be viewed as the sampling analogues of the traditional plug-and-play priors (PnP) and regularization by denoising (RED) algorithms. We also establish a theoretical analysis for characterizing the convergence of the PMC algorithms. Our analysis provides non-asymptotic stationarity guarantees for both algorithms, even in the presence of non-log-concave likelihoods and imperfect score networks. We demonstrate the performance of the PMC algorithms on multiple representative inverse problems with both linear and nonlinear forward models. Experimental results show that PMC significantly improves reconstruction quality and enables high-fidelity uncertainty quantification.
Authors: Yifei Xiong, Nianqiao P. Ju, Sanguo Zhang
Many modern statistical analysis and machine learning applications require training models on sensitive user data. Differential privacy provides a formal guarantee that individual-level information about users does not leak. In this framework, randomized algorithms inject calibrated noise into the confidential data, resulting in privacy-protected datasets or queries. However, restricting access to only privatized data during statistical analysis makes it computationally challenging to make valid inferences on the parameters underlying the confidential data. In this work, we propose simulation-based inference methods from privacy-protected datasets. In addition to sequential Monte Carlo approximate Bayesian computation, we use neural conditional density estimators as a flexible family of distributions to approximate the posterior distribution of model parameters given the observed private query results. We illustrate our methods on discrete time-series data under an infectious disease model and with ordinary linear regression models. Illustrating the privacy-utility trade-off, our experiments and analysis demonstrate the necessity and feasibility of designing valid statistical inference procedures to correct for biases introduced by the privacy-protection mechanisms.
Authors: Hongjun Zhang
Try to generate new bridge types using generative artificial intelligence technology. The grayscale images of the bridge facade with the change of component width was rendered by 3dsMax animation software, and then the OpenCV module performed an appropriate amount of geometric transformation (rotation, horizontal scale, vertical scale) to obtain the image dataset of three-span beam bridge, arch bridge, cable-stayed bridge and suspension bridge. Based on Python programming language, TensorFlow and Keras deep learning platform framework, variational autoencoder was constructed and trained, and low-dimensional bridge-type latent space that is convenient for vector operations was obtained. Variational autoencoder can combine two bridge types on the basis of the original of human into one that is a new bridge type. Generative artificial intelligence technology can assist bridge designers in bridge-type innovation, and can be used as copilot.
Authors: Yixin Liu, Kaidi Xu, Xun Chen, Lichao Sun
The open source of large amounts of image data promotes the development of deep learning techniques. Along with this comes the privacy risk of these open-source image datasets being exploited by unauthorized third parties to train deep learning models for commercial or illegal purposes. To avoid the abuse of public data, a poisoning-based technique, the unlearnable example, is proposed to significantly degrade the generalization performance of models by adding a kind of imperceptible noise to the data. To further enhance its robustness against adversarial training, existing works leverage iterative adversarial training on both the defensive noise and the surrogate model. However, it still remains unknown whether the robustness of unlearnable examples primarily comes from the effect of enhancement in the surrogate model or the defensive noise. Observing that simply removing the adversarial noise on the training process of the defensive noise can improve the performance of robust unlearnable examples, we identify that solely the surrogate model's robustness contributes to the performance. Furthermore, we found a negative correlation exists between the robustness of defensive noise and the protection performance, indicating defensive noise's instability issue. Motivated by this, to further boost the robust unlearnable example, we introduce stable error-minimizing noise (SEM), which trains the defensive noise against random perturbation instead of the time-consuming adversarial perturbation to improve the stability of defensive noise. Through extensive experiments, we demonstrate that SEM achieves a new state-of-the-art performance on CIFAR-10, CIFAR-100, and ImageNet Subset in terms of both effectiveness and efficiency. The code is available at https://github.com/liuyixin-louis/Stable-Unlearnable-Example.
