Authors: Manpreet Singh, Ravdeep Pasricha, Nitish Singh, Ravi Prasad Kondapalli, Manoj R, Kiran R, Laurent Boué
In this paper, we design a real-time question-answering system specifically targeted for helping sellers get relevant material/documentation they can share live with their customers or refer to during a call. Taking the Seismic content repository as a relatively large scale example of a diverse dataset of sales material, we demonstrate how LLM embeddings of sellers' queries can be matched with the relevant content. We achieve this by engineering prompts in an elaborate fashion that makes use of the rich set of meta-features available for documents and sellers. Using a bi-encoder with cross-encoder re-ranker architecture, we show how the solution returns the most relevant content recommendations in just a few seconds even for large datasets. Our recommender system is deployed as an AML endpoint for real-time inferencing and has been integrated into a Copilot interface that is now deployed in the production version of the Dynamics CRM, known as MSX, used daily by Microsoft sellers.
Authors: Yuanchi Ma, Hui He, Zhongxiang Lei, Zhendong Niu
Graph clustering algorithms with autoencoder structures have recently gained popularity due to their efficient performance and low training cost. However, for existing graph autoencoder clustering algorithms based on GCN or GAT, not only do they lack good generalization ability, but also the number of clusters clustered by such autoencoder models is difficult to determine automatically. To solve this problem, we propose a new framework called Graph Clustering with Masked Autoencoders (GCMA). It employs our designed fusion autoencoder based on the graph masking method for the fusion coding of graph. It introduces our improved density-based clustering algorithm as a second decoder while decoding with multi-target reconstruction. By decoding the mask embedding, our model can capture more generalized and comprehensive knowledge. The number of clusters and clustering results can be output end-to-end while improving the generalization ability. As a nonparametric class method, extensive experiments demonstrate the superiority of \textit{GCMA} over state-of-the-art baselines.
Authors: Soyed Tuhin Ahmed, Michael Hefenbrock, Guillaume Prenat, Lorena Anghel, Mehdi B. Tahoori
Bayesian Neural Networks (BayNNs) can inherently estimate predictive uncertainty, facilitating informed decision-making. Dropout-based BayNNs are increasingly implemented in spintronics-based computation-in-memory architectures for resource-constrained yet high-performance safety-critical applications. Although uncertainty estimation is important, the reliability of Dropout generation and BayNN computation is equally important for target applications but is overlooked in existing works. However, testing BayNNs is significantly more challenging compared to conventional NNs, due to their stochastic nature. In this paper, we present for the first time the model of the non-idealities of the spintronics-based Dropout module and analyze their impact on uncertainty estimates and accuracy. Furthermore, we propose a testing framework based on repeatability ranking for Dropout-based BayNN with up to $100\%$ fault coverage while using only $0.2\%$ of training data as test vectors.
Authors: Galib Muhammad Shahriar Himel, Md. Masudul Islam, Kh Abdullah Al-Aff, Shams Ibne Karim, Md. Kabir Uddin Sikder
Skin cancer is a global health concern, necessitating early and accurate diagnosis for improved patient outcomes. This study introduces a groundbreaking approach to skin cancer classification, employing the Vision Transformer, a state-of-the-art deep learning architecture renowned for its success in diverse image analysis tasks. Utilizing the HAM10000 dataset of 10,015 meticulously annotated skin lesion images, the model undergoes preprocessing for enhanced robustness. The Vision Transformer, adapted to the skin cancer classification task, leverages the self-attention mechanism to capture intricate spatial dependencies, achieving superior performance over traditional deep learning architectures. Segment Anything Model aids in precise segmentation of cancerous areas, attaining high IOU and Dice Coefficient. Extensive experiments highlight the model's supremacy, particularly the Google-based ViT patch-32 variant, which achieves 96.15% accuracy and showcases potential as an effective tool for dermatologists in skin cancer diagnosis, contributing to advancements in dermatological practices.
Authors: Chollette C. Olisah, Ben Trewhella, Bo Li, Melvyn L. Smith, Benjamin Winstone, E. Charles Whitfield, Felicidad Fernández Fernández, Harriet Duncalfe
Fruit ripeness estimation models have for decades depended on spectral index features or colour-based features, such as mean, standard deviation, skewness, colour moments, and/or histograms for learning traits of fruit ripeness. Recently, few studies have explored the use of deep learning techniques to extract features from images of fruits with visible ripeness cues. However, the blackberry (Rubus fruticosus) fruit does not show obvious and reliable visible traits of ripeness when mature and therefore poses great difficulty to fruit pickers. The mature blackberry, to the human eye, is black before, during, and post-ripening. To address this engineering application challenge, this paper proposes a novel multi-input convolutional neural network (CNN) ensemble classifier for detecting subtle traits of ripeness in blackberry fruits. The multi-input CNN was created from a pre-trained visual geometry group 16-layer deep convolutional network (VGG16) model trained on the ImageNet dataset. The fully connected layers were optimized for learning traits of ripeness of mature blackberry fruits. The resulting model served as the base for building homogeneous ensemble learners that were ensemble using the stack generalization ensemble (SGE) framework. The input to the network is images acquired with a stereo sensor using visible and near-infrared (VIS-NIR) spectral filters at wavelengths of 700 nm and 770 nm. Through experiments, the proposed model achieved 95.1% accuracy on unseen sets and 90.2% accuracy with in-field conditions. Further experiments reveal that machine sensory is highly and positively correlated to human sensory over blackberry fruit skin texture.
Authors: Hongcheng Guo, Jian Yang, Jiaheng Liu, Jiaqi Bai, Boyang Wang, Zhoujun Li, Tieqiao Zheng, Bo Zhang, Junran peng, Qi Tian
Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps). Considering log data of variant domains, retraining the whole network for unknown domains is inefficient in real industrial scenarios. However, previous deep models merely focused on extracting the semantics of log sequences in the same domain, leading to poor generalization on multi-domain logs. To alleviate this issue, we propose a unified Transformer-based framework for Log anomaly detection (LogFormer) to improve the generalization ability across different domains, where we establish a two-stage process including the pre-training and adapter-based tuning stage. Specifically, our model is first pre-trained on the source domain to obtain shared semantic knowledge of log data. Then, we transfer such knowledge to the target domain via shared parameters. Besides, the Log-Attention module is proposed to supplement the information ignored by the log-paring. The proposed method is evaluated on three public and one real-world datasets. Experimental results on multiple benchmarks demonstrate the effectiveness of our LogFormer with fewer trainable parameters and lower training costs.
Authors: Daniel Anthony Howard, Bo Nørregaard Jørgensen, Zheng Ma
Improving energy efficiency in industrial production processes is crucial for competitiveness, and compliance with climate policies. This paper introduces a data-driven approach to identify optimal melting patterns in induction furnaces. Through time-series K-means clustering the melting patterns could be classified into distinct clusters based on temperature profiles. Using the elbow method, 12 clusters were identified, representing the range of melting patterns. Performance parameters such as melting time, energy-specific performance, and carbon cost were established for each cluster, indicating furnace efficiency and environmental impact. Multiple criteria decision-making methods including Simple Additive Weighting, Multiplicative Exponential Weighting, Technique for Order of Preference by Similarity to Ideal Solution, modified TOPSIS, and VlseKriterijumska Optimizacija I Kompromisno Resenje were utilized to determine the best-practice cluster. The study successfully identified the cluster with the best performance. Implementing the best practice operation resulted in an 8.6 % reduction in electricity costs, highlighting the potential energy savings in the foundry.
Authors: David Owen
We investigate large language model performance across five orders of magnitude of compute scaling in eleven recent model architectures. We show that average benchmark performance, aggregating over many individual tasks and evaluations as in the commonly-used BIG-Bench dataset, is decently predictable as a function of training compute scale. Specifically, when extrapolating BIG-Bench Hard performance across one order of magnitude in compute, we observe average absolute errors of 6 percentage points (pp). By contrast, extrapolation for individual BIG-Bench tasks across an order of magnitude in compute yields higher average errors of 18pp. Nonetheless, individual task performance remains significantly more predictable than chance. Overall, our work suggests compute scaling provides a promising basis to forecast AI capabilities in diverse benchmarks, though predicting performance in specific tasks poses challenges.
Authors: Florian Brück
In this work, we provide a simulation algorithm to simulate from a (multivariate) characteristic function, which is only accessible in a black-box format. We construct a generative neural network, whose loss function exploits a specific representation of the Maximum-Mean-Discrepancy metric to directly incorporate the targeted characteristic function. The construction is universal in the sense that it is independent of the dimension and that it does not require any assumptions on the given characteristic function. Furthermore, finite sample guarantees on the approximation quality in terms of the Maximum-Mean Discrepancy metric are derived. The method is illustrated in a short simulation study.
Authors: Andrew J. Christlieb, Mingchang Ding, Juntao Huang, Nicholas A. Krupansky
We introduce a hyperbolic closure for the Grad moment expansion of the Bhatnagar-Gross-Krook's (BGK) kinetic model using a neural network (NN) trained on BGK's moment data. This closure is motivated by the exact closure for the free streaming limit that we derived in our paper on closures in transport \cite{Huang2022-RTE1}. The exact closure relates the gradient of the highest moment to the gradient of four lower moments. As with our past work, the model presented here learns the gradient of the highest moment in terms of the coefficients of gradients for all lower ones. By necessity, this means that the resulting hyperbolic system is not conservative in the highest moment. For stability, the output layers of the NN are designed to enforce hyperbolicity and Galilean invariance. This ensures the model can be run outside of the training window of the NN. Unlike our previous work on radiation transport that dealt with linear models, the BGK model's nonlinearity demanded advanced training tools. These comprised an optimal learning rate discovery, one cycle training, batch normalization in each neural layer, and the use of the \texttt{AdamW} optimizer. To address the non-conservative structure of the hyperbolic model, we adopt the FORCE numerical method to achieve robust solutions. This results in a comprehensive computing model combining learned closures with methods for solving hyperbolic models. The proposed model can capture accurate moment solutions across a broad spectrum of Knudsen numbers. Our paper details the multi-scale model construction and is run on a range of test problems.
Authors: Gauri Gupta, Ritvik Kapila, Ayush Chopra, Ramesh Raskar
Pandemics, notably the recent COVID-19 outbreak, have impacted both public health and the global economy. A profound understanding of disease progression and efficient response strategies is thus needed to prepare for potential future outbreaks. In this paper, we emphasize the potential of Agent-Based Models (ABM) in capturing complex infection dynamics and understanding the impact of interventions. We simulate realistic pharmaceutical, behavioral, and digital interventions that mirror challenges in real-world policy adoption and suggest a holistic combination of these interventions for pandemic response. Using these simulations, we study the trends of emergent behavior on a large-scale population based on real-world socio-demographic and geo-census data from Kings County in Washington. Our analysis reveals the pivotal role of the initial 100 days in dictating a pandemic's course, emphasizing the importance of quick decision-making and efficient policy development. Further, we highlight that investing in behavioral and digital interventions can reduce the burden on pharmaceutical interventions by reducing the total number of infections and hospitalizations, and by delaying the pandemic's peak. We also infer that allocating the same amount of dollars towards extensive testing with contact tracing and self-quarantine offers greater cost efficiency compared to spending the entire budget on vaccinations.
Authors: Selahattin Akkas, Ariful Azad
Graph neural networks (GNNs) are popular machine learning models for graphs with many applications across scientific domains. However, GNNs are considered black box models, and it is challenging to understand how the model makes predictions. Game theory-based Shapley value approaches are popular explanation methods in other domains but are not well-studied for graphs. Some studies have proposed Shapley value-based GNN explanations, yet they have several limitations: they consider limited samples to approximate Shapley values; some mainly focus on small and large coalition sizes, and they are an order of magnitude slower than other explanation methods, making them inapplicable to even moderate-size graphs. In this work, we propose GNNShap, which provides explanations for edges since they provide more natural explanations for graphs and more fine-grained explanations. We overcome the limitations by sampling from all coalition sizes, parallelizing the sampling on GPUs, and speeding up model predictions by batching. GNNShap gives better fidelity scores and faster explanations than baselines on real-world datasets.
Authors: Mauro Belgiovine, Joshua Groen, Miquel Sirera, Chinenye Tassie, Ayberk Yarkin Yildiz, Sage Trudeau, Stratis Ioannidis, Kaushik Chowdhury
Spectrum sharing allows different protocols of the same standard (e.g., 802.11 family) or different standards (e.g., LTE and DVB) to coexist in overlapping frequency bands. As this paradigm continues to spread, wireless systems must also evolve to identify active transmitters and unauthorized waveforms in real time under intentional distortion of preambles, extremely low signal-to-noise ratios and challenging channel conditions. We overcome limitations of correlation-based preamble matching methods in such conditions through the design of T-PRIME: a Transformer-based machine learning approach. T-PRIME learns the structural design of transmitted frames through its attention mechanism, looking at sequence patterns that go beyond the preamble alone. The paper makes three contributions: First, it compares Transformer models and demonstrates their superiority over traditional methods and state-of-the-art neural networks. Second, it rigorously analyzes T-PRIME's real-time feasibility on DeepWave's AIR-T platform. Third, it utilizes an extensive 66 GB dataset of over-the-air (OTA) WiFi transmissions for training, which is released along with the code for community use. Results reveal nearly perfect (i.e. $>98\%$) classification accuracy under simulated scenarios, showing $100\%$ detection improvement over legacy methods in low SNR ranges, $97\%$ classification accuracy for OTA single-protocol transmissions and up to $75\%$ double-protocol classification accuracy in interference scenarios.
Authors: Joong-Ho Won, Jinan Jung
This paper presents an in-depth analysis of the generalized isotonic recursive partitioning (GIRP) algorithm for fitting isotonic models under separable convex losses, proposed by Luss and Rosset [J. Comput. Graph. Statist., 23 (2014), pp. 192--201] for differentiable losses and extended by Painsky and Rosset [IEEE Trans. Pattern Anal. Mach. Intell., 38 (2016), pp. 308-321] for nondifferentiable losses. The GIRP algorithm poseses an attractive feature that in each step of the algorithm, the intermediate solution satisfies the isotonicity constraint. The paper begins with an example showing that the GIRP algorithm as described in the literature may fail to produce an isotonic model, suggesting that the existence and uniqueness of the solution to the isotonic regression problem must be carefully addressed. It proceeds with showing that, among possibly many solutions, there indeed exists a solution that can be found by recursive binary partitioning of the set of observed data. A small modification of the GIRP algorithm suffices to obtain a correct solution and preserve the desired property that all the intermediate solutions are isotonic. This proposed modification includes a proper choice of intermediate solutions and a simplification of the partitioning step from ternary to binary.
Authors: Steve Paul, Jhoel Witter, Souma Chowdhury
This paper develops a graph reinforcement learning approach to online planning of the schedule and destinations of electric aircraft that comprise an urban air mobility (UAM) fleet operating across multiple vertiports. This fleet scheduling problem is formulated to consider time-varying demand, constraints related to vertiport capacity, aircraft capacity and airspace safety guidelines, uncertainties related to take-off delay, weather-induced route closures, and unanticipated aircraft downtime. Collectively, such a formulation presents greater complexity, and potentially increased realism, than in existing UAM fleet planning implementations. To address these complexities, a new policy architecture is constructed, primary components of which include: graph capsule conv-nets for encoding vertiport and aircraft-fleet states both abstracted as graphs; transformer layers encoding time series information on demand and passenger fare; and a Multi-head Attention-based decoder that uses the encoded information to compute the probability of selecting each available destination for an aircraft. Trained with Proximal Policy Optimization, this policy architecture shows significantly better performance in terms of daily averaged profits on unseen test scenarios involving 8 vertiports and 40 aircraft, when compared to a random baseline and genetic algorithm-derived optimal solutions, while being nearly 1000 times faster in execution than the latter.
Authors: Saurav Agarwal, Ramya Muthukrishnan, Walker Gosrich, Alejandro Ribeiro, Vijay Kumar
Coverage control is the problem of navigating a robot swarm to collaboratively monitor features or a phenomenon of interest not known a priori. The problem is challenging in decentralized settings with robots that have limited communication and sensing capabilities. This paper proposes a learnable Perception-Action-Communication (LPAC) architecture for the coverage control problem. In the proposed solution, a convolution neural network (CNN) processes localized perception of the environment; a graph neural network (GNN) enables communication of relevant information between neighboring robots; finally, a shallow multi-layer perceptron (MLP) computes robot actions. The GNN in the communication module enables collaboration in the robot swarm by computing what information to communicate with neighbors and how to use received information to take appropriate actions. We train models using imitation learning with a centralized clairvoyant algorithm that is aware of the entire environment. Evaluations show that the LPAC models outperform standard decentralized and centralized coverage control algorithms. The learned policy generalizes to environments different from the training dataset, transfers to larger environments with an increased number of robots, and is robust to noisy position estimates. The results indicate that LPAC architectures are well-suited for decentralized navigation in robot swarms to achieve collaborative behavior.
Authors: Sixu Li, Shi Chen, Qin Li
Score-based Generative Models (SGMs) is one leading method in generative modeling, renowned for their ability to generate high-quality samples from complex, high-dimensional data distributions. The method enjoys empirical success and is supported by rigorous theoretical convergence properties. In particular, it has been shown that SGMs can generate samples from a distribution that is close to the ground-truth if the underlying score function is learned well, suggesting the success of SGM as a generative model. We provide a counter-example in this paper. Through the sample complexity argument, we provide one specific setting where the score function is learned well. Yet, SGMs in this setting can only output samples that are Gaussian blurring of training data points, mimicking the effects of kernel density estimation. The finding resonates a series of recent finding that reveal that SGMs can demonstrate strong memorization effect and fail to generate.
Authors: Haotian Gu, Tim Jacobs, Philip Kaminsky, Xin Guo, Xinyu Li
Currently, Amazon relies on third parties for transportation marketplace rate forecasts, despite the poor quality and lack of interpretability of these forecasts. While transportation marketplace rates are typically very challenging to forecast accurately, we have developed a novel signature-based statistical technique to address these challenges and built a predictive and adaptive model to forecast marketplace rates. This novel technique is based on two key properties of the signature transform. The first is its universal nonlinearity which linearizes the feature space and hence translates the forecasting problem into a linear regression analysis; the second is the signature kernel which allows for comparing computationally efficiently similarities between time series data. Combined, these properties allow for efficient feature generation and more precise identification of seasonality and regime switching in the forecasting process. Preliminary result by the model shows that this new technique leads to far superior forecast accuracy versus commercially available industry models with better interpretability, even during the period of Covid-19 and with the sudden onset of the Ukraine war.
Authors: Sumanth Doddapaneni, Krishna Sayana, Ambarish Jash, Sukhdeep Sodhi, Dima Kuzmin
Modeling long histories plays a pivotal role in enhancing recommendation systems, allowing to capture user's evolving preferences, resulting in more precise and personalized recommendations. In this study we tackle the challenges of modeling long user histories for preference understanding in natural language. Specifically, we introduce a new User Embedding Module (UEM) that efficiently processes user history in free-form text by compressing and representing them as embeddings, to use them as soft prompts to a LM. Our experiments demonstrate the superior capability of this approach in handling significantly longer histories compared to conventional text based prompting methods, yielding substantial improvements in predictive performance. The main contribution of this research is to demonstrate the ability to bias language models with user signals represented as embeddings.