Authors: Sai Akash Bathini, Dagli Cihan
The application of Machine learning to finance has become a familiar approach, even more so in stock market forecasting. The stock market is highly volatile, and huge amounts of data are generated every minute globally. The extraction of effective intelligence from this data is of critical importance. However, a collaboration of numerical stock data with qualitative text data can be a challenging task. In this work, we accomplish this by providing an unprecedented, publicly available dataset with technical and fundamental data and sentiment that we gathered from news archives, TV news captions, radio transcripts, tweets, daily financial newspapers, etc. The text data entries used for sentiment extraction total more than 1.4 Million. The dataset consists of daily entries from January 2018 to December 2022 for eight companies representing diverse industrial sectors and the Dow Jones Industrial Average (DJIA) as a whole. Holistic Fundamental and Technical data is provided training ready for Model learning and deployment. Most importantly, the data generated could be used for incremental online learning with real-time data points retrieved daily since no stagnant data was utilized. All the data was retired from APIs or self-designed robust information retrieval technologies. These adaptable technologies facilitate data extraction for any stock. Moreover, the utilization of Spearman's rank correlation over real-time data, linking stock returns with sentiment analysis has produced noteworthy results for the DJIA, achieving accuracy levels surpassing 60\%. The dataset is made available at https://github.com/batking24/Huge-Stock-Dataset.
Authors: Thomas Chen
We consider the gradient descent flow widely used for the minimization of the $\mathcal{L}^2$ cost function in Deep Learning networks, and introduce two modified versions; one adapted for the overparametrized setting, and the other for the underparametrized setting. Both have a clear and natural invariant geometric meaning, taking into account the pullback vector bundle structure in the overparametrized, and the pushforward vector bundle structure in the underparametrized setting. In the overparametrized case, we prove that, provided that a rank condition holds, all orbits of the modified gradient descent drive the $\mathcal{L}^2$ cost to its global minimum at a uniform exponential convergence rate; one thereby obtains an a priori stopping time for any prescribed proximity to the global minimum. We point out relations of the latter to sub-Riemannian geometry.
Authors: Menouar Azib, Benjamin Renard, Philippe Garnier, Vincent Génot, Nicolas André
Event detection in time series is a challenging task due to the prevalence of imbalanced datasets, rare events, and time interval-defined events. Traditional supervised deep learning methods primarily employ binary classification, where each time step is assigned a binary label indicating the presence or absence of an event. However, these methods struggle to handle these specific scenarios effectively. To address these limitations, we propose a novel supervised regression-based deep learning approach that offers several advantages over classification-based methods. Our approach, with a limited number of parameters, can effectively handle various types of events within a unified framework, including rare events and imbalanced datasets. We provide theoretical justifications for its universality and precision and demonstrate its superior performance across diverse domains, particularly for rare events and imbalanced datasets.
Authors: Vincent Roulet, Atish Agarwala, Fabian Pedregosa
Recent empirical work has revealed an intriguing property of deep learning models by which the sharpness (largest eigenvalue of the Hessian) increases throughout optimization until it stabilizes around a critical value at which the optimizer operates at the edge of stability, given a fixed stepsize (Cohen et al, 2022). We investigate empirically how the sharpness evolves when using stepsize-tuners, the Armijo linesearch and Polyak stepsizes, that adapt the stepsize along the iterations to local quantities such as, implicitly, the sharpness itself. We find that the surprisingly poor performance of a classical Armijo linesearch in the deterministic setting may be well explained by its tendency to ever-increase the sharpness of the objective. On the other hand, we observe that Polyak stepsizes operate generally at the edge of stability or even slightly beyond, outperforming its Armijo and constant stepsizes counterparts in the deterministic setting. We conclude with an analysis that suggests unlocking stepsize tuners requires an understanding of the joint dynamics of the step size and the sharpness.
Authors: Mahesh Ramesh, Aswinkumar Ramkumar
Recent studies have demonstrated the effectiveness of Gated Linear Units (GLU) in enhancing transformer models, particularly in Large Language Models (LLMs). Additionally, utilizing a parallel configuration within each Transformer block rather than the conventional serialized method has been revealed to accelerate the training of LLMs without significantly impacting performance. However, when the MLP and attention block were run in parallel for the image classification task, we observed a noticeable decline in performance. We propose a novel transformer variant that integrates non-linearity within the attention block to tackle this problem. We implemented the GLU-based activation function on the Value tensor, and this new technique surpasses the current state-of-the-art S/16 variant of Vision Transformers by 0.6% on the ImageNet-1K dataset while utilizing fewer parameters. It also supersedes the B/16 variant while using only half the parameters. Furthermore, we provide results with the GELU activation function variant to confirm our assertions. Lastly, we showcase that the MABViT variants exhibit greater potential when utilized in deep transformers compared to the standard architecture.
Authors: Derek Lim, Haggai Maron, Marc T. Law, Jonathan Lorraine, James Lucas
Neural networks efficiently encode learned information within their parameters. Consequently, many tasks can be unified by treating neural networks themselves as input data. When doing so, recent studies demonstrated the importance of accounting for the symmetries and geometry of parameter spaces. However, those works developed architectures tailored to specific networks such as MLPs and CNNs without normalization layers, and generalizing such architectures to other types of networks can be challenging. In this work, we overcome these challenges by building new metanetworks - neural networks that take weights from other neural networks as input. Put simply, we carefully build graphs representing the input neural networks and process the graphs using graph neural networks. Our approach, Graph Metanetworks (GMNs), generalizes to neural architectures where competing methods struggle, such as multi-head attention layers, normalization layers, convolutional layers, ResNet blocks, and group-equivariant linear layers. We prove that GMNs are expressive and equivariant to parameter permutation symmetries that leave the input neural network functions unchanged. We validate the effectiveness of our method on several metanetwork tasks over diverse neural network architectures.
Authors: Candi Zheng, Yuan Lan
Popular guidance for denoising diffusion probabilistic model (DDPM) linearly combines distinct conditional models together to provide enhanced control over samples. However, this approach overlooks nonlinear effects that become significant when guidance scale is large. To address this issue, we propose characteristic guidance, a sampling method that provides first-principle non-linear correction for classifier-free guided DDPMs. Such correction forces the guided DDPMs to respect the Fokker-Planck equation of their underlying diffusion process, in a way that is training-free, derivative-free, and compatible with existing sampling methods. Experiments show that characteristic guidance enhances control and reduces color and exposure issues in image generation, proving effective in diverse applications ranging from latent space sampling to solving physics problems like magnet phase transitions.
Authors: Tony T. Wang, Miles Wang, Kaivalya Hariharan, Nir Shavit
LLMs often face competing pressures (for example helpfulness vs. harmlessness). To understand how models resolve such conflicts, we study Llama-2-chat models on the forbidden fact task. Specifically, we instruct Llama-2 to truthfully complete a factual recall statement while forbidding it from saying the correct answer. This often makes the model give incorrect answers. We decompose Llama-2 into 1000+ components, and rank each one with respect to how useful it is for forbidding the correct answer. We find that in aggregate, around 35 components are enough to reliably implement the full suppression behavior. However, these components are fairly heterogeneous and many operate using faulty heuristics. We discover that one of these heuristics can be exploited via a manually designed adversarial attack which we call The California Attack. Our results highlight some roadblocks standing in the way of being able to successfully interpret advanced ML systems. Project website available at https://forbiddenfacts.github.io .
Authors: Hao Tian, Sourav Medya, Wei Ye
Combinatorial Optimization (CO) problems over graphs appear routinely in many applications such as in optimizing traffic, viral marketing in social networks, and matching for job allocation. Due to their combinatorial nature, these problems are often NP-hard. Existing approximation algorithms and heuristics rely on the search space to find the solutions and become time-consuming when this space is large. In this paper, we design a neural method called COMBHelper to reduce this space and thus improve the efficiency of the traditional CO algorithms based on node selection. Specifically, it employs a Graph Neural Network (GNN) to identify promising nodes for the solution set. This pruned search space is then fed to the traditional CO algorithms. COMBHelper also uses a Knowledge Distillation (KD) module and a problem-specific boosting module to bring further efficiency and efficacy. Our extensive experiments show that the traditional CO algorithms with COMBHelper are at least 2 times faster than their original versions.
Authors: Pakkapon Phongthawee, Worameth Chinchuthakun, Nontaphat Sinsunthithet, Amit Raj, Varun Jampani, Pramook Khungurn, Supasorn Suwajanakorn
We present a simple yet effective technique to estimate lighting in a single input image. Current techniques rely heavily on HDR panorama datasets to train neural networks to regress an input with limited field-of-view to a full environment map. However, these approaches often struggle with real-world, uncontrolled settings due to the limited diversity and size of their datasets. To address this problem, we leverage diffusion models trained on billions of standard images to render a chrome ball into the input image. Despite its simplicity, this task remains challenging: the diffusion models often insert incorrect or inconsistent objects and cannot readily generate images in HDR format. Our research uncovers a surprising relationship between the appearance of chrome balls and the initial diffusion noise map, which we utilize to consistently generate high-quality chrome balls. We further fine-tune an LDR difusion model (Stable Diffusion XL) with LoRA, enabling it to perform exposure bracketing for HDR light estimation. Our method produces convincing light estimates across diverse settings and demonstrates superior generalization to in-the-wild scenarios.