Authors: Yu Liu, Yuexin Zhang, Kunming Li, Yongliang Qiao, Stewart Worrall, You-Fu Li, He Kong
Predicting pedestrian motion trajectories is crucial for path planning and motion control of autonomous vehicles. Accurately forecasting crowd trajectories is challenging due to the uncertain nature of human motions in different environments. For training, recent deep learning-based prediction approaches mainly utilize information like trajectory history and interactions between pedestrians, among others. This can limit the prediction performance across various scenarios since the discrepancies between training datasets have not been properly incorporated. To overcome this limitation, this paper proposes a graph transformer structure to improve prediction performance, capturing the differences between the various sites and scenarios contained in the datasets. In particular, a self-attention mechanism and a domain adaption module have been designed to improve the generalization ability of the model. Moreover, an additional metric considering cross-dataset sequences is introduced for training and performance evaluation purposes. The proposed framework is validated and compared against existing methods using popular public datasets, i.e., ETH and UCY. Experimental results demonstrate the improved performance of our proposed scheme.
Authors: Xinying Mu, Mark Kon
A machine learning (ML) feature network is a graph that connects ML features in learning tasks based on their similarity. This network representation allows us to view feature vectors as functions on the network. By leveraging function operations from Fourier analysis and from functional analysis, one can easily generate new and novel features, making use of the graph structure imposed on the feature vectors. Such network structures have previously been studied implicitly in image processing and computational biology. We thus describe feature networks as graph structures imposed on feature vectors, and provide applications in machine learning. One application involves graph-based generalizations of convolutional neural networks, involving structured deep learning with hierarchical representations of features that have varying depth or complexity. This extends also to learning algorithms that are able to generate useful new multilevel features. Additionally, we discuss the use of feature networks to engineer new features, which can enhance the expressiveness of the model. We give a specific example of a deep tree-structured feature network, where hierarchical connections are formed through feature clustering and feed-forward learning. This results in low learning complexity and computational efficiency. Unlike "standard" neural features which are limited to modulated (thresholded) linear combinations of adjacent ones, feature networks offer more general feedforward dependencies among features. For example, radial basis functions or graph structure-based dependencies between features can be utilized.
Authors: Sébastien Lachapelle, Pau Rodríguez López, Yash Sharma, Katie Everett, Rémi Le Priol, Alexandre Lacoste, Simon Lacoste-Julien
This work introduces a novel principle for disentanglement we call mechanism sparsity regularization, which applies when the latent factors of interest depend sparsely on observed auxiliary variables and/or past latent factors. We propose a representation learning method that induces disentanglement by simultaneously learning the latent factors and the sparse causal graphical model that explains them. We develop a nonparametric identifiability theory that formalizes this principle and shows that the latent factors can be recovered by regularizing the learned causal graph to be sparse. More precisely, we show identifiablity up to a novel equivalence relation we call "consistency", which allows some latent factors to remain entangled (hence the term partial disentanglement). To describe the structure of this entanglement, we introduce the notions of entanglement graphs and graph preserving functions. We further provide a graphical criterion which guarantees complete disentanglement, that is identifiability up to permutations and element-wise transformations. We demonstrate the scope of the mechanism sparsity principle as well as the assumptions it relies on with several worked out examples. For instance, the framework shows how one can leverage multi-node interventions with unknown targets on the latent factors to disentangle them. We further draw connections between our nonparametric results and the now popular exponential family assumption. Lastly, we propose an estimation procedure based on variational autoencoders and a sparsity constraint and demonstrate it on various synthetic datasets. This work is meant to be a significantly extended version of Lachapelle et al. (2022).
Authors: Mengmeng Zhang, Fan Wu, Yude Bu, Shanshan Li, Zhenping Yi, Meng Liu, Xiaoming Kong
The age and mass of red giants are essential for understanding the structure and evolution of the Milky Way. Traditional isochrone methods for these estimations are inherently limited due to overlapping isochrones in the Hertzsprung-Russell diagram, while asteroseismology, though more precise, requires high-precision, long-term observations. In response to these challenges, we developed a novel framework, Spectral Transformer (SPT), to predict the age and mass of red giants aligned with asteroseismology from their spectra. A key component of SPT, the Multi-head Hadamard Self-Attention mechanism, designed specifically for spectra, can capture complex relationships across different wavelength. Further, we introduced a Mahalanobis distance-based loss function to address scale imbalance and interaction mode loss, and incorporated Monte Carlo dropout for quantitative analysis of prediction uncertainty.Trained and tested on 3,880 red giant spectra from LAMOST, the SPT achieved remarkable age and mass estimations with average percentage errors of 17.64% and 6.61%, respectively, and provided uncertainties for each corresponding prediction. The results significantly outperform those of traditional machine learning algorithms and demonstrate a high level of consistency with asteroseismology methods and isochrone fitting techniques. In the future, our work will leverage datasets from the Chinese Space Station Telescope and the Large Synoptic Survey Telescope to enhance the precision of the model and broaden its applicability in the field of astronomy and astrophysics.
Authors: Ruiyu Mao, Ouyang Xu, Yunhui Guo
Active learning is a commonly used approach that reduces the labeling effort required to train deep neural networks. However, the effectiveness of current active learning methods is limited by their closed-world assumptions, which assume that all data in the unlabeled pool comes from a set of predefined known classes. This assumption is often not valid in practical situations, as there may be unknown classes in the unlabeled data, leading to the active open-set annotation problem. The presence of unknown classes in the data can significantly impact the performance of existing active learning methods due to the uncertainty they introduce. To address this issue, we propose a novel data-centric active learning method called NEAT that actively annotates open-set data. NEAT is designed to label known classes data from a pool of both known and unknown classes unlabeled data. It utilizes the clusterability of labels to identify the known classes from the unlabeled pool and selects informative samples from those classes based on a consistency criterion that measures inconsistencies between model predictions and local feature distribution. Unlike the recently proposed learning-centric method for the same problem, NEAT is much more computationally efficient and is a data-centric active open-set annotation method. Our experiments demonstrate that NEAT achieves significantly better performance than state-of-the-art active learning methods for active open-set annotation.
Authors: Seonguk Seo, Jinkyu Kim, Geeho Kim, Bohyung Han
We propose a novel contrastive learning framework to effectively address the challenges of data heterogeneity in federated learning. We first analyze the inconsistency of gradient updates across clients during local training and establish its dependence on the distribution of feature representations, leading to the derivation of the supervised contrastive learning (SCL) objective to mitigate local deviations. In addition, we show that a na\"ive adoption of SCL in federated learning leads to representation collapse, resulting in slow convergence and limited performance gains. To address this issue, we introduce a relaxed contrastive learning loss that imposes a divergence penalty on excessively similar sample pairs within each class. This strategy prevents collapsed representations and enhances feature transferability, facilitating collaborative training and leading to significant performance improvements. Our framework outperforms all existing federated learning approaches by huge margins on the standard benchmarks through extensive experimental results.
Authors: Haonan Shi, Tu Ouyang, An Wang
Machine learning models, in particular deep neural networks, are currently an integral part of various applications, from healthcare to finance. However, using sensitive data to train these models raises concerns about privacy and security. One method that has emerged to verify if the trained models are privacy-preserving is Membership Inference Attacks (MIA), which allows adversaries to determine whether a specific data point was part of a model's training dataset. While a series of MIAs have been proposed in the literature, only a few can achieve high True Positive Rates (TPR) in the low False Positive Rate (FPR) region (0.01%~1%). This is a crucial factor to consider for an MIA to be practically useful in real-world settings. In this paper, we present a novel approach to MIA that is aimed at significantly improving TPR at low FPRs. Our method, named learning-based difficulty calibration for MIA(LDC-MIA), characterizes data records by their hardness levels using a neural network classifier to determine membership. The experiment results show that LDC-MIA can improve TPR at low FPR by up to 4x compared to the other difficulty calibration based MIAs. It also has the highest Area Under ROC curve (AUC) across all datasets. Our method's cost is comparable with most of the existing MIAs, but is orders of magnitude more efficient than one of the state-of-the-art methods, LiRA, while achieving similar performance.
Authors: Sicong Huang, Jiawei He, Kry Yik Chau Lui
While likelihood is attractive in theory, its estimates by deep generative models (DGMs) are often broken in practice, and perform poorly for out of distribution (OOD) Detection. Various recent works started to consider alternative scores and achieved better performances. However, such recipes do not come with provable guarantees, nor is it clear that their choices extract sufficient information.
We attempt to change this by conducting a case study on variational autoencoders (VAEs). First, we introduce the likelihood path (LPath) principle, generalizing the likelihood principle. This narrows the search for informative summary statistics down to the minimal sufficient statistics of VAEs' conditional likelihoods. Second, introducing new theoretic tools such as nearly essential support, essential distance and co-Lipschitzness, we obtain non-asymptotic provable OOD detection guarantees for certain distillation of the minimal sufficient statistics. The corresponding LPath algorithm demonstrates SOTA performances, even using simple and small VAEs with poor likelihood estimates. To our best knowledge, this is the first provable unsupervised OOD method that delivers excellent empirical results, better than any other VAEs based techniques. We use the same model as \cite{xiao2020likelihood}, open sourced from: https://github.com/XavierXiao/Likelihood-Regret
Authors: Jiechuan Jiang, Kefan Su, Zongqing Lu
Cooperative multi-agent reinforcement learning is a powerful tool to solve many real-world cooperative tasks, but restrictions of real-world applications may require training the agents in a fully decentralized manner. Due to the lack of information about other agents, it is challenging to derive algorithms that can converge to the optimal joint policy in a fully decentralized setting. Thus, this research area has not been thoroughly studied. In this paper, we seek to systematically review the fully decentralized methods in two settings: maximizing a shared reward of all agents and maximizing the sum of individual rewards of all agents, and discuss open questions and future research directions.
Authors: Rumsha Fatima, Shahzad Younis, Faraz Shaikh, Hamna Imran, Haseeb Sultan, Shahzad Rasool, Mehak Rafiq
The reliable diagnosis of cardiac conditions through electrocardiogram (ECG) analysis critically depends on accurately detecting P waves and measuring the PR interval. However, achieving consistent and generalizable diagnoses across diverse populations presents challenges due to the inherent global variations observed in ECG signals. This paper is focused on applying the Q learning reinforcement algorithm to the various ECG datasets available in the PhysioNet/Computing in Cardiology Challenge (CinC). Five ECG beats, including Normal Sinus Rhythm, Atrial Flutter, Atrial Fibrillation, 1st Degree Atrioventricular Block, and Left Atrial Enlargement, are included to study variations of P waves and PR Interval on Lead II and Lead V1. Q-Agent classified 71,672 beat samples in 8,867 patients with an average accuracy of 90.4% and only 9.6% average hamming loss over misclassification. The average classification time at the 100th episode containing around 40,000 samples is 0.04 seconds. An average training reward of 344.05 is achieved at an alpha, gamma, and SoftMax temperature rate of 0.001, 0.9, and 0.1, respectively.
Authors: Hanli Zhang, Anusha Srikanthan, Spencer Folk, Vijay Kumar, Nikolai Matni
Motivated by the increasing use of quadrotors for payload delivery, we consider a joint trajectory generation and feedback control design problem for a quadrotor experiencing aerodynamic wrenches. Unmodeled aerodynamic drag forces from carried payloads can lead to catastrophic outcomes. Prior work model aerodynamic effects as residual dynamics or external disturbances in the control problem leading to a reactive policy that could be catastrophic. Moreover, redesigning controllers and tuning control gains on hardware platforms is a laborious effort. In this paper, we argue that adapting the trajectory generation component keeping the controller fixed can improve trajectory tracking for quadrotor systems experiencing drag forces. To achieve this, we formulate a drag-aware planning problem by applying a suitable relaxation to an optimal quadrotor control problem, introducing a tracking cost function which measures the ability of a controller to follow a reference trajectory. This tracking cost function acts as a regularizer in trajectory generation and is learned from data obtained from simulation. Our experiments in both simulation and on the Crazyflie hardware platform show that changing the planner reduces tracking error by as much as 83%. Evaluation on hardware demonstrates that our planned path, as opposed to a baseline, avoids controller saturation and catastrophic outcomes during aggressive maneuvers.
Authors: Xiran Xu, Bo Wang, Yujie Yan, Haolin Zhu, Zechen Zhang, Xihong Wu, Jing Chen
To investigate the processing of speech in the brain, simple linear models are commonly used to establish a relationship between brain signals and speech features. However, these linear models are ill-equipped to model a highly dynamic and complex non-linear system like the brain. Although non-linear methods with neural networks have been developed recently, reconstructing unseen stimuli from unseen subjects' EEG is still a highly challenging task. This work presents a novel method, ConvConcatNet, to reconstruct mel-specgrams from EEG, in which the deep convolution neural network and extensive concatenation operation were combined. With our ConvConcatNet model, the Pearson correlation between the reconstructed and the target mel-spectrogram can achieve 0.0420, which was ranked as No.1 in the Task 2 of the Auditory EEG Challenge. The codes and models to implement our work will be available on Github: https://github.com/xuxiran/ConvConcatNet
Authors: Sebastian Johann Wetzel
I introduce a unified framework for interpreting neural network classifiers tailored toward automated scientific discovery. In contrast to neural network-based regression, for classification, it is in general impossible to find a one-to-one mapping from the neural network to a symbolic equation even if the neural network itself bases its classification on a quantity that can be written as a closed-form equation. In this paper, I embed a trained neural network into an equivalence class of classifying functions that base their decisions on the same quantity. I interpret neural networks by finding an intersection between this equivalence class and human-readable equations defined by the search space of symbolic regression. The approach is not limited to classifiers or full neural networks and can be applied to arbitrary neurons in hidden layers or latent spaces or to simplify the process of interpreting neural network regressors.
Authors: YongKyung Oh, Dongyoung Lim, Sungil Kim
To handle the complexities of irregular and incomplete time series data, we propose an invertible solution of Neural Differential Equations (NDE)-based method. While NDE-based methods are a powerful method for analyzing irregularly-sampled time series, they typically do not guarantee reversible transformations in their standard form. Our method suggests the variation of Neural Controlled Differential Equations (Neural CDEs) with Neural Flow, which ensures invertibility while maintaining a lower computational burden. Additionally, it enables the training of a dual latent space, enhancing the modeling of dynamic temporal dynamics. Our research presents an advanced framework that excels in both classification and interpolation tasks. At the core of our approach is an enhanced dual latent states architecture, carefully designed for high precision across various time series tasks. Empirical analysis demonstrates that our method significantly outperforms existing models. This work significantly advances irregular time series analysis, introducing innovative techniques and offering a versatile tool for diverse practical applications.
Authors: Haoyu Chu, Yuto Miyatake, Wenjun Cui, Shikui Wei, Daisuke Furihata
Recently, there has been growing interest in using physics-informed neural networks (PINNs) to solve differential equations. However, the preservation of structure, such as energy and stability, in a suitable manner has yet to be established. This limitation could be a potential reason why the learning process for PINNs is not always efficient and the numerical results may suggest nonphysical behavior. Besides, there is little research on their applications on downstream tasks. To address these issues, we propose structure-preserving PINNs to improve their performance and broaden their applications for downstream tasks. Firstly, by leveraging prior knowledge about the physical system, a structure-preserving loss function is designed to assist the PINN in learning the underlying structure. Secondly, a framework that utilizes structure-preserving PINN for robust image recognition is proposed. Here, preserving the Lyapunov structure of the underlying system ensures the stability of the system. Experimental results demonstrate that the proposed method improves the numerical accuracy of PINNs for partial differential equations. Furthermore, the robustness of the model against adversarial perturbations in image data is enhanced.
Authors: Shayan Mohajer Hamidi, En-Hui Yang
Federated learning (FL) is a promising technology via which some edge devices/clients collaboratively train a machine learning model orchestrated by a server. Learning an unfair model is known as a critical problem in federated learning, where the trained model may unfairly advantage or disadvantage some of the devices. To tackle this problem, in this work, we propose AdaFed. The goal of AdaFed is to find an updating direction for the server along which (i) all the clients' loss functions are decreasing; and (ii) more importantly, the loss functions for the clients with larger values decrease with a higher rate. AdaFed adaptively tunes this common direction based on the values of local gradients and loss functions. We validate the effectiveness of AdaFed on a suite of federated datasets, and demonstrate that AdaFed outperforms state-of-the-art fair FL methods.
Authors: Christian Mulomba Mukendi, Hyebong Choi
he evaluation of the impact of actions undertaken is essential in management. This paper assesses the impact of efforts considered to mitigate risk and create safe environments on a global scale. We measure this impact by looking at the probability of improvement over a specific short period of time. Using the World Risk Index, we conduct a temporal analysis of global disaster risk dynamics from 2011 to 2021. This temporal exploration through the lens of the World Risk Index provides insights into the complex dynamics of disaster risk. We found that, despite sustained efforts, the global landscape remains divided into two main clusters: high susceptibility and moderate susceptibility, regardless of geographical location. This clustering was achieved using a semi-supervised approach through the Label Spreading algorithm, with 98% accuracy. We also found that the prediction of clusters achieved through supervised learning on the period considered in this study (one, three, and five years) showed that the Logistic regression (almost 99% at each stage) performed better than other classifiers. This suggests that the current policies and mechanisms are not effective in helping countries move from a hazardous position to a safer one during the period considered. In fact, statistical projections using a scenario analysis indicate that there is only a 1% chance of such a shift occurring within a five-year timeframe. This sobering reality highlights the need for a paradigm shift. Traditional long-term disaster management strategies are not effective for countries that are highly vulnerable. Our findings indicate the need for an innovative approach that is tailored to the specific vulnerabilities of these nations. As the threat of vulnerability persists, our research calls for the development of new strategies that can effectively address the ongoing challenges of disaster risk management
Authors: Shubao Zhao, Ming Jin, Zhaoxiang Hou, Chengyi Yang, Zengxiang Li, Qingsong Wen, Yi Wang
Time series forecasting is crucial and challenging in the real world. The recent surge in interest regarding time series foundation models, which cater to a diverse array of downstream tasks, is noteworthy. However, existing methods often overlook the multi-scale nature of time series, an aspect crucial for precise forecasting. To bridge this gap, we propose HiMTM, a hierarchical multi-scale masked time series modeling method designed for long-term forecasting. Specifically, it comprises four integral components: (1) hierarchical multi-scale transformer (HMT) to capture temporal information at different scales; (2) decoupled encoder-decoder (DED) forces the encoder to focus on feature extraction, while the decoder to focus on pretext tasks; (3) multi-scale masked reconstruction (MMR) provides multi-stage supervision signals for pre-training; (4) cross-scale attention fine-tuning (CSA-FT) to capture dependencies between different scales for forecasting. Collectively, these components enhance multi-scale feature extraction capabilities in masked time series modeling and contribute to improved prediction accuracy. We conduct extensive experiments on 7 mainstream datasets to prove that HiMTM has obvious advantages over contemporary self-supervised and end-to-end learning methods. The effectiveness of HiMTM is further showcased by its application in the industry of natural gas demand forecasting.