Authors: Lei Wang, Jieming Bian, Jie Xu
Federated learning (FL) with noisy labels poses a significant challenge. Existing methods designed for handling noisy labels in centralized learning tend to lose their effectiveness in the FL setting, mainly due to the small dataset size and the heterogeneity of client data. While some attempts have been made to tackle FL with noisy labels, they primarily focused on scenarios involving class-conditional noise. In this paper, we study the more challenging and practical issue of instance-dependent noise (IDN) in FL. We introduce a novel algorithm called FedBeat (Federated Learning with Bayesian Ensemble-Assisted Transition Matrix Estimation). FedBeat aims to build a global statistically consistent classifier using the IDN transition matrix (IDNTM), which encompasses three synergistic steps: (1) A federated data extraction step that constructs a weak global model and extracts high-confidence data using a Bayesian model ensemble method. (2) A federated transition matrix estimation step in which clients collaboratively train an IDNTM estimation network based on the extracted data. (3) A federated classifier correction step that enhances the global model's performance by training it using a loss function tailored for noisy labels, leveraging the IDNTM. Experiments conducted on CIFAR-10 and SVHN verify that the proposed method significantly outperforms state-of-the-art methods.
Authors: Ruining Zhang, Haoran Han, Maolong Lv, Qisong Yang, Jian Cheng
Extensive utilization of deep reinforcement learning (DRL) policy networks in diverse continuous control tasks has raised questions regarding performance degradation in expansive state spaces where the input state norm is larger than that in the training environment. This paper aims to uncover the underlying factors contributing to such performance deterioration when dealing with expanded state spaces, using a novel analysis technique known as state division. In contrast to prior approaches that employ state division merely as a post-hoc explanatory tool, our methodology delves into the intrinsic characteristics of DRL policy networks. Specifically, we demonstrate that the expansion of state space induces the activation function $\tanh$ to exhibit saturability, resulting in the transformation of the state division boundary from nonlinear to linear. Our analysis centers on the paradigm of the double-integrator system, revealing that this gradual shift towards linearity imparts a control behavior reminiscent of bang-bang control. However, the inherent linearity of the division boundary prevents the attainment of an ideal bang-bang control, thereby introducing unavoidable overshooting. Our experimental investigations, employing diverse RL algorithms, establish that this performance phenomenon stems from inherent attributes of the DRL policy network, remaining consistent across various optimization algorithms.
Authors: En Yu, Jie Lu, Bin Zhang, Guangquan Zhang
Multistream classification poses significant challenges due to the necessity for rapid adaptation in dynamic streaming processes with concept drift. Despite the growing research outcomes in this area, there has been a notable oversight regarding the temporal dynamic relationships between these streams, leading to the issue of negative transfer arising from irrelevant data. In this paper, we propose a novel Online Boosting Adaptive Learning (OBAL) method that effectively addresses this limitation by adaptively learning the dynamic correlation among different streams. Specifically, OBAL operates in a dual-phase mechanism, in the first of which we design an Adaptive COvariate Shift Adaptation (AdaCOSA) algorithm to construct an initialized ensemble model using archived data from various source streams, thus mitigating the covariate shift while learning the dynamic correlations via an adaptive re-weighting strategy. During the online process, we employ a Gaussian Mixture Model-based weighting mechanism, which is seamlessly integrated with the acquired correlations via AdaCOSA to effectively handle asynchronous drift. This approach significantly improves the predictive performance and stability of the target stream. We conduct comprehensive experiments on several synthetic and real-world data streams, encompassing various drifting scenarios and types. The results clearly demonstrate that OBAL achieves remarkable advancements in addressing multistream classification problems by effectively leveraging positive knowledge derived from multiple sources.
Authors: Daiki Koge, Naoaki Ono, Shigehiko Kanaya
Learning representations of molecular structures using deep learning is a fundamental problem in molecular property prediction tasks. Molecules inherently exist in the real world as three-dimensional structures; furthermore, they are not static but in continuous motion in the 3D Euclidean space, forming a potential energy surface. Therefore, it is desirable to generate multiple conformations in advance and extract molecular representations using a 4D-QSAR model that incorporates multiple conformations. However, this approach is impractical for drug and material discovery tasks because of the computational cost of obtaining multiple conformations. To address this issue, we propose a pre-training method for molecular GNNs using an existing dataset of molecular conformations to generate a latent vector universal to multiple conformations from a 2D molecular graph. Our method, called Boltzmann GNN, is formulated by maximizing the conditional marginal likelihood of a conditional generative model for conformations generation. We show that our model has a better prediction performance for molecular properties than existing pre-training methods using molecular graphs and three-dimensional molecular structures.
Authors: Harsha Vardhan Tetali, Joel B. Harley, Benjamin D. Haeffele
With the recent success of representation learning methods, which includes deep learning as a special case, there has been considerable interest in developing techniques that incorporate known physical constraints into the learned representation. As one example, in many applications that involve a signal propagating through physical media (e.g., optics, acoustics, fluid dynamics, etc), it is known that the dynamics of the signal must satisfy constraints imposed by the wave equation. Here we propose a matrix factorization technique that decomposes such signals into a sum of components, where each component is regularized to ensure that it {nearly} satisfies wave equation constraints. Although our proposed formulation is non-convex, we prove that our model can be efficiently solved to global optimality. Through this line of work we establish theoretical connections between wave-informed learning and filtering theory in signal processing. We further demonstrate the application of this work on modal analysis problems commonly arising in structural diagnostics and prognostics.
Authors: Chengming Hu, Haolun Wu, Xuan Li, Chen Ma, Xi Chen, Jun Yan, Boyu Wang, Xue Liu
Knowledge distillation aims to train a compact student network using soft supervision from a larger teacher network and hard supervision from ground truths. However, determining an optimal knowledge fusion ratio that balances these supervisory signals remains challenging. Prior methods generally resort to a constant or heuristic-based fusion ratio, which often falls short of a proper balance. In this study, we introduce a novel adaptive method for learning a sample-wise knowledge fusion ratio, exploiting both the correctness of teacher and student, as well as how well the student mimics the teacher on each sample. Our method naturally leads to the intra-sample trilateral geometric relations among the student prediction ($S$), teacher prediction ($T$), and ground truth ($G$). To counterbalance the impact of outliers, we further extend to the inter-sample relations, incorporating the teacher's global average prediction $\bar{T}$ for samples within the same class. A simple neural network then learns the implicit mapping from the intra- and inter-sample relations to an adaptive, sample-wise knowledge fusion ratio in a bilevel-optimization manner. Our approach provides a simple, practical, and adaptable solution for knowledge distillation that can be employed across various architectures and model sizes. Extensive experiments demonstrate consistent improvements over other loss re-weighting methods on image classification, attack detection, and click-through rate prediction.
Authors: Zaifan Jiang, Xing Huang, Chao Wei
Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model based algorithm to optimize preference learning, which first fitting a reward model for preference score, and then optimizing generating policy with on-policy PPO algorithm to maximize the reward. The processing of RLHF is complex, time-consuming and unstable. Direct Preference Optimization (DPO) algorithm using off-policy algorithm to direct optimize generating policy and eliminating the need for reward model, which is data efficient and stable. DPO use Bradley-Terry model and log-loss which leads to over-fitting to the preference data at the expense of ignoring KL-regularization term when preference is deterministic. IPO uses a root-finding MSE loss to solve the ignoring KL-regularization problem. In this paper, we'll figure out, although IPO fix the problem when preference is deterministic, but both DPO and IPO fails the KL-regularization term because the support of preference distribution not equal to reference distribution. Then, we design a simple and intuitive off-policy preference optimization algorithm from an importance sampling view, which we call Maximum Preference Optimization (MPO), and add off-policy KL-regularization terms which makes KL-regularization truly effective. The objective of MPO bears resemblance to RLHF's objective, and likes IPO, MPO is off-policy. So, MPO attains the best of both worlds. To simplify the learning process and save memory usage, MPO eliminates the needs for both reward model and reference policy.