Authors: Xiaoyan Hu, Farzan Farnia, Ho-fung Leung
Reinforcement learning (RL) problems where the learner attempts to infer an unobserved reward from some feedback variables have been studied in several recent papers. The setting of Interaction-Grounded Learning (IGL) is an example of such feedback-based reinforcement learning tasks where the learner optimizes the return by inferring latent binary rewards from the interaction with the environment. In the IGL setting, a relevant assumption used in the RL literature is that the feedback variable $Y$ is conditionally independent of the context-action $(X,A)$ given the latent reward $R$. In this work, we propose Variational Information-based IGL (VI-IGL) as an information-theoretic method to enforce the conditional independence assumption in the IGL-based RL problem. The VI-IGL framework learns a reward decoder using an information-based objective based on the conditional mutual information (MI) between the context-action $(X,A)$ and the feedback variable $Y$ observed from the environment. To estimate and optimize the information-based terms for the continuous random variables in the RL problem, VI-IGL leverages the variational representation of mutual information and results in a min-max optimization problem. Furthermore, we extend the VI-IGL framework to general $f$-Information measures in the information theory literature, leading to the generalized $f$-VI-IGL framework to address the RL problem under the IGL condition. Finally, we provide the empirical results of applying the VI-IGL method to several reinforcement learning settings, which indicate an improved performance in comparison to the previous IGL-based RL algorithm.
Authors: Gabriele Iommazzo, Claudia D'Ambrosio, Antonio Frangioni, Leo Liberti
We discuss the issue of finding a good mathematical programming solver configuration for a particular instance of a given problem, and we propose a two-phase approach to solve it. In the first phase we learn the relationships between the instance, the configuration and the performance of the configured solver on the given instance. A specific difficulty of learning a good solver configuration is that parameter settings may not all be independent; this requires enforcing (hard) constraints, something that many widely used supervised learning methods cannot natively achieve. We tackle this issue in the second phase of our approach, where we use the learnt information to construct and solve an optimization problem having an explicit representation of the dependency/consistency constraints on the configuration parameter settings. We discuss computational results for two different instantiations of this approach on a unit commitment problem arising in the short-term planning of hydro valleys. We use logistic regression as the supervised learning methodology and consider CPLEX as the solver of interest.
Authors: Kaizheng Wang, Keivan Shariatmadar, Shireen Kudukkil Manchingal, Fabio Cuzzolin, David Moens, Hans Hallez
Uncertainty estimation is increasingly attractive for improving the reliability of neural networks. In this work, we present novel credal-set interval neural networks (CreINNs) designed for classification tasks. CreINNs preserve the traditional interval neural network structure, capturing weight uncertainty through deterministic intervals, while forecasting credal sets using the mathematical framework of probability intervals. Experimental validations on an out-of-distribution detection benchmark (CIFAR10 vs SVHN) showcase that CreINNs outperform epistemic uncertainty estimation when compared to variational Bayesian neural networks (BNNs) and deep ensembles (DEs). Furthermore, CreINNs exhibit a notable reduction in computational complexity compared to variational BNNs and demonstrate smaller model sizes than DEs.
Authors: Tom Richard Vargis, Siavash Ghiasvand
This work prioritizes building a modular pipeline that utilizes existing models to systematically restore images, rather than creating new restoration models from scratch. Restoration is carried out at an object-specific level, with each object regenerated using its corresponding class label information. The approach stands out by providing complete user control over the entire restoration process. Users can select models for specialized restoration steps, customize the sequence of steps to meet their needs, and refine the resulting regenerated image with depth awareness. The research provides two distinct pathways for implementing image regeneration, allowing for a comparison of their respective strengths and limitations. The most compelling aspect of this versatile system is its adaptability. This adaptability enables users to target particular object categories, including medical images, by providing models that are trained on those object classes.
Authors: Bernardo Torres, Stefan Lattner, Gaël Richard
Significant strides have been made in creating voice identity representations using speech data. However, the same level of progress has not been achieved for singing voices. To bridge this gap, we suggest a framework for training singer identity encoders to extract representations suitable for various singing-related tasks, such as singing voice similarity and synthesis. We explore different self-supervised learning techniques on a large collection of isolated vocal tracks and apply data augmentations during training to ensure that the representations are invariant to pitch and content variations. We evaluate the quality of the resulting representations on singer similarity and identification tasks across multiple datasets, with a particular emphasis on out-of-domain generalization. Our proposed framework produces high-quality embeddings that outperform both speaker verification and wav2vec 2.0 pre-trained baselines on singing voice while operating at 44.1 kHz. We release our code and trained models to facilitate further research on singing voice and related areas.
Authors: Michal K. Grzeszczyk, Tomasz Trzciński, Arkadiusz Sitek
In this work, we present a novel, machine-learning approach for constructing Multiclass Interpretable Scoring Systems (MISS) - a fully data-driven methodology for generating single, sparse, and user-friendly scoring systems for multiclass classification problems. Scoring systems are commonly utilized as decision support models in healthcare, criminal justice, and other domains where interpretability of predictions and ease of use are crucial. Prior methods for data-driven scoring, such as SLIM (Supersparse Linear Integer Model), were limited to binary classification tasks and extensions to multiclass domains were primarily accomplished via one-versus-all-type techniques. The scores produced by our method can be easily transformed into class probabilities via the softmax function. We demonstrate techniques for dimensionality reduction and heuristics that enhance the training efficiency and decrease the optimality gap, a measure that can certify the optimality of the model. Our approach has been extensively evaluated on datasets from various domains, and the results indicate that it is competitive with other machine learning models in terms of classification performance metrics and provides well-calibrated class probabilities.
Authors: Florin Leon, Marius Gavrilescu, Sabina-Adriana Floria, Alina-Adriana Minea
This paper proposes a classification framework aimed at identifying correlations between job ad requirements and transversal skill sets, with a focus on predicting the necessary skills for individual job descriptions using a deep learning model. The approach involves data collection, preprocessing, and labeling using ESCO (European Skills, Competences, and Occupations) taxonomy. Hierarchical classification and multi-label strategies are used for skill identification, while augmentation techniques address data imbalance, enhancing model robustness. A comparison between results obtained with English-specific and multi-language sentence embedding models reveals close accuracy. The experimental case studies detail neural network configurations, hyperparameters, and cross-validation results, highlighting the efficacy of the hierarchical approach and the suitability of the multi-language model for the diverse European job market. Thus, a new approach is proposed for the hierarchical classification of transversal skills from job ads.
Authors: Junhoo Lee, Yearim Kim, Hyunho Lee, Nojun Kwak
Although meta-learning seems promising performance in the realm of rapid adaptability, it is constrained by fixed cardinality. When faced with tasks of varying cardinalities that were unseen during training, the model lacks its ability. In this paper, we address and resolve this challenge by harnessing `label equivalence' emerged from stochastic numeric label assignments during episodic task sampling. Questioning what defines ``true" meta-learning, we introduce the ``any-way" learning paradigm, an innovative model training approach that liberates model from fixed cardinality constraints. Surprisingly, this model not only matches but often outperforms traditional fixed-way models in terms of performance, convergence speed, and stability. This disrupts established notions about domain generalization. Furthermore, we argue that the inherent label equivalence naturally lacks semantic information. To bridge this semantic information gap arising from label equivalence, we further propose a mechanism for infusing semantic class information into the model. This would enhance the model's comprehension and functionality. Experiments conducted on renowned architectures like MAML and ProtoNet affirm the effectiveness of our method.
Authors: Kenichi Fujita, Hiroshi Sato, Takanori Ashihara, Hiroki Kanagawa, Marc Delcroix, Takafumi Moriya, Yusuke Ijima
The zero-shot text-to-speech (TTS) method, based on speaker embeddings extracted from reference speech using self-supervised learning (SSL) speech representations, can reproduce speaker characteristics very accurately. However, this approach suffers from degradation in speech synthesis quality when the reference speech contains noise. In this paper, we propose a noise-robust zero-shot TTS method. We incorporated adapters into the SSL model, which we fine-tuned with the TTS model using noisy reference speech. In addition, to further improve performance, we adopted a speech enhancement (SE) front-end. With these improvements, our proposed SSL-based zero-shot TTS achieved high-quality speech synthesis with noisy reference speech. Through the objective and subjective evaluations, we confirmed that the proposed method is highly robust to noise in reference speech, and effectively works in combination with SE.
Authors: Farbin Fayza, Satyavolu Papa Rao, Darius Bunandar, Udit Gupta, Ajay Joshi
Photonic integrated circuits are finding use in a variety of applications including optical transceivers, LIDAR, bio-sensing, photonic quantum computing, and Machine Learning (ML). In particular, with the exponentially increasing sizes of ML models, photonics-based accelerators are getting special attention as a sustainable solution because they can perform ML inferences with multiple orders of magnitude higher energy efficiency than CMOS-based accelerators. However, recent studies have shown that hardware manufacturing and infrastructure contribute significantly to the carbon footprint of computing devices, even surpassing the emissions generated during their use. For example, the manufacturing process accounts for 74% of the total carbon emissions from Apple in 2019. This prompts us to ask -- if we consider both the embodied (manufacturing) and operational carbon cost of photonics, is it indeed a viable avenue for a sustainable future? So, in this paper, we build a carbon footprint model for photonic chips and investigate the sustainability of photonics-based accelerators by conducting a case study on ADEPT, a photonics-based accelerator for deep neural network inference. Our analysis shows that photonics can reduce both operational and embodied carbon footprints with its high energy efficiency and at least 4$\times$ less fabrication carbon cost per unit area than 28 nm CMOS.
Authors: Teru Nagamori, Sayaka Shiota, Hitoshi Kiya
We propose a novel method for privacy-preserving deep neural networks (DNNs) with the Vision Transformer (ViT). The method allows us not only to train models and test with visually protected images but to also avoid the performance degradation caused from the use of encrypted images, whereas conventional methods cannot avoid the influence of image encryption. A domain adaptation method is used to efficiently fine-tune ViT with encrypted images. In experiments, the method is demonstrated to outperform conventional methods in an image classification task on the CIFAR-10 and ImageNet datasets in terms of classification accuracy.
Authors: Matilda Beinat, Julian Beinat, Mohammed Shoaib, Jorge Gomez Magenti
Projected to impact 1.6 million people in the UK by 2040 and costing {\pounds}25 billion annually, dementia presents a growing challenge to society. This study, a pioneering effort to predict the translational potential of dementia research using machine learning, hopes to address the slow translation of fundamental discoveries into practical applications despite dementia's significant societal and economic impact. We used the Dimensions database to extract data from 43,091 UK dementia research publications between the years 1990-2023, specifically metadata (authors, publication year etc.), concepts mentioned in the paper, and the paper abstract. To prepare the data for machine learning we applied methods such as one hot encoding and/or word embeddings. We trained a CatBoost Classifier to predict if a publication will be cited in a future patent or clinical trial. We trained several model variations. The model combining metadata, concept, and abstract embeddings yielded the highest performance: for patent predictions, an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.84 and 77.17% accuracy; for clinical trial predictions, an AUROC of 0.81 and 75.11% accuracy. The results demonstrate that integrating machine learning within current research methodologies can uncover overlooked publications, expediting the identification of promising research and potentially transforming dementia research by predicting real-world impact and guiding translational strategies.
Authors: Nicolò Romandini, Alessio Mora, Carlo Mazzocca, Rebecca Montanari, Paolo Bellavista
Federated Learning (FL) enables collaborative training of a Machine Learning (ML) model across multiple parties, facilitating the preservation of users' and institutions' privacy by keeping data stored locally. Instead of centralizing raw data, FL exchanges locally refined model parameters to build a global model incrementally. While FL is more compliant with emerging regulations such as the European General Data Protection Regulation (GDPR), ensuring the right to be forgotten in this context - allowing FL participants to remove their data contributions from the learned model - remains unclear. In addition, it is recognized that malicious clients may inject backdoors into the global model through updates, e.g. to generate mispredictions on specially crafted data examples. Consequently, there is the need for mechanisms that can guarantee individuals the possibility to remove their data and erase malicious contributions even after aggregation, without compromising the already acquired "good" knowledge. This highlights the necessity for novel Federated Unlearning (FU) algorithms, which can efficiently remove specific clients' contributions without full model retraining. This survey provides background concepts, empirical evidence, and practical guidelines to design/implement efficient FU schemes. Our study includes a detailed analysis of the metrics for evaluating unlearning in FL and presents an in-depth literature review categorizing state-of-the-art FU contributions under a novel taxonomy. Finally, we outline the most relevant and still open technical challenges, by identifying the most promising research directions in the field.
Authors: Aldo Pacchiano, Jonathan N. Lee, Emma Brunskill
We study the problem of experiment planning with function approximation in contextual bandit problems. In settings where there is a significant overhead to deploying adaptive algorithms -- for example, when the execution of the data collection policies is required to be distributed, or a human in the loop is needed to implement these policies -- producing in advance a set of policies for data collection is paramount. We study the setting where a large dataset of contexts but not rewards is available and may be used by the learner to design an effective data collection strategy. Although when rewards are linear this problem has been well studied, results are still missing for more complex reward models. In this work we propose two experiment planning strategies compatible with function approximation. The first is an eluder planning and sampling procedure that can recover optimality guarantees depending on the eluder dimension of the reward function class. For the second, we show that a uniform sampler achieves competitive optimality rates in the setting where the number of actions is small. We finalize our results introducing a statistical gap fleshing out the fundamental differences between planning and adaptive learning and provide results for planning with model selection.
Authors: Even Marius Nordhagen, Henrik Andersen Sveinsson, Anders Malthe-Sørenssen
This Letter introduces an approach for precisely designing surface friction properties using a conditional generative machine learning model, specifically a diffusion denoising probabilistic model (DDPM). We created a dataset of synthetic surfaces with frictional properties determined by molecular dynamics simulations, which trained the DDPM to predict surface structures from desired frictional outcomes. Unlike traditional trial-and-error and numerical optimization methods, our approach directly yields surface designs meeting specified frictional criteria with high accuracy and efficiency. This advancement in material surface engineering demonstrates the potential of machine learning in reducing the iterative nature of surface design processes. Our findings not only provide a new pathway for precise surface property tailoring but also suggest broader applications in material science where surface characteristics are critical.
Authors: Jochen Stiasny, Spyros Chatzivasileiadis
The ability to accurately approximate trajectories of dynamical systems enables their analysis, prediction, and control. Neural network (NN)-based approximations have attracted significant interest due to fast evaluation with good accuracy over long integration time steps. In contrast to established numerical approximation schemes such as Runge-Kutta methods, the estimation of the error of the NN-based approximations proves to be difficult. In this work, we propose to use the NN's predictions in a high-order implicit Runge-Kutta (IRK) method. The residuals in the implicit system of equations can be related to the NN's prediction error, hence, we can provide an error estimate at several points along a trajectory. We find that this error estimate highly correlates with the NN's prediction error and that increasing the order of the IRK method improves this estimate. We demonstrate this estimation methodology for Physics-Informed Neural Network (PINNs) on the logistic equation as an illustrative example and then apply it to a four-state electric generator model that is regularly used in power system modelling.
Authors: Alexander Mey, Rui Manuel Castro
We consider the task of identifying the causal parents of a target variable among a set of candidate variables from observational data. Our main assumption is that the candidate variables are observed in different environments which may, for example, correspond to different settings of a machine or different time intervals in a dynamical process. Under certain assumptions different environments can be regarded as interventions on the observed system. We assume a linear relationship between target and covariates, which can be different in each environment with the only restriction that the causal structure is invariant across environments. This is an extension of the ICP ($\textbf{I}$nvariant $\textbf{C}$ausal $\textbf{P}$rediction) principle by Peters et al. [2016], who assumed a fixed linear relationship across all environments. Within our proposed setting we provide sufficient conditions for identifiability of the causal parents and introduce a practical method called LoLICaP ($\textbf{Lo}$cally $\textbf{L}$inear $\textbf{I}$nvariant $\textbf{Ca}$usal $\textbf{P}$rediction), which is based on a hypothesis test for parent identification using a ratio of minimum and maximum statistics. We then show in a simplified setting that the statistical power of LoLICaP converges exponentially fast in the sample size, and finally we analyze the behavior of LoLICaP experimentally in more general settings.
Authors: Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Mohamed El Amine Seddik, Karttikeya Mangalam, Noel E. O'Connor
Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an alignment exist between uni-modal vision and language encoders since they fundamentally represent the same physical world? Analyzing the latent spaces structure of vision and language models on image-caption benchmarks using the Centered Kernel Alignment (CKA), we find that the representation spaces of unaligned and aligned encoders are semantically similar. In the absence of statistical similarity in aligned encoders like CLIP, we show that a possible matching of unaligned encoders exists without any training. We frame this as a seeded graph-matching problem exploiting the semantic similarity between graphs and propose two methods - a Fast Quadratic Assignment Problem optimization, and a novel localized CKA metric-based matching/retrieval. We demonstrate the effectiveness of this on several downstream tasks including cross-lingual, cross-domain caption matching and image classification.
Authors: Giulio Barletta, Giovanni Trezza, Eliodoro Chiavazzo
We assume that a sufficiently large database is available, where a physical property of interest and a number of associated ruling primitive variables or observables are stored. We introduce and test two machine learning approaches to discover possible groups or combinations of primitive variables: The first approach is based on regression models whereas the second on classification models. The variable group (here referred to as the new effective good variable) can be considered as successfully found, when the physical property of interest is characterized by the following effective invariant behaviour: In the first method, invariance of the group implies invariance of the property up to a given accuracy; in the other method, upon partition of the physical property values into two or more classes, invariance of the group implies invariance of the class. For the sake of illustration, the two methods are successfully applied to two popular empirical correlations describing the convective heat transfer phenomenon and to the Newton's law of universal gravitation.
Authors: Yaqi Duan, Martin J. Wainwright
We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both off-line and on-line settings. Our analysis highlights two key stability properties, relating to how changes in value functions and/or policies affect the Bellman operator and occupation measures. We argue that these properties are satisfied in many continuous state-action Markov decision processes, and demonstrate how they arise naturally when using linear function approximation methods. Our analysis offers fresh perspectives on the roles of pessimism and optimism in off-line and on-line RL, and highlights the connection between off-line RL and transfer learning.
Authors: Emanuele Luzio, Moacir Antonelli Ponti, Christian Ramirez Arevalo, Luis Argerich
Machine learning models typically focus on specific targets like creating classifiers, often based on known population feature distributions in a business context. However, models calculating individual features adapt over time to improve precision, introducing the concept of decoupling: shifting from point evaluation to data distribution. We use calibration strategies as strategy for decoupling machine learning (ML) classifiers from score-based actions within business logic frameworks. To evaluate these strategies, we perform a comparative analysis using a real-world business scenario and multiple ML models. Our findings highlight the trade-offs and performance implications of the approach, offering valuable insights for practitioners seeking to optimize their decoupling efforts. In particular, the Isotonic and Beta calibration methods stand out for scenarios in which there is shift between training and testing data.
Authors: Denny Thaler, Somayajulu L. N. Dhulipala, Franz Bamer, Bernd Markert, Michael D. Shields
We present a new Subset Simulation approach using Hamiltonian neural network-based Monte Carlo sampling for reliability analysis. The proposed strategy combines the superior sampling of the Hamiltonian Monte Carlo method with computationally efficient gradient evaluations using Hamiltonian neural networks. This combination is especially advantageous because the neural network architecture conserves the Hamiltonian, which defines the acceptance criteria of the Hamiltonian Monte Carlo sampler. Hence, this strategy achieves high acceptance rates at low computational cost. Our approach estimates small failure probabilities using Subset Simulations. However, in low-probability sample regions, the gradient evaluation is particularly challenging. The remarkable accuracy of the proposed strategy is demonstrated on different reliability problems, and its efficiency is compared to the traditional Hamiltonian Monte Carlo method. We note that this approach can reach its limitations for gradient estimations in low-probability regions of complex and high-dimensional distributions. Thus, we propose techniques to improve gradient prediction in these particular situations and enable accurate estimations of the probability of failure. The highlight of this study is the reliability analysis of a system whose parameter distributions must be inferred with Bayesian inference problems. In such a case, the Hamiltonian Monte Carlo method requires a full model evaluation for each gradient evaluation and, therefore, comes at a very high cost. However, using Hamiltonian neural networks in this framework replaces the expensive model evaluation, resulting in tremendous improvements in computational efficiency.
Authors: Thomas Rudolf, Daniel Flögel, Tobias Schürmann, Simon Süß, Stefan Schwab, Sören Hohmann
Robust and performant controllers are essential for industrial applications. However, deriving controller parameters for complex and nonlinear systems is challenging and time-consuming. To facilitate automatic controller parametrization, this work presents a novel approach using deep reinforcement learning (DRL) with N-dimensional B-spline geometries (BSGs). We focus on the control of parameter-variant systems, a class of systems with complex behavior which depends on the operating conditions. For this system class, gain-scheduling control structures are widely used in applications across industries due to well-known design principles. Facilitating the expensive controller parametrization task regarding these control structures, we deploy an DRL agent. Based on control system observations, the agent autonomously decides how to adapt the controller parameters. We make the adaptation process more efficient by introducing BSGs to map the controller parameters which may depend on numerous operating conditions. To preprocess time-series data and extract a fixed-length feature vector, we use a long short-term memory (LSTM) neural networks. Furthermore, this work contributes actor regularizations that are relevant to real-world environments which differ from training. Accordingly, we apply dropout layer normalization to the actor and critic networks of the truncated quantile critic (TQC) algorithm. To show our approach's working principle and effectiveness, we train and evaluate the DRL agent on the parametrization task of an industrial control structure with parameter lookup tables.
Authors: Shuofei Qiao, Ningyu Zhang, Runnan Fang, Yujie Luo, Wangchunshu Zhou, Yuchen Eleanor Jiang, Chengfei Lv, Huajun Chen
Language agents have achieved considerable performance on various complex tasks. Despite the incessant exploration in this field, existing language agent systems still struggle with costly, non-reproducible data reliance and face the challenge of compelling a single model for multiple functions. To this end, we introduce AutoAct, an automatic agent learning framework that does not rely on large-scale annotated data and synthetic trajectories from closed-source models (e.g., GPT-4). Given limited data with a tool library, AutoAct first automatically synthesizes planning trajectories without any assistance from humans or strong closed-source models. Then, AutoAct leverages a division-of-labor strategy to automatically differentiate based on the target task information and synthesized trajectories, producing a sub-agent group to complete the task. We conduct comprehensive experiments with different LLMs, which demonstrates that AutoAct yields better or parallel performance compared to various strong baselines. We even notice that AutoAct, when using the Llama-2-13b model, can achieve performance comparable to that of the GPT-3.5-Turbo agent. Code will be available at https://github.com/zjunlp/AutoAct.
Authors: Alberto Regadío, Luis Esteban, Sebastián Sánchez-Prieto
To address the possible lack or total absence of pulses from particle detectors during the development of its associate electronics, we propose a model that can generate them without losing the features of the real ones. This model is based on artificial neural networks, namely Generative Adversarial Networks (GAN). We describe the proposed network architecture, its training methodology and the approach to train the GAN with real pulses from a scintillator receiving radiation from sources of ${}^{137}$Cs and ${}^{22}$Na. The Generator was installed in a Xilinx's System-On-Chip (SoC). We show how the network is capable of generating pulses with the same shape as the real ones that even match the data distributions in the original pulse-height histogram data.
Authors: Jessica Dai, Bailey Flanigan, Nika Haghtalab, Meena Jagadeesan, Chara Podimata
A common explanation for negative user impacts of content recommender systems is misalignment between the platform's objective and user welfare. In this work, we show that misalignment in the platform's objective is not the only potential cause of unintended impacts on users: even when the platform's objective is fully aligned with user welfare, the platform's learning algorithm can induce negative downstream impacts on users. The source of these user impacts is that different pieces of content may generate observable user reactions (feedback information) at different rates; these feedback rates may correlate with content properties, such as controversiality or demographic similarity of the creator, that affect the user experience. Since differences in feedback rates can impact how often the learning algorithm engages with different content, the learning algorithm may inadvertently promote content with certain such properties. Using the multi-armed bandit framework with probabilistic feedback, we examine the relationship between feedback rates and a learning algorithm's engagement with individual arms for different no-regret algorithms. We prove that no-regret algorithms can exhibit a wide range of dependencies: if the feedback rate of an arm increases, some no-regret algorithms engage with the arm more, some no-regret algorithms engage with the arm less, and other no-regret algorithms engage with the arm approximately the same number of times. From a platform design perspective, our results highlight the importance of looking beyond regret when measuring an algorithm's performance, and assessing the nature of a learning algorithm's engagement with different types of content as well as their resulting downstream impacts.
Authors: Amin Farajzadeh, Animesh Yadav, Halim Yanikomeroglu
The deployment of federated learning (FL) within vertical heterogeneous networks, such as those enabled by high-altitude platform station (HAPS), offers the opportunity to engage a wide array of clients, each endowed with distinct communication and computational capabilities. This diversity not only enhances the training accuracy of FL models but also hastens their convergence. Yet, applying FL in these expansive networks presents notable challenges, particularly the significant non-IIDness in client data distributions. Such data heterogeneity often results in slower convergence rates and reduced effectiveness in model training performance. Our study introduces a client selection strategy tailored to address this issue, leveraging user network traffic behaviour. This strategy involves the prediction and classification of clients based on their network usage patterns while prioritizing user privacy. By strategically selecting clients whose data exhibit similar patterns for participation in FL training, our approach fosters a more uniform and representative data distribution across the network. Our simulations demonstrate that this targeted client selection methodology significantly reduces the training loss of FL models in HAPS networks, thereby effectively tackling a crucial challenge in implementing large-scale FL systems.
Authors: Carolin Schmidt, Mathias Tygesen, Filipe Rodrigues
Urban mobility is on the cusp of transformation with the emergence of shared, connected, and cooperative automated vehicles. Yet, for them to be accepted by customers, trust in their punctuality is vital. Many pilot initiatives operate without a fixed schedule, thus enhancing the importance of reliable arrival time (AT) predictions. This study presents an AT prediction system for autonomous shuttles, utilizing separate models for dwell and running time predictions, validated on real-world data from five cities. Alongside established methods such as XGBoost, we explore the benefits of integrating spatial data using graph neural networks (GNN). To accurately handle the case of a shuttle bypassing a stop, we propose a hierarchical model combining a random forest classifier and a GNN. The results for the final AT prediction are promising, showing low errors even when predicting several stops ahead. Yet, no single model emerges as universally superior, and we provide insights into the characteristics of pilot sites that influence the model selection process. Finally, we identify dwell time prediction as the key determinant in overall AT prediction accuracy when autonomous shuttles are deployed in low-traffic areas or under regulatory speed limits. This research provides insights into the current state of autonomous public transport prediction models and paves the way for more data-informed decision-making as the field advances.
Authors: Mohamad Shahbazi, Liesbeth Claessens, Michael Niemeyer, Edo Collins, Alessio Tonioni, Luc Van Gool, Federico Tombari
We introduce InseRF, a novel method for generative object insertion in the NeRF reconstructions of 3D scenes. Based on a user-provided textual description and a 2D bounding box in a reference viewpoint, InseRF generates new objects in 3D scenes. Recently, methods for 3D scene editing have been profoundly transformed, owing to the use of strong priors of text-to-image diffusion models in 3D generative modeling. Existing methods are mostly effective in editing 3D scenes via style and appearance changes or removing existing objects. Generating new objects, however, remains a challenge for such methods, which we address in this study. Specifically, we propose grounding the 3D object insertion to a 2D object insertion in a reference view of the scene. The 2D edit is then lifted to 3D using a single-view object reconstruction method. The reconstructed object is then inserted into the scene, guided by the priors of monocular depth estimation methods. We evaluate our method on various 3D scenes and provide an in-depth analysis of the proposed components. Our experiments with generative insertion of objects in several 3D scenes indicate the effectiveness of our method compared to the existing methods. InseRF is capable of controllable and 3D-consistent object insertion without requiring explicit 3D information as input. Please visit our project page at https://mohamad-shahbazi.github.io/inserf.
Authors: Morteza Haghir Chehreghani, Mostafa Haghir Chehreghani
We propose a hierarchical correlation clustering method that extends the well-known correlation clustering to produce hierarchical clusters applicable to both positive and negative pairwise dissimilarities. Then, in the following, we study unsupervised representation learning with such hierarchical correlation clustering. For this purpose, we first investigate embedding the respective hierarchy to be used for tree-preserving embedding and feature extraction. Thereafter, we study the extension of minimax distance measures to correlation clustering, as another representation learning paradigm. Finally, we demonstrate the performance of our methods on several datasets.
Authors: Damir Filipovic, Michael Multerer, Paul Schneider
We develop a new framework for embedding joint probability distributions in tensor product reproducing kernel Hilbert spaces (RKHS). Our framework accommodates a low-dimensional, normalized and positive model of a Radon-Nikodym derivative, which we estimate from sample sizes of up to several million data points, alleviating the inherent limitations of RKHS modeling. Well-defined normalized and positive conditional distributions are natural by-products to our approach. The embedding is fast to compute and accommodates learning problems ranging from prediction to classification. Our theoretical findings are supplemented by favorable numerical results.
Authors: Ziang Li, Yiwen Guo, Haodi Liu, Changshui Zhang
Backpropagation (BP) is widely used for calculating gradients in deep neural networks (DNNs). Applied often along with stochastic gradient descent (SGD) or its variants, BP is considered as a de-facto choice in a variety of machine learning tasks including DNN training and adversarial attack/defense. Recently, a linear variant of BP named LinBP was introduced for generating more transferable adversarial examples for performing black-box attacks, by Guo et al. Although it has been shown empirically effective in black-box attacks, theoretical studies and convergence analyses of such a method is lacking. This paper serves as a complement and somewhat an extension to Guo et al.'s paper, by providing theoretical analyses on LinBP in neural-network-involved learning tasks, including adversarial attack and model training. We demonstrate that, somewhat surprisingly, LinBP can lead to faster convergence in these tasks in the same hyper-parameter settings, compared to BP. We confirm our theoretical results with extensive experiments.
Authors: Ruichen Jiang, Aryan Mokhtari
The optimistic gradient method has seen increasing popularity for solving convex-concave saddle point problems. To analyze its iteration complexity, a recent work [arXiv:1906.01115] proposed an interesting perspective that interprets this method as an approximation to the proximal point method. In this paper, we follow this approach and distill the underlying idea of optimism to propose a generalized optimistic method, which includes the optimistic gradient method as a special case. Our general framework can handle constrained saddle point problems with composite objective functions and can work with arbitrary norms using Bregman distances. Moreover, we develop a backtracking line search scheme to select the step sizes without knowledge of the smoothness coefficients. We instantiate our method with first-, second- and higher-order oracles and give best-known global iteration complexity bounds. For our first-order method, we show that the averaged iterates converge at a rate of $O(1/N)$ when the objective function is convex-concave, and it achieves linear convergence when the objective is strongly-convex-strongly-concave. For our second- and higher-order methods, under the additional assumption that the distance-generating function has Lipschitz gradient, we prove a complexity bound of $O(1/\epsilon^\frac{2}{p+1})$ in the convex-concave setting and a complexity bound of $O((L_pD^\frac{p-1}{2}/\mu)^\frac{2}{p+1}+\log\log\frac{1}{\epsilon})$ in the strongly-convex-strongly-concave setting, where $L_p$ ($p\geq 2$) is the Lipschitz constant of the $p$-th-order derivative, $\mu$ is the strong convexity parameter, and $D$ is the initial Bregman distance to the saddle point. Moreover, our line search scheme provably only requires a constant number of calls to a subproblem solver per iteration on average, making our first- and second-order methods particularly amenable to implementation.
Authors: Luca Ballotta, Giovanni Peserico, Francesco Zanini
In this paper, we consider a wireless network of smart sensors (agents) that monitor a dynamical process and send measurements to a base station that performs global monitoring and decision-making. Smart sensors are equipped with both sensing and computation, and can either send raw measurements or process them prior to transmission. Constrained agent resources raise a fundamental latency-accuracy trade-off. On the one hand, raw measurements are inaccurate but fast to produce. On the other hand, data processing on resource-constrained platforms generates accurate measurements at the cost of non-negligible computation latency. Further, if processed data are also compressed, latency caused by wireless communication might be higher for raw measurements. Hence, it is challenging to decide when and where sensors in the network should transmit raw measurements or leverage time-consuming local processing. To tackle this design problem, we propose a Reinforcement Learning approach to learn an efficient policy that dynamically decides when measurements are to be processed at each sensor. Effectiveness of our proposed approach is validated through a numerical simulation with case study on smart sensing motivated by the Internet of Drones.
Authors: Manu Joseph, Harsh Raj
We propose a novel high-performance, interpretable, and parameter \& computationally efficient deep learning architecture for tabular data, Gated Adaptive Network for Deep Automated Learning of Features (GANDALF). GANDALF relies on a new tabular processing unit with a gating mechanism and in-built feature selection called Gated Feature Learning Unit (GFLU) as a feature representation learning unit. We demonstrate that GANDALF outperforms or stays at-par with SOTA approaches like XGBoost, SAINT, FT-Transformers, etc. by experiments on multiple established public benchmarks. We have made available the code at github.com/manujosephv/pytorch_tabular under MIT License.
Authors: Juliane Braunsmann, Marko Rajković, Martin Rumpf, Benedikt Wirth
Autoencoders, which consist of an encoder and a decoder, are widely used in machine learning for dimension reduction of high-dimensional data. The encoder embeds the input data manifold into a lower-dimensional latent space, while the decoder represents the inverse map, providing a parametrization of the data manifold by the manifold in latent space. A good regularity and structure of the embedded manifold may substantially simplify further data processing tasks such as cluster analysis or data interpolation. We propose and analyze a novel regularization for learning the encoder component of an autoencoder: a loss functional that prefers isometric, extrinsically flat embeddings and allows to train the encoder on its own. To perform the training it is assumed that for pairs of nearby points on the input manifold their local Riemannian distance and their local Riemannian average can be evaluated. The loss functional is computed via Monte Carlo integration with different sampling strategies for pairs of points on the input manifold. Our main theorem identifies a geometric loss functional of the embedding map as the $\Gamma$-limit of the sampling-dependent loss functionals. Numerical tests, using image data that encodes different explicitly given data manifolds, show that smooth manifold embeddings into latent space are obtained. Due to the promotion of extrinsic flatness, these embeddings are regular enough such that interpolation between not too distant points on the manifold is well approximated by linear interpolation in latent space as one possible postprocessing.
Authors: Juan-Ni Wu, Tong Wang, Yue Chen, Li-Juan Tang, Hai-Long Wu, Ru-Qin Yu
Effective representation of molecules is a crucial factor affecting the performance of artificial intelligence models. This study introduces a flexible, fragment-based, multiscale molecular representation framework called t-SMILES (tree-based SMILES) with three code algorithms: TSSA (t-SMILES with Shared Atom), TSDY (t-SMILES with Dummy Atom) and TSID (t-SMILES with ID). It describes molecules using SMILES-type strings obtained by performing a breadth-first search on a full binary tree formed from a fragmented molecular graph. Systematic evaluations using JTVAE, BRICS, MMPA, and Scaffold show the feasibility to construct a multi-code molecular description system, where various descriptions complement each other, enhancing the overall performance. Additionally, it exhibits impressive performance on low-resource datasets, whether the model is original, data augmented, or pre-training fine-tuned. It significantly outperforms classical SMILES, DeepSMILES, SELFIES and baseline models in goal-directed tasks. Furthermore, it surpasses start-of-the-art fragment, graph and SMILES based approaches on ChEMBL, Zinc, and QM9.
Authors: Matko Bošnjak, Pierre H. Richemond, Nenad Tomasev, Florian Strub, Jacob C. Walker, Felix Hill, Lars Holger Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic
Learning from large amounts of unsupervised data and a small amount of supervision is an important open problem in computer vision. We propose a new semi-supervised learning method, Semantic Positives via Pseudo-Labels (SemPPL), that combines labelled and unlabelled data to learn informative representations. Our method extends self-supervised contrastive learning -- where representations are shaped by distinguishing whether two samples represent the same underlying datum (positives) or not (negatives) -- with a novel approach to selecting positives. To enrich the set of positives, we leverage the few existing ground-truth labels to predict the missing ones through a $k$-nearest neighbours classifier by using the learned embeddings of the labelled data. We thus extend the set of positives with datapoints having the same pseudo-label and call these semantic positives. We jointly learn the representation and predict bootstrapped pseudo-labels. This creates a reinforcing cycle. Strong initial representations enable better pseudo-label predictions which then improve the selection of semantic positives and lead to even better representations. SemPPL outperforms competing semi-supervised methods setting new state-of-the-art performance of $68.5\%$ and $76\%$ top-$1$ accuracy when using a ResNet-$50$ and training on $1\%$ and $10\%$ of labels on ImageNet, respectively. Furthermore, when using selective kernels, SemPPL significantly outperforms previous state-of-the-art achieving $72.3\%$ and $78.3\%$ top-$1$ accuracy on ImageNet with $1\%$ and $10\%$ labels, respectively, which improves absolute $+7.8\%$ and $+6.2\%$ over previous work. SemPPL also exhibits state-of-the-art performance over larger ResNet models as well as strong robustness, out-of-distribution and transfer performance. We release the checkpoints and the evaluation code at https://github.com/deepmind/semppl .