Authors: Ankush Maity, Roshan Pious, Sourabh Kumar Lenka, Vishal Choudhary, Prof. Sharayu Lokhande
This compilation of various research paper highlights provides a comprehensive overview of recent developments in super-resolution image and video using deep learning algorithms such as Generative Adversarial Networks. The studies covered in these summaries provide fresh techniques to addressing the issues of improving image and video quality, such as recursive learning for video super-resolution, novel loss functions, frame-rate enhancement, and attention model integration. These approaches are frequently evaluated using criteria such as PSNR, SSIM, and perceptual indices. These advancements, which aim to increase the visual clarity and quality of low-resolution video, have tremendous potential in a variety of sectors ranging from surveillance technology to medical imaging. In addition, this collection delves into the wider field of Generative Adversarial Networks, exploring their principles, training approaches, and applications across a broad range of domains, while also emphasizing the challenges and opportunities for future research in this rapidly advancing and changing field of artificial intelligence.
Authors: Dongsheng Ding, Zhengyan Huan, Alejandro Ribeiro
We study a class of constrained reinforcement learning (RL) problems in which multiple constraint specifications are not identified before training. It is challenging to identify appropriate constraint specifications due to the undefined trade-off between the reward maximization objective and the constraint satisfaction, which is ubiquitous in constrained decision-making. To tackle this issue, we propose a new constrained RL approach that searches for policy and constraint specifications together. This method features the adaptation of relaxing the constraint according to a relaxation cost introduced in the learning objective. Since this feature mimics how ecological systems adapt to disruptions by altering operation, our approach is termed as resilient constrained RL. Specifically, we provide a set of sufficient conditions that balance the constraint satisfaction and the reward maximization in notion of resilient equilibrium, propose a tractable formulation of resilient constrained policy optimization that takes this equilibrium as an optimal solution, and advocate two resilient constrained policy search algorithms with non-asymptotic convergence guarantees on the optimality gap and constraint satisfaction. Furthermore, we demonstrate the merits and the effectiveness of our approach in computational experiments.
Authors: Han Zhou, Wei Dong, Yangyi Liu, Jun Chen
Haze usually leads to deteriorated images with low contrast, color shift and structural distortion. We observe that many deep learning based models exhibit exceptional performance on removing homogeneous haze, but they usually fail to address the challenge of non-homogeneous dehazing. Two main factors account for this situation. Firstly, due to the intricate and non uniform distribution of dense haze, the recovery of structural and chromatic features with high fidelity is challenging, particularly in regions with heavy haze. Secondly, the existing small scale datasets for non-homogeneous dehazing are inadequate to support reliable learning of feature mappings between hazy images and their corresponding haze-free counterparts by convolutional neural network (CNN)-based models. To tackle these two challenges, we propose a novel two branch network that leverages 2D discrete wavelete transform (DWT), fast Fourier convolution (FFC) residual block and a pretrained ConvNeXt model. Specifically, in the DWT-FFC frequency branch, our model exploits DWT to capture more high-frequency features. Moreover, by taking advantage of the large receptive field provided by FFC residual blocks, our model is able to effectively explore global contextual information and produce images with better perceptual quality. In the prior knowledge branch, an ImageNet pretrained ConvNeXt as opposed to Res2Net is adopted. This enables our model to learn more supplementary information and acquire a stronger generalization ability. The feasibility and effectiveness of the proposed method is demonstrated via extensive experiments and ablation studies. The code is available at https://github.com/zhouh115/DWT-FFC.
Authors: MD Shafikul Islam, Azmine Toushik Wasi
Inventory Routing Problem (IRP) is a crucial challenge in supply chain management as it involves optimizing efficient route selection while considering the uncertainty of inventory demand planning. To solve IRPs, usually a two-stage approach is employed, where demand is predicted using machine learning techniques first, and then an optimization algorithm is used to minimize routing costs. Our experiment shows machine learning models fall short of achieving perfect accuracy because inventory levels are influenced by the dynamic business environment, which, in turn, affects the optimization problem in the next stage, resulting in sub-optimal decisions. In this paper, we formulate and propose a decision-focused learning-based approach to solving real-world IRPs. This approach directly integrates inventory prediction and routing optimization within an end-to-end system potentially ensuring a robust supply chain strategy.
Authors: Azmine Toushik Wasi
Islamophobic language is a prevalent challenge on online social interaction platforms. Identifying and eliminating such hatred is a crucial step towards a future of harmony and peace. This study presents a novel paradigm for identifying and explaining hate speech towards Islam using graph neural networks. Utilizing the intrinsic ability of graph neural networks to find, extract, and use relationships across disparate data points, our model consistently achieves outstanding performance while offering explanations for the underlying correlations and causation.