Authors: Jesse Islam, Maxime Turgeon, Robert Sladek, Sahir Bhatnagar
In the context of survival analysis, data-driven neural network-based methods have been developed to model complex covariate effects. While these methods may provide better predictive performance than regression-based approaches, not all can model time-varying interactions and complex baseline hazards. To address this, we propose Case-Base Neural Networks (CBNNs) as a new approach that combines the case-base sampling framework with flexible neural network architectures. Using a novel sampling scheme and data augmentation to naturally account for censoring, we construct a feed-forward neural network that includes time as an input. CBNNs predict the probability of an event occurring at a given moment to estimate the full hazard function. We compare the performance of CBNNs to regression and neural network-based survival methods in a simulation and three case studies using two time-dependent metrics. First, we examine performance on a simulation involving a complex baseline hazard and time-varying interactions to assess all methods, with CBNN outperforming competitors. Then, we apply all methods to three real data applications, with CBNNs outperforming the competing models in two studies and showing similar performance in the third. Our results highlight the benefit of combining case-base sampling with deep learning to provide a simple and flexible framework for data-driven modeling of single event survival outcomes that estimates time-varying effects and a complex baseline hazard by design. An R package is available at https://github.com/Jesse-Islam/cbnn.
Authors: Taiga Abe, E. Kelly Buchanan, Geoff Pleiss, John P. Cunningham
Classic results establish that encouraging predictive diversity improves performance in ensembles of low-capacity models, e.g. through bagging or boosting. Here we demonstrate that these intuitions do not apply to high-capacity neural network ensembles (deep ensembles), and in fact the opposite is often true. In a large scale study of nearly 600 neural network classification ensembles, we examine a variety of interventions that trade off component model performance for predictive diversity. While such interventions can improve the performance of small neural network ensembles (in line with standard intuitions), they harm the performance of the large neural network ensembles most often used in practice. Surprisingly, we also find that discouraging predictive diversity is often benign in large-network ensembles, fully inverting standard intuitions. Even when diversity-promoting interventions do not sacrifice component model performance (e.g. using heterogeneous architectures and training paradigms), we observe an opportunity cost associated with pursuing increased predictive diversity. Examining over 1000 ensembles, we observe that the performance benefits of diverse architectures/training procedures are easily dwarfed by the benefits of simply using higher-capacity models, despite the fact that such higher capacity models often yield significantly less predictive diversity. Overall, our findings demonstrate that standard intuitions around predictive diversity, originally developed for low-capacity ensembles, do not directly apply to modern high-capacity deep ensembles. This work clarifies fundamental challenges to the goal of improving deep ensembles by making them more diverse, while suggesting an alternative path: simply forming ensembles from ever more powerful (and less diverse) component models.
Authors: Nived Rajaraman, Yanjun Han, Jiantao Jiao, Kannan Ramchandran
We consider the sequential decision-making problem where the mean outcome is a non-linear function of the chosen action. Compared with the linear model, two curious phenomena arise in non-linear models: first, in addition to the "learning phase" with a standard parametric rate for estimation or regret, there is an "burn-in period" with a fixed cost determined by the non-linear function; second, achieving the smallest burn-in cost requires new exploration algorithms. For a special family of non-linear functions named ridge functions in the literature, we derive upper and lower bounds on the optimal burn-in cost, and in addition, on the entire learning trajectory during the burn-in period via differential equations. In particular, a two-stage algorithm that first finds a good initial action and then treats the problem as locally linear is statistically optimal. In contrast, several classical algorithms, such as UCB and algorithms relying on regression oracles, are provably suboptimal.
Authors: Guangyao Zheng, Samson Zhou, Vladimir Braverman, Michael A. Jacobs, Vishwa S. Parekh
Selective experience replay is a popular strategy for integrating lifelong learning with deep reinforcement learning. Selective experience replay aims to recount selected experiences from previous tasks to avoid catastrophic forgetting. Furthermore, selective experience replay based techniques are model agnostic and allow experiences to be shared across different models. However, storing experiences from all previous tasks make lifelong learning using selective experience replay computationally very expensive and impractical as the number of tasks increase. To that end, we propose a reward distribution-preserving coreset compression technique for compressing experience replay buffers stored for selective experience replay.
We evaluated the coreset compression technique on the brain tumor segmentation (BRATS) dataset for the task of ventricle localization and on the whole-body MRI for localization of left knee cap, left kidney, right trochanter, left lung, and spleen. The coreset lifelong learning models trained on a sequence of 10 different brain MR imaging environments demonstrated excellent performance localizing the ventricle with a mean pixel error distance of 12.93 for the compression ratio of 10x. In comparison, the conventional lifelong learning model localized the ventricle with a mean pixel distance of 10.87. Similarly, the coreset lifelong learning models trained on whole-body MRI demonstrated no significant difference (p=0.28) between the 10x compressed coreset lifelong learning models and conventional lifelong learning models for all the landmarks. The mean pixel distance for the 10x compressed models across all the landmarks was 25.30, compared to 19.24 for the conventional lifelong learning models. Our results demonstrate that the potential of the coreset-based ERB compression method for compressing experiences without a significant drop in performance.
Authors: Kai Zhang, Yutong Dai, Hongyi Wang, Eric Xing, Xun Chen, Lichao Sun
Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devices in federated learning, such as mobile phones and IoT devices with varying memory capabilities, would limit the scale and hence the performance of the model could be trained. The mainstream approaches to address memory limitations focus on width-slimming techniques, where different clients train subnetworks with reduced widths locally and then the server aggregates the subnetworks. The global model produced from these methods suffers from performance degradation due to the negative impact of the actions taken to handle the varying subnetwork widths in the aggregation phase. In this paper, we introduce a memory-adaptive depth-wise learning solution in FL called FeDepth, which adaptively decomposes the full model into blocks according to the memory budgets of each client and trains blocks sequentially to obtain a full inference model. Our method outperforms state-of-the-art approaches, achieving 5% and more than 10% improvements in top-1 accuracy on CIFAR-10 and CIFAR-100, respectively. We also demonstrate the effectiveness of depth-wise fine-tuning on ViT. Our findings highlight the importance of memory-aware techniques for federated learning with heterogeneous devices and the success of depth-wise training strategy in improving the global model's performance.
Authors: Guangyao Zheng, Michael A. Jacobs, Vladimir Braverman, Vishwa S. Parekh
Federated learning is a recent development in the machine learning area that allows a system of devices to train on one or more tasks without sharing their data to a single location or device. However, this framework still requires a centralized global model to consolidate individual models into one, and the devices train synchronously, which both can be potential bottlenecks for using federated learning. In this paper, we propose a novel method of asynchronous decentralized federated lifelong learning (ADFLL) method that inherits the merits of federated learning and can train on multiple tasks simultaneously without the need for a central node or synchronous training. Thus, overcoming the potential drawbacks of conventional federated learning. We demonstrate excellent performance on the brain tumor segmentation (BRATS) dataset for localizing the left ventricle on multiple image sequences and image orientation. Our framework allows agents to achieve the best performance with a mean distance error of 7.81, better than the conventional all-knowing agent's mean distance error of 11.78, and significantly (p=0.01) better than a conventional lifelong learning agent with a distance error of 15.17 after eight rounds of training. In addition, all ADFLL agents have comparable or better performance than a conventional LL agent. In conclusion, we developed an ADFLL framework with excellent performance and speed-up compared to conventional RL agents.
Authors: Steven Dahdah, James Richard Forbes
This paper proposes a method to identify a Koopman model of a feedback-controlled system given a known controller. The Koopman operator allows a nonlinear system to be rewritten as an infinite-dimensional linear system by viewing it in terms of an infinite set of lifting functions. A finite-dimensional approximation of the Koopman operator can be identified from data by choosing a finite subset of lifting functions and solving a regression problem in the lifted space. Existing methods are designed to identify open-loop systems. However, it is impractical or impossible to run experiments on some systems, such as unstable systems, in an open-loop fashion. The proposed method leverages the linearity of the Koopman operator, along with knowledge of the controller and the structure of the closed-loop system, to simultaneously identify the closed-loop and plant systems. The advantages of the proposed closed-loop Koopman operator approximation method are demonstrated experimentally using a rotary inverted pendulum system. An open-source software implementation of the proposed method is publicly available, along with the experimental dataset generated for this paper.
Authors: David Melching, Erik Schultheis, Eric Breitbarth
Digital image correlation (DIC) has become a valuable tool to monitor and evaluate mechanical experiments of cracked specimen, but the automatic detection of cracks is often difficult due to inherent noise and artefacts. Machine learning models have been extremely successful in detecting crack paths and crack tips using DIC-measured, interpolated full-field displacements as input to a convolution-based segmentation model. Still, big data is needed to train such models. However, scientific data is often scarce as experiments are expensive and time-consuming. In this work, we present a method to directly generate large amounts of artificial displacement data of cracked specimen resembling real interpolated DIC displacements. The approach is based on generative adversarial networks (GANs). During training, the discriminator receives physical domain knowledge in the form of the derived von Mises equivalent strain. We show that this physics-guided approach leads to improved results in terms of visual quality of samples, sliced Wasserstein distance, and geometry score when compared to a classical unguided GAN approach.
Authors: Arundhati Banerjee, Soham Phade, Stefano Ermon, Stephan Zheng
We study how a principal can efficiently and effectively intervene on the rewards of a previously unseen learning agent in order to induce desirable outcomes. This is relevant to many real-world settings like auctions or taxation, where the principal may not know the learning behavior nor the rewards of real people. Moreover, the principal should be few-shot adaptable and minimize the number of interventions, because interventions are often costly. We introduce MERMAIDE, a model-based meta-learning framework to train a principal that can quickly adapt to out-of-distribution agents with different learning strategies and reward functions. We validate this approach step-by-step. First, in a Stackelberg setting with a best-response agent, we show that meta-learning enables quick convergence to the theoretically known Stackelberg equilibrium at test time, although noisy observations severely increase the sample complexity. We then show that our model-based meta-learning approach is cost-effective in intervening on bandit agents with unseen explore-exploit strategies. Finally, we outperform baselines that use either meta-learning or agent behavior modeling, in both $0$-shot and $K=1$-shot settings with partial agent information.
Authors: Haoyu Chu, Shikui Wei, Ting Liu, Yao Zhao, Yuto Miyatake
Deep equilibrium (DEQ) models have emerged as a promising class of implicit layer models, which abandon traditional depth by solving for the fixed points of a single nonlinear layer. Despite their success, the stability of the fixed points for these models remains poorly understood. By considering DEQ models as nonlinear dynamic systems, we propose a robust DEQ model named LyaDEQ with guaranteed provable stability via Lyapunov theory. The crux of our method is ensuring the Lyapunov stability of the DEQ model's fixed points, which enables the proposed model to resist minor initial perturbations. To avoid poor adversarial defense due to Lyapunov-stable fixed points being located near each other, we orthogonalize the layers after the Lyapunov stability module to separate different fixed points. We evaluate LyaDEQ models under well-known adversarial attacks, and experimental results demonstrate significant improvement in robustness. Furthermore, we show that the LyaDEQ model can be combined with other defense methods, such as adversarial training, to achieve even better adversarial robustness.
Authors: Georg Siedel, Weijia Shao, Silvia Vock, Andrey Morozov
Robustness is a fundamental property of machine learning classifiers required to achieve safety and reliability. In the field of adversarial robustness of image classifiers, robustness is commonly defined as the stability of a model to all input changes within a p-norm distance. However, in the field of random corruption robustness, variations observed in the real world are used, while p-norm corruptions are rarely considered. This study investigates the use of random p-norm corruptions to augment the training and test data of image classifiers. We evaluate the model robustness against imperceptible random p-norm corruptions and propose a novel robustness metric. We empirically investigate whether robustness transfers across different p-norms and derive conclusions on which p-norm corruptions a model should be trained and evaluated. We find that training data augmentation with a combination of p-norm corruptions significantly improves corruption robustness, even on top of state-of-the-art data augmentation schemes.
Authors: Tu T. Do, Mai Anh Vu, Tuan L. Vo, Hoang Thien Ly, Thu Nguyen, Steven A. Hicks, Michael A. Riegler, Pål Halvorsen, Binh T. Nguyen
Monotone missing data is a common problem in data analysis. However, imputation combined with dimensionality reduction can be computationally expensive, especially with the increasing size of datasets. To address this issue, we propose a Blockwise principal component analysis Imputation (BPI) framework for dimensionality reduction and imputation of monotone missing data. The framework conducts Principal Component Analysis (PCA) on the observed part of each monotone block of the data and then imputes on merging the obtained principal components using a chosen imputation technique. BPI can work with various imputation techniques and can significantly reduce imputation time compared to conducting dimensionality reduction after imputation. This makes it a practical and efficient approach for large datasets with monotone missing data. Our experiments validate the improvement in speed. In addition, our experiments also show that while applying MICE imputation directly on missing data may not yield convergence, applying BPI with MICE for the data may lead to convergence.
Authors: Cheng Tan, Zhangyang Gao, Lirong Wu, Jun Xia, Jiangbin Zheng, Xihong Yang, Yue Liu, Bozhen Hu, Stan Z. Li
Antibodies are crucial proteins produced by the immune system in response to foreign substances or antigens. The specificity of an antibody is determined by its complementarity-determining regions (CDRs), which are located in the variable domains of the antibody chains and form the antigen-binding site. Previous studies have utilized complex techniques to generate CDRs, but they suffer from inadequate geometric modeling. Moreover, the common iterative refinement strategies lead to an inefficient inference. In this paper, we propose a \textit{simple yet effective} model that can co-design 1D sequences and 3D structures of CDRs in a one-shot manner. To achieve this, we decouple the antibody CDR design problem into two stages: (i) geometric modeling of protein complex structures and (ii) sequence-structure co-learning. We develop a novel macromolecular structure invariant embedding, typically for protein complexes, that captures both intra- and inter-component interactions among the backbone atoms, including C$\alpha$, N, C, and O atoms, to achieve comprehensive geometric modeling. Then, we introduce a simple cross-gate MLP for sequence-structure co-learning, allowing sequence and structure representations to implicitly refine each other. This enables our model to design desired sequences and structures in a one-shot manner. Extensive experiments are conducted to evaluate our results at both the sequence and structure levels, which demonstrate that our model achieves superior performance compared to the state-of-the-art antibody CDR design methods.
Authors: Jongho Park, Jinchao Xu
We propose a new training algorithm, named DualFL (Dualized Federated Learning), for solving distributed optimization problems in federated learning. DualFL achieves communication acceleration for very general convex cost functions, thereby providing a solution to an open theoretical problem in federated learning concerning cost functions that may not be smooth nor strongly convex. We provide a detailed analysis for the local iteration complexity of DualFL to ensure the overall computational efficiency of DualFL. Furthermore, we introduce a completely new approach for the convergence analysis of federated learning based on a dual formulation. This new technique enables concise and elegant analysis, which contrasts the complex calculations used in existing literature on convergence of federated learning algorithms.
Authors: Niall Jeffrey, Benjamin D. Wandelt
Evidence Networks can enable Bayesian model comparison when state-of-the-art methods (e.g. nested sampling) fail and even when likelihoods or priors are intractable or unknown. Bayesian model comparison, i.e. the computation of Bayes factors or evidence ratios, can be cast as an optimization problem. Though the Bayesian interpretation of optimal classification is well-known, here we change perspective and present classes of loss functions that result in fast, amortized neural estimators that directly estimate convenient functions of the Bayes factor. This mitigates numerical inaccuracies associated with estimating individual model probabilities. We introduce the leaky parity-odd power (l-POP) transform, leading to the novel ``l-POP-Exponential'' loss function. We explore neural density estimation for data probability in different models, showing it to be less accurate and scalable than Evidence Networks. Multiple real-world and synthetic examples illustrate that Evidence Networks are explicitly independent of dimensionality of the parameter space and scale mildly with the complexity of the posterior probability density function. This simple yet powerful approach has broad implications for model inference tasks. As an application of Evidence Networks to real-world data we compute the Bayes factor for two models with gravitational lensing data of the Dark Energy Survey. We briefly discuss applications of our methods to other, related problems of model comparison and evaluation in implicit inference settings.
Authors: Philipp Wiesner, Ramin Khalili, Dennis Grinwald, Pratik Agrawal, Lauritz Thamsen, Odej Kao
Federated Learning (FL) is an emerging machine learning technique that enables distributed model training across data silos or edge devices without data sharing. Yet, FL inevitably introduces inefficiencies compared to centralized model training, which will further increase the already high energy usage and associated carbon emissions of machine learning in the future. One idea to reduce FL's carbon footprint is to schedule training jobs based on the availability of renewable excess energy that can occur at certain times and places in the grid. However, in the presence of such volatile and unreliable resources, existing FL schedulers cannot always ensure fast, efficient, and fair training.
We propose FedZero, an FL system that operates exclusively on renewable excess energy and spare capacity of compute infrastructure to effectively reduce a training's operational carbon emissions to zero. Using energy and load forecasts, FedZero leverages the spatio-temporal availability of excess resources by selecting clients for fast convergence and fair participation. Our evaluation, based on real solar and load traces, shows that FedZero converges significantly faster than existing approaches under the mentioned constraints while consuming less energy. Furthermore, it is robust to forecasting errors and scalable to tens of thousands of clients.
Authors: Yuchen Bai, Jean-Baptiste Durand, Grégoire Vincent, Florence Forbes
LiDAR (Light Detection and Ranging) has become an essential part of the remote sensing toolbox used for biosphere monitoring. In particular, LiDAR provides the opportunity to map forest leaf area with unprecedented accuracy, while leaf area has remained an important source of uncertainty affecting models of gas exchanges between the vegetation and the atmosphere. Unmanned Aerial Vehicles (UAV) are easy to mobilize and therefore allow frequent revisits to track the response of vegetation to climate change. However, miniature sensors embarked on UAVs usually provide point clouds of limited density, which are further affected by a strong decrease in density from top to bottom of the canopy due to progressively stronger occlusion. In such a context, discriminating leaf points from wood points presents a significant challenge due in particular to strong class imbalance and spatially irregular sampling intensity. Here we introduce a neural network model based on the Pointnet ++ architecture which makes use of point geometry only (excluding any spectral information). To cope with local data sparsity, we propose an innovative sampling scheme which strives to preserve local important geometric information. We also propose a loss function adapted to the severe class imbalance. We show that our model outperforms state-of-the-art alternatives on UAV point clouds. We discuss future possible improvements, particularly regarding much denser point clouds acquired from below the canopy.
Authors: Christopher Williams, Fabian Falck, George Deligiannidis, Chris Holmes, Arnaud Doucet, Saifuddin Syed
U-Nets are a go-to, state-of-the-art neural architecture across numerous tasks for continuous signals on a square such as images and Partial Differential Equations (PDE), however their design and architecture is understudied. In this paper, we provide a framework for designing and analysing general U-Net architectures. We present theoretical results which characterise the role of the encoder and decoder in a U-Net, their high-resolution scaling limits and their conjugacy to ResNets via preconditioning. We propose Multi-ResNets, U-Nets with a simplified, wavelet-based encoder without learnable parameters. Further, we show how to design novel U-Net architectures which encode function constraints, natural bases, or the geometry of the data. In diffusion models, our framework enables us to identify that high-frequency information is dominated by noise exponentially faster, and show how U-Nets with average pooling exploit this. In our experiments, we demonstrate how Multi-ResNets achieve competitive and often superior performance compared to classical U-Nets in image segmentation, PDE surrogate modelling, and generative modelling with diffusion models. Our U-Net framework paves the way to study the theoretical properties of U-Nets and design natural, scalable neural architectures for a multitude of problems beyond the square.
Authors: Michael Giegrich, Roel Oomen, Christoph Reisinger
In this paper, we propose a novel $K$-nearest neighbor resampling procedure for estimating the performance of a policy from historical data containing realized episodes of a decision process generated under a different policy. We provide statistical consistency results under weak conditions. In particular, we avoid the common assumption of identically and independently distributed transitions and rewards. Instead, our analysis allows for the sampling of entire episodes, as is common practice in most applications. To establish the consistency in this setting, we generalize Stone's Theorem, a well-known result in nonparametric statistics on local averaging, to include episodic data and the counterfactual estimation underlying off-policy evaluation (OPE). By focusing on feedback policies that depend deterministically on the current state in environments with continuous state-action spaces and system-inherent stochasticity effected by chosen actions, and relying on trajectory simulation similar to Monte Carlo methods, the proposed method is particularly well suited for stochastic control environments. Compared to other OPE methods, our algorithm does not require optimization, can be efficiently implemented via tree-based nearest neighbor search and parallelization, and does not explicitly assume a parametric model for the environment's dynamics. Numerical experiments demonstrate the effectiveness of the algorithm compared to existing baselines in a variety of stochastic control settings, including a linear quadratic regulator, trade execution in limit order books, and online stochastic bin packing.
Authors: Antoine Lesage-Landry, Julien Pallage
We propose new algorithms with provable performance for online binary optimization subject to general constraints and in dynamic settings. We consider the subset of problems in which the objective function is submodular. We propose the online submodular greedy algorithm (OSGA) which solves to optimality an approximation of the previous round loss function to avoid the NP-hardness of the original problem. We extend OSGA to a generic approximation function. We show that OSGA has a dynamic regret bound similar to the tightest bounds in online convex optimization with respect to the time horizon and the cumulative round optimum variation. For instances where no approximation exists or a computationally simpler implementation is desired, we design the online submodular projected gradient descent (OSPGD) by leveraging the Lova\'sz extension. We obtain a regret bound that is akin to the conventional online gradient descent (OGD). Finally, we numerically test our algorithms in two power system applications: fast-timescale demand response and real-time distribution network reconfiguration.
Authors: Jie Wang, Zheng Yan, Jiahe Lan, Elisa Bertino, Witold Pedrycz
Trust evaluation assesses trust relationships between entities and facilitates decision-making. Machine Learning (ML) shows great potential for trust evaluation owing to its learning capabilities. In recent years, Graph Neural Networks (GNNs), as a new ML paradigm, have demonstrated superiority in dealing with graph data. This has motivated researchers to explore their use in trust evaluation, as trust relationships among entities can be modeled as a graph. However, current trust evaluation methods that employ GNNs fail to fully satisfy the dynamic nature of trust, overlook the adverse effects of trust-related attacks, and cannot provide convincing explanations on evaluation results. To address these problems, we propose TrustGuard, a GNN-based accurate trust evaluation model that supports trust dynamicity, is robust against typical attacks, and provides explanations through visualization. Specifically, TrustGuard is designed with a layered architecture that contains a snapshot input layer, a spatial aggregation layer, a temporal aggregation layer, and a prediction layer. Among them, the spatial aggregation layer adopts a defense mechanism to robustly aggregate local trust, and the temporal aggregation layer applies an attention mechanism for effective learning of temporal patterns. Extensive experiments on two real-world datasets show that TrustGuard outperforms state-of-the-art GNN-based trust evaluation models with respect to trust prediction across single-timeslot and multi-timeslot, even in the presence of attacks. In addition, TrustGuard can explain its evaluation results by visualizing both spatial and temporal views.
Authors: David Jacob Kedziora, Anna Musiał, Wojciech Rudno-Rudziński, Bogdan Gabrys
Novel methods for rapidly estimating single-photon source (SPS) quality have been promoted in recent literature to address the expensive and time-consuming nature of experimental validation via intensity interferometry. However, the frequent lack of uncertainty discussions and reproducible details raises concerns about their reliability. This study investigates the use of data augmentation, a machine learning technique, to supplement experimental data with bootstrapped samples and quantify the uncertainty of such estimates. Eight datasets obtained from measurements involving a single InGaAs/GaAs epitaxial quantum dot serve as a proof-of-principle example. Analysis of one of the SPS quality metrics derived from efficient histogram fitting of the synthetic samples, i.e. the probability of multi-photon emission events, reveals significant uncertainty contributed by stochastic variability in the Poisson processes that describe detection rates. Ignoring this source of error risks severe overconfidence in both early quality estimates and claims for state-of-the-art SPS devices. Additionally, this study finds that standard least-squares fitting is comparable to using a Poisson likelihood, and expanding averages show some promise for early estimation. Also, reducing background counts improves fitting accuracy but does not address the Poisson-process variability. Ultimately, data augmentation demonstrates its value in supplementing physical experiments; its benefit here is to emphasise the need for a cautious assessment of SPS quality.
Authors: Patrick Emami, Abhijeet Sahu, Peter Graf
Short-term forecasting of residential and commercial building energy consumption is widely used in power systems and continues to grow in importance. Data-driven short-term load forecasting (STLF), although promising, has suffered from a lack of open, large-scale datasets with high building diversity. This has hindered exploring the pretrain-then-fine-tune paradigm for STLF. To help address this, we present BuildingsBench, which consists of: 1) Buildings-900K, a large-scale dataset of 900K simulated buildings representing the U.S. building stock; and 2) an evaluation platform with over 1,900 real residential and commercial buildings from 7 open datasets. BuildingsBench benchmarks two under-explored tasks: zero-shot STLF, where a pretrained model is evaluated on unseen buildings without fine-tuning, and transfer learning, where a pretrained model is fine-tuned on a target building. The main finding of our benchmark analysis is that synthetically pretrained models generalize surprisingly well to real commercial buildings. An exploration of the effect of increasing dataset size and diversity on zero-shot commercial building performance reveals a power-law with diminishing returns. We also show that fine-tuning pretrained models on real commercial and residential buildings improves performance for a majority of target buildings. We hope that BuildingsBench encourages and facilitates future research on generalizable STLF. All datasets and code can be accessed from https://github.com/NREL/BuildingsBench.
Authors: Francesco Cagnetta, Leonardo Petrini, Umberto M. Tomasini, Alessandro Favero, Matthieu Wyart
Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional data representations. However, how many training examples are required to learn such representations remains unknown. To quantitatively study this question, we introduce the Random Hierarchy Model: a family of synthetic tasks inspired by the hierarchical structure of language and images. The model is a classification task where each class corresponds to a group of high-level features, chosen among several equivalent groups associated with the same class. In turn, each feature corresponds to a group of sub-features chosen among several equivalent ones and so on, following a hierarchy of composition rules. We find that deep networks learn the task by developing internal representations invariant to exchanging equivalent groups. Moreover, the number of data required corresponds to the point where correlations between low-level features and classes become detectable. Overall, our results indicate how deep networks overcome the curse of dimensionality by building invariant representations, and provide an estimate of the number of data required to learn a hierarchical task.
Authors: Benjamin S. Ruben, Cengiz Pehlevan
Feature bagging is a well-established ensembling method which aims to reduce prediction variance by combining predictions of many estimators trained on subsets or projections of features. Here, we develop a theory of feature-bagging in noisy least-squares ridge ensembles and simplify the resulting learning curves in the special case of equicorrelated data. Using analytical learning curves, we demonstrate that subsampling shifts the double-descent peak of a linear predictor. This leads us to introduce heterogeneous feature ensembling, with estimators built on varying numbers of feature dimensions, as a computationally efficient method to mitigate double-descent. Then, we compare the performance of a feature-subsampling ensemble to a single linear predictor, describing a trade-off between noise amplification due to subsampling and noise reduction due to ensembling. Our qualitative insights carry over to linear classifiers applied to image classification tasks with realistic datasets constructed using a state-of-the-art deep learning feature map.
Authors: Anindya Mondal, Sauradip Nag, Joaquin M Prada, Xiatian Zhu, Anjan Dutta
Existing action recognition methods are typically actor-specific due to the intrinsic topological and apparent differences among the actors. This requires actor-specific pose estimation (e.g., humans vs. animals), leading to cumbersome model design complexity and high maintenance costs. Moreover, they often focus on learning the visual modality alone and single-label classification whilst neglecting other available information sources (e.g., class name text) and the concurrent occurrence of multiple actions. To overcome these limitations, we propose a new approach called 'actor-agnostic multi-modal multi-label action recognition,' which offers a unified solution for various types of actors, including humans and animals. We further formulate a novel Multi-modal Semantic Query Network (MSQNet) model in a transformer-based object detection framework (e.g., DETR), characterized by leveraging visual and textual modalities to represent the action classes better. The elimination of actor-specific model designs is a key advantage, as it removes the need for actor pose estimation altogether. Extensive experiments on five publicly available benchmarks show that our MSQNet consistently outperforms the prior arts of actor-specific alternatives on human and animal single- and multi-label action recognition tasks by up to 50%. Code is made available at https://github.com/mondalanindya/MSQNet.
Authors: Phuong Quynh Le, Jörg Schlötterer, Christin Seifert
Models trained with empirical risk minimization (ERM) are known to learn to rely on spurious features, i.e., their prediction is based on undesired auxiliary features which are strongly correlated with class labels but lack causal reasoning. This behavior particularly degrades accuracy in groups of samples of the correlated class that are missing the spurious feature or samples of the opposite class but with the spurious feature present. The recently proposed Deep Feature Reweighting (DFR) method improves accuracy of these worst groups. Based on the main argument that ERM mods can learn core features sufficiently well, DFR only needs to retrain the last layer of the classification model with a small group-balanced data set. In this work, we examine the applicability of DFR to realistic data in the medical domain. Furthermore, we investigate the reasoning behind the effectiveness of last-layer retraining and show that even though DFR has the potential to improve the accuracy of the worst group, it remains susceptible to spurious correlations.
Authors: Matthew J. Vowels
Causal inference is a crucial goal of science, enabling researchers to arrive at meaningful conclusions regarding the predictions of hypothetical interventions using observational data. Path models, Structural Equation Models (SEMs), and, more generally, Directed Acyclic Graphs (DAGs), provide a means to unambiguously specify assumptions regarding the causal structure underlying a phenomenon. Unlike DAGs, which make very few assumptions about the functional and parametric form, SEM assumes linearity. This can result in functional misspecification which prevents researchers from undertaking reliable effect size estimation. In contrast, we propose Super Learner Equation Modeling, a path modeling technique integrating machine learning Super Learner ensembles. We empirically demonstrate its ability to provide consistent and unbiased estimates of causal effects, its competitive performance for linear models when compared with SEM, and highlight its superiority over SEM when dealing with non-linear relationships. We provide open-source code, and a tutorial notebook with example usage, accentuating the easy-to-use nature of the method.
Authors: Nico Uhlemann, Felix Fent, Markus Lienkamp
In this paper, we assess the state of the art in pedestrian trajectory prediction within the context of generating single trajectories, a critical aspect aligning with the requirements in autonomous systems. The evaluation is conducted on the widely-used ETH/UCY dataset where the Average Displacement Error (ADE) and the Final Displacement Error (FDE) are reported. Alongside this, we perform an ablation study to investigate the impact of the observed motion history on prediction performance. To evaluate the scalability of each approach when confronted with varying amounts of agents, the inference time of each model is measured. Following a quantitative analysis, the resulting predictions are compared in a qualitative manner, giving insight into the strengths and weaknesses of current approaches. The results demonstrate that although a constant velocity model (CVM) provides a good approximation of the overall dynamics in the majority of cases, additional features need to be incorporated to reflect common pedestrian behavior observed. Therefore, this study presents a data-driven analysis with the intent to guide the future development of pedestrian trajectory prediction algorithms.
Authors: Zihui Ma, Lingyao Li, Libby Hemphill, Gregory B. Baecher, Yubai Yuan
Effective disaster response is critical for affected communities. Responders and decision-makers would benefit from reliable, timely measures of the issues impacting their communities during a disaster, and social media offers a potentially rich data source. Social media can reflect public concerns and demands during a disaster, offering valuable insights for decision-makers to understand evolving situations and optimize resource allocation. We used Bidirectional Encoder Representations from Transformers (BERT) topic modeling to cluster topics from Twitter data. Then, we conducted a temporal-spatial analysis to examine the distribution of these topics across different regions during the 2020 western U.S. wildfire season. Our results show that Twitter users mainly focused on three topics:"health impact," "damage," and "evacuation." We used the Susceptible-Infected-Recovered (SIR) theory to explore the magnitude and velocity of topic diffusion on Twitter. The results displayed a clear relationship between topic trends and wildfire propagation patterns. The estimated parameters obtained from the SIR model in selected cities revealed that residents exhibited a high level of several concerns during the wildfire. Our study details how the SIR model and topic modeling using social media data can provide decision-makers with a quantitative approach to measure disaster response and support their decision-making processes.
Authors: Shuyan Wang
The goal of Causal Discovery is to find automated search methods for learning causal structures from observational data. In some cases all variables of the interested causal mechanism are measured, and the task is to predict the effects one measured variable has on another. In contrast, sometimes the variables of primary interest are not directly observable but instead inferred from their manifestations in the data. These are referred to as latent variables. One commonly known example is the psychological construct of intelligence, which cannot directly measured so researchers try to assess through various indicators such as IQ tests. In this case, casual discovery algorithms can uncover underlying patterns and structures to reveal the causal connections between the latent variables and between the latent and observed variables. This thesis focuses on two questions in causal discovery: providing an alternative definition of k-Triangle Faithfulness that (i) is weaker than strong faithfulness when applied to the Gaussian family of distributions, (ii) can be applied to non-Gaussian families of distributions, and (iii) under the assumption that the modified version of Strong Faithfulness holds, can be used to show the uniform consistency of a modified causal discovery algorithm; relaxing the sufficiency assumption to learn causal structures with latent variables. Given the importance of inferring cause-and-effect relationships for understanding and forecasting complex systems, the work in this thesis of relaxing various simplification assumptions is expected to extend the causal discovery method to be applicable in a wider range with diversified causal mechanism and statistical phenomena.
Authors: Hewei Tang, Qingkai Kong, Joseph P. Morris
Deep learning-based surrogate models have been widely applied in geological carbon storage (GCS) problems to accelerate the prediction of reservoir pressure and CO2 plume migration. Large amounts of data from physics-based numerical simulators are required to train a model to accurately predict the complex physical behaviors associated with this process. In practice, the available training data are always limited in large-scale 3D problems due to the high computational cost. Therefore, we propose to use a multi-fidelity Fourier neural operator (FNO) to solve large-scale GCS problems with more affordable multi-fidelity training datasets. FNO has a desirable grid-invariant property, which simplifies the transfer learning procedure between datasets with different discretization. We first test the model efficacy on a GCS reservoir model being discretized into 110k grid cells. The multi-fidelity model can predict with accuracy comparable to a high-fidelity model trained with the same amount of high-fidelity data with 81% less data generation costs. We further test the generalizability of the multi-fidelity model on a same reservoir model with a finer discretization of 1 million grid cells. This case was made more challenging by employing high-fidelity and low-fidelity datasets generated by different geostatistical models and reservoir simulators. We observe that the multi-fidelity FNO model can predict pressure fields with reasonable accuracy even when the high-fidelity data are extremely limited. The findings of this study can help for better understanding of the transferability of multi-fidelity deep learning surrogate models.
Authors: Ahmad Hammoudeh, Stéphane Dupont
Image registration (IR) is a process that deforms images to align them with respect to a reference space, making it easier for medical practitioners to examine various medical images in a standardized reference frame, such as having the same rotation and scale. This document introduces image registration using a simple numeric example. It provides a definition of image registration along with a space-oriented symbolic representation. This review covers various aspects of image transformations, including affine, deformable, invertible, and bidirectional transformations, as well as medical image registration algorithms such as Voxelmorph, Demons, SyN, Iterative Closest Point, and SynthMorph. It also explores atlas-based registration and multistage image registration techniques, including coarse-fine and pyramid approaches. Furthermore, this survey paper discusses medical image registration taxonomies, datasets, evaluation measures, such as correlation-based metrics, segmentation-based metrics, processing time, and model size. It also explores applications in image-guided surgery, motion tracking, and tumor diagnosis. Finally, the document addresses future research directions, including the further development of transformers.
Authors: Shivam Mehta, Ruibo Tu, Jonas Beskow, Éva Székely, Gustav Eje Henter
We introduce Matcha-TTS, a new encoder-decoder architecture for speedy TTS acoustic modelling, trained using optimal-transport conditional flow matching (OT-CFM). This yields an ODE-based decoder capable of high output quality in fewer synthesis steps than models trained using score matching. Careful design choices additionally ensure each synthesis step is fast to run. The method is probabilistic, non-autoregressive, and learns to speak from scratch without external alignments. Compared to strong pre-trained baseline models, the Matcha-TTS system has the smallest memory footprint, rivals the speed of the fastest models on long utterances, and attains the highest mean opinion score in a listening test. Please see https://shivammehta25.github.io/Matcha-TTS/ for audio examples, code, and pre-trained models.
Authors: Ahmed H. Shahin, An Zhao, Alexander C. Whitehead, Daniel C. Alexander, Joseph Jacob, David Barber
Survival analysis is a valuable tool for estimating the time until specific events, such as death or cancer recurrence, based on baseline observations. This is particularly useful in healthcare to prognostically predict clinically important events based on patient data. However, existing approaches often have limitations; some focus only on ranking patients by survivability, neglecting to estimate the actual event time, while others treat the problem as a classification task, ignoring the inherent time-ordered structure of the events. Furthermore, the effective utilization of censored samples - training data points where the exact event time is unknown - is essential for improving the predictive accuracy of the model. In this paper, we introduce CenTime, a novel approach to survival analysis that directly estimates the time to event. Our method features an innovative event-conditional censoring mechanism that performs robustly even when uncensored data is scarce. We demonstrate that our approach forms a consistent estimator for the event model parameters, even in the absence of uncensored data. Furthermore, CenTime is easily integrated with deep learning models with no restrictions on batch size or the number of uncensored samples. We compare our approach with standard survival analysis methods, including the Cox proportional-hazard model and DeepHit. Our results indicate that CenTime offers state-of-the-art performance in predicting time-to-death while maintaining comparable ranking performance. Our implementation is publicly available at https://github.com/ahmedhshahin/CenTime.
Authors: Yucheng Wang, Yuecong Xu, Jianfei Yang, Min Wu, Xiaoli Li, Lihua Xie, Zhenghua Chen
Contrastive learning, as a self-supervised learning paradigm, becomes popular for Multivariate Time-Series (MTS) classification. It ensures the consistency across different views of unlabeled samples and then learns effective representations for these samples. Existing contrastive learning methods mainly focus on achieving temporal consistency with temporal augmentation and contrasting techniques, aiming to preserve temporal patterns against perturbations for MTS data. However, they overlook spatial consistency that requires the stability of individual sensors and their correlations. As MTS data typically originate from multiple sensors, ensuring spatial consistency becomes essential for the overall performance of contrastive learning on MTS data. Thus, we propose Graph-Aware Contrasting for spatial consistency across MTS data. Specifically, we propose graph augmentations including node and edge augmentations to preserve the stability of sensors and their correlations, followed by graph contrasting with both node- and graph-level contrasting to extract robust sensor- and global-level features. We further introduce multi-window temporal contrasting to ensure temporal consistency in the data for each sensor. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on various MTS classification tasks. The code is available at https://github.com/Frank-Wang-oss/TS-GAC.
Authors: Yucheng Wang, Yuecong Xu, Jianfei Yang, Min Wu, Xiaoli Li, Lihua Xie, Zhenghua Chen
Multivariate Time-Series (MTS) data is crucial in various application fields. With its sequential and multi-source (multiple sensors) properties, MTS data inherently exhibits Spatial-Temporal (ST) dependencies, involving temporal correlations between timestamps and spatial correlations between sensors in each timestamp. To effectively leverage this information, Graph Neural Network-based methods (GNNs) have been widely adopted. However, existing approaches separately capture spatial dependency and temporal dependency and fail to capture the correlations between Different sEnsors at Different Timestamps (DEDT). Overlooking such correlations hinders the comprehensive modelling of ST dependencies within MTS data, thus restricting existing GNNs from learning effective representations. To address this limitation, we propose a novel method called Fully-Connected Spatial-Temporal Graph Neural Network (FC-STGNN), including two key components namely FC graph construction and FC graph convolution. For graph construction, we design a decay graph to connect sensors across all timestamps based on their temporal distances, enabling us to fully model the ST dependencies by considering the correlations between DEDT. Further, we devise FC graph convolution with a moving-pooling GNN layer to effectively capture the ST dependencies for learning effective representations. Extensive experiments show the effectiveness of FC-STGNN on multiple MTS datasets compared to SOTA methods. The code is available at https://github.com/Frank-Wang-oss/FCSTGNN.
Authors: Zhijun Pan, Fangqiang Ding, Hantao Zhong, Chris Xiaoxuan Lu
Mobile autonomy relies on the precise perception of dynamic environments. Robustly tracking moving objects in 3D world thus plays a pivotal role for applications like trajectory prediction, obstacle avoidance, and path planning. While most current methods utilize LiDARs or cameras for Multiple Object Tracking (MOT), the capabilities of 4D imaging radars remain largely unexplored. Recognizing the challenges posed by radar noise and point sparsity in 4D radar data, we introduce RaTrack, an innovative solution tailored for radar-based tracking. Bypassing the typical reliance on specific object types and 3D bounding boxes, our method focuses on motion segmentation and clustering, enriched by a motion estimation module. Evaluated on the View-of-Delft dataset, RaTrack showcases superior tracking precision of moving objects, largely surpassing the performance of the state of the art.
Authors: Minsu Kim, Walid Saad
In continual learning (CL), an AI agent (e.g., autonomous vehicles or robotics) learns from non-stationary data streams under dynamic environments. For the practical deployment of such applications, it is important to guarantee robustness to unseen environments while maintaining past experiences. In this paper, a novel CL framework is proposed to achieve robust generalization to dynamic environments while retaining past knowledge. The considered CL agent uses a capacity-limited memory to save previously observed environmental information to mitigate forgetting issues. Then, data points are sampled from the memory to estimate the distribution of risks over environmental change so as to obtain predictors that are robust with unseen changes. The generalization and memorization performance of the proposed framework are theoretically analyzed. This analysis showcases the tradeoff between memorization and generalization with the memory size. Experiments show that the proposed algorithm outperforms memory-based CL baselines across all environments while significantly improving the generalization performance on unseen target environments.
Authors: Tuyen Trung Truong
In root finding and optimization, there are many cases where there is a closed set $A$ one likes that the sequence constructed by one's favourite method will not converge to A (here, we do not assume extra properties on $A$ such as being convex or connected). For example, if one wants to find roots, and one chooses initial points in the basin of attraction for 1 root $z^*$ (a fact which one may not know before hand), then one will always end up in that root. In this case, one would like to have a mechanism to avoid this point $z^*$ in the next runs of one's algorithm.
Assume that one already has a method IM for optimization (and root finding) for non-constrained optimization. We provide a simple modification IM1 of the method to treat the situation discussed in the previous paragraph. If the method IM has strong theoretical guarantees, then so is IM1. As applications, we prove two theoretical applications: one concerns finding roots of a meromorphic function in an open subset of a Riemann surface, and the other concerns finding local minima of a function in an open subset of a Euclidean space inside it the function has at most countably many critical points.
Along the way, we compare with main existing relevant methods in the current literature. We provide several examples in various different settings to illustrate the usefulness of the new approach.
Authors: Lin Ni, Sijie Wang, Zeyu Zhang, Xiaoxuan Li, Xianda Zheng, Paul Denny, Jiamou Liu
Learnersourcing offers great potential for scalable education through student content creation. However, predicting student performance on learnersourced questions, which is essential for personalizing the learning experience, is challenging due to the inherent noise in student-generated data. Moreover, while conventional graph-based methods can capture the complex network of student and question interactions, they often fall short under cold start conditions where limited student engagement with questions yields sparse data. To address both challenges, we introduce an innovative strategy that synergizes the potential of integrating Signed Graph Neural Networks (SGNNs) and Large Language Model (LLM) embeddings. Our methodology employs a signed bipartite graph to comprehensively model student answers, complemented by a contrastive learning framework that enhances noise resilience. Furthermore, LLM's contribution lies in generating foundational question embeddings, proving especially advantageous in addressing cold start scenarios characterized by limited graph data. Validation across five real-world datasets sourced from the PeerWise platform underscores our approach's effectiveness. Our method outperforms baselines, showcasing enhanced predictive accuracy and robustness.
Authors: Oscar Mañas, Benno Krojer, Aishwarya Agrawal
8 years after the visual question answering (VQA) task was proposed, accuracy remains the primary metric for automatic evaluation. VQA Accuracy has been effective so far in the IID evaluation setting. However, our community is undergoing a shift towards open-ended generative models and OOD evaluation. In this new paradigm, the existing VQA Accuracy metric is overly stringent and underestimates the performance of VQA systems. Thus, there is a need to develop more robust automatic VQA metrics that serve as a proxy for human judgment. In this work, we propose to leverage the in-context learning capabilities of instruction-tuned large language models (LLMs) to build a better VQA metric. We formulate VQA evaluation as an answer-rating task where the LLM is instructed to score the accuracy of a candidate answer given a set of reference answers. We demonstrate the proposed metric better correlates with human judgment compared to existing metrics across several VQA models and benchmarks. We hope wide adoption of our metric will contribute to better estimating the research progress on the VQA task. We plan to release the evaluation code and collected human judgments.
Authors: Shivam Mehta, Ruibo Tu, Simon Alexanderson, Jonas Beskow, Éva Székely, Gustav Eje Henter
As text-to-speech technologies achieve remarkable naturalness in read-aloud tasks, there is growing interest in multimodal synthesis of verbal and non-verbal communicative behaviour, such as spontaneous speech and associated body gestures. This paper presents a novel, unified architecture for jointly synthesising speech acoustics and skeleton-based 3D gesture motion from text, trained using optimal-transport conditional flow matching (OT-CFM). The proposed architecture is simpler than the previous state of the art, has a smaller memory footprint, and can capture the joint distribution of speech and gestures, generating both modalities together in one single process. The new training regime, meanwhile, enables better synthesis quality in much fewer steps (network evaluations) than before. Uni- and multimodal subjective tests demonstrate improved speech naturalness, gesture human-likeness, and cross-modal appropriateness compared to existing benchmarks. Please see https://shivammehta25.github.io/Match-TTSG/ for video examples and code.
Authors: Pengcheng Xu, Tao Feng, Tianfan Fu, Siddhartha Laghuvarapu, Jimeng Sun
In this work, we introduce a method to fine-tune a Transformer-based generative model for molecular de novo design. Leveraging the superior sequence learning capacity of Transformers over Recurrent Neural Networks (RNNs), our model can generate molecular structures with desired properties effectively. In contrast to the traditional RNN-based models, our proposed method exhibits superior performance in generating compounds predicted to be active against various biological targets, capturing long-term dependencies in the molecular structure sequence. The model's efficacy is demonstrated across numerous tasks, including generating analogues to a query structure and producing compounds with particular attributes, outperforming the baseline RNN-based methods. Our approach can be used for scaffold hopping, library expansion starting from a single molecule, and generating compounds with high predicted activity against biological targets.
Authors: Luigi Sigillo, Eleonora Grassucci, Aurelio Uncini, Danilo Comminiello
Neural network generalizability is becoming a broad research field due to the increasing availability of datasets from different sources and for various tasks. This issue is even wider when processing medical data, where a lack of methodological standards causes large variations being provided by different imaging centers or acquired with various devices and cofactors. To overcome these limitations, we introduce a novel, generalizable, data- and task-agnostic framework able to extract salient features from medical images. The proposed quaternion wavelet network (QUAVE) can be easily integrated with any pre-existing medical image analysis or synthesis task, and it can be involved with real, quaternion, or hypercomplex-valued models, generalizing their adoption to single-channel data. QUAVE first extracts different sub-bands through the quaternion wavelet transform, resulting in both low-frequency/approximation bands and high-frequency/fine-grained features. Then, it weighs the most representative set of sub-bands to be involved as input to any other neural model for image processing, replacing standard data samples. We conduct an extensive experimental evaluation comprising different datasets, diverse image analysis, and synthesis tasks including reconstruction, segmentation, and modality translation. We also evaluate QUAVE in combination with both real and quaternion-valued models. Results demonstrate the effectiveness and the generalizability of the proposed framework that improves network performance while being flexible to be adopted in manifold scenarios and robust to domain shifts. The full code is available at: https://github.com/ispamm/QWT.
Authors: Zhengqi Gao, Fan-Keng Sun, Duane S. Boning
In this paper, we exploit a fundamental principle of analog electronic circuitry, Kirchhoff's current law, to introduce a unique class of neural network models that we refer to as KirchhoffNet. KirchhoffNet establishes close connections with message passing neural networks and continuous-depth networks. We demonstrate that even in the absence of any traditional layers (such as convolution, pooling, or linear layers), KirchhoffNet attains 98.86% test accuracy on the MNIST dataset, comparable with state of the art (SOTA) results. What makes KirchhoffNet more intriguing is its potential in the realm of hardware. Contemporary deep neural networks are conventionally deployed on GPUs. In contrast, KirchhoffNet can be physically realized by an analog electronic circuit. Moreover, we justify that irrespective of the number of parameters within a KirchhoffNet, its forward calculation can always be completed within 1/f seconds, with f representing the hardware's clock frequency. This characteristic introduces a promising technology for implementing ultra-large-scale neural networks.
Authors: R. Alawadhi, D. Angella, A. Leonardo, T. Schettini Gherardini
We construct all possible complete intersection Calabi-Yau five-folds in a product of four or less complex projective spaces, with up to four constraints. We obtain $27068$ spaces, which are not related by permutations of rows and columns of the configuration matrix, and determine the Euler number for all of them. Excluding the $3909$ product manifolds among those, we calculate the cohomological data for $12433$ cases, i.e. $53.7 \%$ of the non-product spaces, obtaining $2375$ different Hodge diamonds. The dataset containing all the above information is available at https://www.dropbox.com/scl/fo/z7ii5idt6qxu36e0b8azq/h?rlkey=0qfhx3tykytduobpld510gsfy&dl=0 . The distributions of the invariants are presented, and a comparison with the lower-dimensional analogues is discussed. Supervised machine learning is performed on the cohomological data, via classifier and regressor (both fully connected and convolutional) neural networks. We find that $h^{1,1}$ can be learnt very efficiently, with very high $R^2$ score and an accuracy of $96\%$, i.e. $96 \%$ of the predictions exactly match the correct values. For $h^{1,4},h^{2,3}, \eta$, we also find very high $R^2$ scores, but the accuracy is lower, due to the large ranges of possible values.
Authors: Liang Zhang, Junchi Yang, Amin Karbasi, Niao He
Algorithmic reproducibility measures the deviation in outputs of machine learning algorithms upon minor changes in the training process. Previous work suggests that first-order methods would need to trade-off convergence rate (gradient complexity) for better reproducibility. In this work, we challenge this perception and demonstrate that both optimal reproducibility and near-optimal convergence guarantees can be achieved for smooth convex minimization and smooth convex-concave minimax problems under various error-prone oracle settings. Particularly, given the inexact initialization oracle, our regularization-based algorithms achieve the best of both worlds - optimal reproducibility and near-optimal gradient complexity - for minimization and minimax optimization. With the inexact gradient oracle, the near-optimal guarantees also hold for minimax optimization. Additionally, with the stochastic gradient oracle, we show that stochastic gradient descent ascent is optimal in terms of both reproducibility and gradient complexity. We believe our results contribute to an enhanced understanding of the reproducibility-convergence trade-off in the context of convex optimization.
Authors: Zhicheng Yang, Yiwei Wang, Yinya Huang, Jing Xiong, Xiaodan Liang, Jing Tang
In-context learning (ICL) with large language models (LLMs) has become the modern tools of choice for many natural language processing tasks. However, how the text style of in-context examples influences the performance of LLMs still remains under-explored. This paper presents a novel and effective approach, named \textbf{AlignedCoT}, to improve the reasoning capability of LLMs by aligning the in-context examples with the native style of LLMs.''Native'' refers to the inherent characteristic of LLMs which can be probed by zero-shot scenarios.AlignedCoT is widely applicable to ICL methods, making it easy to combine with state-of-the-art techniques to further improve the LLMs' performance. We conduct extensive and comprehensive experiments on several benchmarks on mathematical question-answering, common-sense reasoning, and text understanding. The empirical results demonstrate that our AlignedCoT significantly improves performance over the carefully handcrafted demonstrations. Specifically, with AlignedCoT, we observe an average +3.2\% improvement for \texttt{gpt-3.5-turbo} compared to the carefully handcrafted CoT on multi-step reasoning benchmarks.Furthermore, we use AlignedCoT to rewrite the CoT text style in the training set, which improves the performance of Retrieval Augmented Generation by 3.6\%.The source code and dataset is available at https://github.com/yangzhch6/AlignedCoT
Authors: Mohammad Dehghani, Zahra Yazdanparast, Rasoul Samani
COVID-19 continues to be considered an endemic disease in spite of the World Health Organization's declaration that the pandemic is over. This pandemic has disrupted people's lives in unprecedented ways and caused widespread morbidity and mortality. As a result, it is important for emergency physicians to identify patients with a higher mortality risk in order to prioritize hospital equipment, especially in areas with limited medical services. The collected data from patients is beneficial to predict the outcome of COVID-19 cases, although there is a question about which data makes the most accurate predictions. Therefore, this study aims to accomplish two main objectives. First, we want to examine whether deep learning algorithms can predict a patient's morality. Second, we investigated the impact of Clinical and RT-PCR on prediction to determine which one is more reliable. We defined four stages with different feature sets and used interpretable deep learning methods to build appropriate model. Based on results, the deep neural decision forest performed the best across all stages and proved its capability to predict the recovery and death of patients. Additionally, results indicate that Clinical alone (without the use of RT-PCR) is the most effective method of diagnosis, with an accuracy of 80%. It is important to document and understand experiences from the COVID-19 pandemic in order to aid future medical efforts. This study can provide guidance for medical professionals in the event of a crisis or outbreak similar to COVID-19.
Authors: Vincent Dumoulin, Daniel D. Johnson, Pablo Samuel Castro, Hugo Larochelle, Yann Dauphin
Learning from human feedback (LHF) -- and in particular learning from pairwise preferences -- has recently become a crucial ingredient in training large language models (LLMs), and has been the subject of much research. Most recent works frame it as a reinforcement learning problem, where a reward function is learned from pairwise preference data and the LLM is treated as a policy which is adapted to maximize the rewards, often under additional regularization constraints. We propose an alternative interpretation which centers on the generative process for pairwise preferences and treats LHF as a density estimation problem. We provide theoretical and empirical results showing that for a family of generative processes defined via preference behavior distribution equations, training a reward function on pairwise preferences effectively models an annotator's implicit preference distribution. Finally, we discuss and present findings on "annotator misspecification" -- failure cases where wrong modeling assumptions are made about annotator behavior, resulting in poorly-adapted models -- suggesting that approaches that learn from pairwise human preferences could have trouble learning from a population of annotators with diverse viewpoints.
Authors: Fanfei Meng, Lele Zhang, Yu Chen, Yuxin Wang
Federated learning (FL) is an emerging paradigm for decentralized training of machine learning models on distributed clients, without revealing the data to the central server. The learning scheme may be horizontal, vertical or hybrid (both vertical and horizontal). Most existing research work with deep neural network (DNN) modelling is focused on horizontal data distributions, while vertical and hybrid schemes are much less studied. In this paper, we propose a generalized algorithm FedEmb, for modelling vertical and hybrid DNN-based learning. The idea of our algorithm is characterised by higher inference accuracy, stronger privacy-preserving properties, and lower client-server communication bandwidth demands as compared with existing work. The experimental results show that FedEmb is an effective method to tackle both split feature & subject space decentralized problems, shows 0.3% to 4.2% inference accuracy improvement with limited privacy revealing for datasets stored in local clients, and reduces 88.9 % time complexity over vertical baseline method.
Authors: Fanfei Meng, Lele Zhang, Yu Chen, Yuxin Wang
Transformer requires a fixed number of layers and heads which makes them inflexible to the complexity of individual samples and expensive in training and inference. To address this, we propose a sample-based Dynamic Hierarchical Transformer (DHT) model whose layers and heads can be dynamically configured with single data samples via solving contextual bandit problems. To determine the number of layers and heads, we use the Uniform Confidence Bound while we deploy combinatorial Thompson Sampling in order to select specific head combinations given their number. Different from previous work that focuses on compressing trained networks for inference only, DHT is not only advantageous for adaptively optimizing the underlying network architecture during training but also has a flexible network for efficient inference. To the best of our knowledge, this is the first comprehensive data-driven dynamic transformer without any additional auxiliary neural networks that implement the dynamic system. According to the experiment results, we achieve up to 74% computational savings for both training and inference with a minimal loss of accuracy.
Authors: Haojie Pan, Zepeng Zhai, Hao Yuan, Yaojia Lv, Ruiji Fu, Ming Liu, Zhongyuan Wang, Bing Qin
Driven by curiosity, humans have continually sought to explore and understand the world around them, leading to the invention of various tools to satiate this inquisitiveness. Despite not having the capacity to process and memorize vast amounts of information in their brains, humans excel in critical thinking, planning, reflection, and harnessing available tools to interact with and interpret the world, enabling them to find answers efficiently. The recent advancements in large language models (LLMs) suggest that machines might also possess the aforementioned human-like capabilities, allowing them to exhibit powerful abilities even with a constrained parameter count. In this paper, we introduce KwaiAgents, a generalized information-seeking agent system based on LLMs. Within KwaiAgents, we propose an agent system that employs LLMs as its cognitive core, which is capable of understanding a user's query, behavior guidelines, and referencing external documents. The agent can also update and retrieve information from its internal memory, plan and execute actions using a time-aware search-browse toolkit, and ultimately provide a comprehensive response. We further investigate the system's performance when powered by LLMs less advanced than GPT-4, and introduce the Meta-Agent Tuning (MAT) framework, designed to ensure even an open-sourced 7B or 13B model performs well among many agent systems. We exploit both benchmark and human evaluations to systematically validate these capabilities. Extensive experiments show the superiority of our agent system compared to other autonomous agents and highlight the enhanced generalized agent-abilities of our fine-tuned LLMs.
Authors: Mohsin Hasan, Guojun Zhang, Kaiyang Guo, Xi Chen, Pascal Poupart
Federated Learning (FL) involves training a model over a dataset distributed among clients, with the constraint that each client's dataset is localized and possibly heterogeneous. In FL, small and noisy datasets are common, highlighting the need for well-calibrated models that represent the uncertainty of predictions. The closest FL techniques to achieving such goals are the Bayesian FL methods which collect parameter samples from local posteriors, and aggregate them to approximate the global posterior. To improve scalability for larger models, one common Bayesian approach is to approximate the global predictive posterior by multiplying local predictive posteriors. In this work, we demonstrate that this method gives systematically overconfident predictions, and we remedy this by proposing $\beta$-Predictive Bayes, a Bayesian FL algorithm that interpolates between a mixture and product of the predictive posteriors, using a tunable parameter $\beta$. This parameter is tuned to improve the global ensemble's calibration, before it is distilled to a single model. Our method is evaluated on a variety of regression and classification datasets to demonstrate its superiority in calibration to other baselines, even as data heterogeneity increases. Code available at https://github.com/hasanmohsin/betaPredBayesFL
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: Zheng Zhang, Sirui Li, Jingcheng Zhou, Junxiang Wang, Abhinav Angirekula, Allen Zhang, Liang Zhao
Spatial networks are networks whose graph topology is constrained by their embedded spatial space. Understanding the coupled spatial-graph properties is crucial for extracting powerful representations from spatial networks. Therefore, merely combining individual spatial and network representations cannot reveal the underlying interaction mechanism of spatial networks. Besides, existing spatial network representation learning methods can only consider networks embedded in Euclidean space, and can not well exploit the rich geometric information carried by irregular and non-uniform non-Euclidean space. In order to address this issue, in this paper we propose a novel generic framework to learn the representation of spatial networks that are embedded in non-Euclidean manifold space. Specifically, a novel message-passing-based neural network is proposed to combine graph topology and spatial geometry, where spatial geometry is extracted as messages on the edges. We theoretically guarantee that the learned representations are provably invariant to important symmetries such as rotation or translation, and simultaneously maintain sufficient ability in distinguishing different geometric structures. The strength of our proposed method is demonstrated through extensive experiments on both synthetic and real-world datasets.
Authors: Yao Rong, Peizhu Qian, Vaibhav Unhelkar, Enkelejda Kasneci
Effectively explaining decisions of black-box machine learning models is critical to responsible deployment of AI systems that rely on them. Recognizing their importance, the field of explainable AI (XAI) provides several techniques to generate these explanations. Yet, there is relatively little emphasis on the user (the explainee) in this growing body of work and most XAI techniques generate "one-size-fits-all" explanations. To bridge this gap and achieve a step closer towards human-centered XAI, we present I-CEE, a framework that provides Image Classification Explanations tailored to User Expertise. Informed by existing work, I-CEE explains the decisions of image classification models by providing the user with an informative subset of training data (i.e., example images), corresponding local explanations, and model decisions. However, unlike prior work, I-CEE models the informativeness of the example images to depend on user expertise, resulting in different examples for different users. We posit that by tailoring the example set to user expertise, I-CEE can better facilitate users' understanding and simulatability of the model. To evaluate our approach, we conduct detailed experiments in both simulation and with human participants (N = 100) on multiple datasets. Experiments with simulated users show that I-CEE improves users' ability to accurately predict the model's decisions (simulatability) compared to baselines, providing promising preliminary results. Experiments with human participants demonstrate that our method significantly improves user simulatability accuracy, highlighting the importance of human-centered XAI
Authors: Bao Nguyen, Binh Nguyen, Viet Anh Nguyen
Flow matching is a powerful framework for generating high-quality samples in various applications, especially image synthesis. However, the intensive computational demands of these models, especially during the fine-tuning process and sampling processes, pose significant challenges for low-resource scenarios. This paper introduces Bellman Optimal Step-size Straightening (BOSS) technique for distilling flow-matching generative models: it aims specifically for a few-step efficient image sampling while adhering to a computational budget constraint. First, this technique involves a dynamic programming algorithm that optimizes the step sizes of the pretrained network. Then, it refines the velocity network to match the optimal step sizes, aiming to straighten the generation paths. Extensive experimental evaluations across image generation tasks demonstrate the efficacy of BOSS in terms of both resource utilization and image quality. Our results reveal that BOSS achieves substantial gains in efficiency while maintaining competitive sample quality, effectively bridging the gap between low-resource constraints and the demanding requirements of flow-matching generative models. Our paper also fortifies the responsible development of artificial intelligence, offering a more sustainable generative model that reduces computational costs and environmental footprints. Our code can be found at https://github.com/nguyenngocbaocmt02/BOSS.
Authors: Kaitlyn Wang, Yufang Jin
Effective monitoring of walnut water status and stress level across the whole orchard is an essential step towards precision irrigation management of walnuts, a significant crop in California. This study presents a machine learning approach using Random Forest (RF) models to map stem water potential (SWP) by integrating high-resolution multispectral remote sensing imagery from Unmanned Aerial Vehicle (UAV) flights with weather data. From 2017 to 2018, five flights of an UAV equipped with a seven-band multispectral camera were conducted over a commercial walnut orchard, paired with concurrent ground measurements of sampled walnut plants. The RF regression model, utilizing vegetation indices derived from orthomosaiced UAV imagery and weather data, effectively estimated ground-measured SWPs, achieving an $R^2$ of 0.63 and a mean absolute error (MAE) of 0.80 bars. The integration of weather data was particularly crucial for consolidating data across various flight dates. Significant variables for SWP estimation included wind speed and vegetation indices such as NDVI, NDRE, and PSRI.A reduced RF model excluding red-edge indices of NDRE and PSRI, demonstrated slightly reduced accuracy ($R^2$ = 0.54). Additionally, the RF classification model predicted water stress levels in walnut trees with 85% accuracy, surpassing the 80% accuracy of the reduced classification model. The results affirm the efficacy of UAV-based multispectral imaging combined with machine learning, incorporating thermal data, NDVI, red-edge indices, and weather data, in walnut water stress estimation and assessment. This methodology offers a scalable, cost-effective tool for data-driven precision irrigation management at an individual plant level in walnut orchards.
Authors: Kaixuan Chen, Wei Luo, Shunyu Liu, Yaoquan Wei, Yihe Zhou, Yunpeng Qing, Quan Zhang, Jie Song, Mingli Song
In this paper, we present a novel transformer architecture tailored for learning robust power system state representations, which strives to optimize power dispatch for the power flow adjustment across different transmission sections. Specifically, our proposed approach, named Powerformer, develops a dedicated section-adaptive attention mechanism, separating itself from the self-attention used in conventional transformers. This mechanism effectively integrates power system states with transmission section information, which facilitates the development of robust state representations. Furthermore, by considering the graph topology of power system and the electrical attributes of bus nodes, we introduce two customized strategies to further enhance the expressiveness: graph neural network propagation and multi-factor attention mechanism. Extensive evaluations are conducted on three power system scenarios, including the IEEE 118-bus system, a realistic 300-bus system in China, and a large-scale European system with 9241 buses, where Powerformer demonstrates its superior performance over several baseline methods.
Authors: Arundhati Banerjee, Jeff Schneider
Multi-agent multi-target tracking has a wide range of applications, including wildlife patrolling, security surveillance or environment monitoring. Such algorithms often make restrictive assumptions: the number of targets and/or their initial locations may be assumed known, or agents may be pre-assigned to monitor disjoint partitions of the environment, reducing the burden of exploration. This also limits applicability when there are fewer agents than targets, since agents are unable to continuously follow the targets in their fields of view. Multi-agent tracking algorithms additionally assume inter-agent synchronization of observations, or the presence of a central controller to coordinate joint actions. Instead, we focus on the setting of decentralized multi-agent, multi-target, simultaneous active search-and-tracking with asynchronous inter-agent communication. Our proposed algorithm DecSTER uses a sequential monte carlo implementation of the probability hypothesis density filter for posterior inference combined with Thompson sampling for decentralized multi-agent decision making. We compare different action selection policies, focusing on scenarios where targets outnumber agents. In simulation, we demonstrate that DecSTER is robust to unreliable inter-agent communication and outperforms information-greedy baselines in terms of the Optimal Sub-Pattern Assignment (OSPA) metric for different numbers of targets and varying teamsizes.
Authors: Zilin Huang, Zihao Sheng, Chengyuan Ma, Sikai Chen
Despite significant progress in autonomous vehicles (AVs), the development of driving policies that ensure both the safety of AVs and traffic flow efficiency has not yet been fully explored. In this paper, we propose an enhanced human-in-the-loop reinforcement learning method, termed the Human as AI mentor-based deep reinforcement learning (HAIM-DRL) framework, which facilitates safe and efficient autonomous driving in mixed traffic platoon. Drawing inspiration from the human learning process, we first introduce an innovative learning paradigm that effectively injects human intelligence into AI, termed Human as AI mentor (HAIM). In this paradigm, the human expert serves as a mentor to the AI agent. While allowing the agent to sufficiently explore uncertain environments, the human expert can take control in dangerous situations and demonstrate correct actions to avoid potential accidents. On the other hand, the agent could be guided to minimize traffic flow disturbance, thereby optimizing traffic flow efficiency. In detail, HAIM-DRL leverages data collected from free exploration and partial human demonstrations as its two training sources. Remarkably, we circumvent the intricate process of manually designing reward functions; instead, we directly derive proxy state-action values from partial human demonstrations to guide the agents' policy learning. Additionally, we employ a minimal intervention technique to reduce the human mentor's cognitive load. Comparative results show that HAIM-DRL outperforms traditional methods in driving safety, sampling efficiency, mitigation of traffic flow disturbance, and generalizability to unseen traffic scenarios. The code and demo videos for this paper can be accessed at: https://zilin-huang.github.io/HAIM-DRL-website/
Authors: Sina Ehsani, Elina Sergeeva, Wendy Murdy, Benjamin Fox
Accurate prediction of flight-level passenger traffic is of paramount importance in airline operations, influencing key decisions from pricing to route optimization. This study introduces a novel, multimodal deep learning approach to the challenge of predicting flight-level passenger traffic, yielding substantial accuracy improvements compared to traditional models. Leveraging an extensive dataset from American Airlines, our model ingests historical traffic data, fare closure information, and seasonality attributes specific to each flight. Our proposed neural network integrates the strengths of Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN), exploiting the temporal patterns and spatial relationships within the data to enhance prediction performance. Crucial to the success of our model is a comprehensive data processing strategy. We construct 3D tensors to represent data, apply careful masking strategies to mirror real-world dynamics, and employ data augmentation techniques to enrich the diversity of our training set. The efficacy of our approach is borne out in the results: our model demonstrates an approximate 33\% improvement in Mean Squared Error (MSE) compared to traditional benchmarks. This study, therefore, highlights the significant potential of deep learning techniques and meticulous data processing in advancing the field of flight traffic prediction.
Authors: Chen Yang, Peng Liang, Zinan Ma
Stakeholders constantly make assumptions in the development of deep learning (DL) frameworks. These assumptions are related to various types of software artifacts (e.g., requirements, design decisions, and technical debt) and can turn out to be invalid, leading to system failures. Existing approaches and tools for assumption management usually depend on manual identification of assumptions. However, assumptions are scattered in various sources (e.g., code comments, commits, pull requests, and issues) of DL framework development, and manually identifying assumptions has high costs (e.g., time and resources). To overcome the issues of manually identifying assumptions in DL framework development, we constructed a new and largest dataset (i.e., AssuEval) of assumptions collected from the TensorFlow and Keras repositories on GitHub; explored the performance of seven traditional machine learning models (e.g., Support Vector Machine, Classification and Regression Trees), a popular DL model (i.e., ALBERT), and a large language model (i.e., ChatGPT) of identifying assumptions on the AssuEval dataset. The experiment results show that: ALBERT achieves the best performance (f1-score: 0.9584) of identifying assumptions on the AssuEval dataset, which is much better than the other models (the 2nd best f1-score is 0.6211, achieved by ChatGPT). Though ChatGPT is the most popular large language model, we do not recommend using it to identify assumptions in DL framework development because of its low performance on the task. Fine-tuning ChatGPT specifically for assumption identification could improve the performance. This study provides researchers with the largest dataset of assumptions for further research (e.g., assumption classification, evaluation, and reasoning) and helps practitioners better understand assumptions and how to manage them in their projects.
Authors: Masahiro Kato, Kyohei Okumura, Takuya Ishihara, Toru Kitagawa
Evidence-based targeting has been a topic of growing interest among the practitioners of policy and business. Formulating decision-maker's policy learning as a fixed-budget best arm identification (BAI) problem with contextual information, we study an optimal adaptive experimental design for policy learning with multiple treatment arms. In the sampling stage, the planner assigns treatment arms adaptively over sequentially arriving experimental units upon observing their contextual information (covariates). After the experiment, the planner recommends an individualized assignment rule to the population. Setting the worst-case expected regret as the performance criterion of adaptive sampling and recommended policies, we derive its asymptotic lower bounds, and propose a strategy, Adaptive Sampling-Policy Learning strategy (PLAS), whose leading factor of the regret upper bound aligns with the lower bound as the size of experimental units increases.
Authors: Simisola Odimayo, Chollette C. Olisah, Khadija Mohammed
Alzheimer's disease (AD), the predominant form of dementia, poses a growing global challenge and underscores the urgency of accurate and early diagnosis. The clinical technique radiologists adopt for distinguishing between mild cognitive impairment (MCI) and AD using Machine Resonance Imaging (MRI) encounter hurdles because they are not consistent and reliable. Machine learning has been shown to offer promise for early AD diagnosis. However, existing models focused on focal fine-grain features without considerations to focal structural features that give off information on neurodegeneration of the brain cerebral cortex. Therefore, this paper proposes a machine learning (ML) framework that integrates Gamma correction, an image enhancement technique, and includes a structure-focused neurodegeneration convolutional neural network (CNN) architecture called SNeurodCNN for discriminating between AD and MCI. The ML framework leverages the mid-sagittal and para-sagittal brain image viewpoints of the structure-focused Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Through experiments, our proposed machine learning framework shows exceptional performance. The parasagittal viewpoint set achieves 97.8% accuracy, with 97.0% specificity and 98.5% sensitivity. The midsagittal viewpoint is shown to present deeper insights into the structural brain changes given the increase in accuracy, specificity, and sensitivity, which are 98.1% 97.2%, and 99.0%, respectively. Using GradCAM technique, we show that our proposed model is capable of capturing the structural dynamics of MCI and AD which exist about the frontal lobe, occipital lobe, cerebellum, and parietal lobe. Therefore, our model itself as a potential brain structural change Digi-Biomarker for early diagnosis of AD.
Authors: Xiangyu Chang, Sk Miraj Ahmed, Srikanth V. Krishnamurthy, Basak Guler, Ananthram Swami, Samet Oymak, Amit K. Roy-Chowdhury
Parameter-efficient tuning (PET) methods such as LoRA, Adapter, and Visual Prompt Tuning (VPT) have found success in enabling adaptation to new domains by tuning small modules within a transformer model. However, the number of domains encountered during test time can be very large, and the data is usually unlabeled. Thus, adaptation to new domains is challenging; it is also impractical to generate customized tuned modules for each such domain. Toward addressing these challenges, this work introduces PLUTO: a Plug-and-pLay modUlar Test-time domain adaptatiOn strategy. We pre-train a large set of modules, each specialized for different source domains, effectively creating a ``module store''. Given a target domain with few-shot unlabeled data, we introduce an unsupervised test-time adaptation (TTA) method to (1) select a sparse subset of relevant modules from this store and (2) create a weighted combination of selected modules without tuning their weights. This plug-and-play nature enables us to harness multiple most-relevant source domains in a single inference call. Comprehensive evaluations demonstrate that PLUTO uniformly outperforms alternative TTA methods and that selecting $\leq$5 modules suffice to extract most of the benefit. At a high level, our method equips pre-trained transformers with the capability to dynamically adapt to new domains, motivating a new paradigm for efficient and scalable domain adaptation.
Authors: Ke Zhang, Lichao Sun, Bolin Ding, Siu Ming Yiu, Carl Yang
Behemoth graphs are often fragmented and separately stored by multiple data owners as distributed subgraphs in many realistic applications. Without harming data privacy, it is natural to consider the subgraph federated learning (subgraph FL) scenario, where each local client holds a subgraph of the entire global graph, to obtain globally generalized graph mining models. To overcome the unique challenge of incomplete information propagation on local subgraphs due to missing cross-subgraph neighbors, previous works resort to the augmentation of local neighborhoods through the joint FL of missing neighbor generators and GNNs. Yet their technical designs have profound limitations regarding the utility, efficiency, and privacy goals of FL. In this work, we propose FedDEP to comprehensively tackle these challenges in subgraph FL. FedDEP consists of a series of novel technical designs: (1) Deep neighbor generation through leveraging the GNN embeddings of potential missing neighbors; (2) Efficient pseudo-FL for neighbor generation through embedding prototyping; and (3) Privacy protection through noise-less edge-local-differential-privacy. We analyze the correctness and efficiency of FedDEP, and provide theoretical guarantees on its privacy. Empirical results on four real-world datasets justify the clear benefits of proposed techniques.
Authors: Mahdi Nikdan, Soroush Tabesh, Dan Alistarh
We investigate parameter-efficient fine-tuning (PEFT) methods that can provide good accuracy under limited computational and memory budgets in the context of large language models (LLMs). We present a new PEFT method called Robust Adaptation (RoSA) inspired by robust principal component analysis (PCA) that jointly trains $\textit{low-rank}$ and $\textit{highly-sparse}$ components on top of a set of fixed pretrained weights to efficiently approximate the performance of a full-fine-tuning (FFT) solution. Across a series of challenging generative tasks such as grade-school math and SQL query generation, which require fine-tuning for good performance, we show that RoSA outperforms both LoRA and pure sparse fine-tuning, at the same parameter budget. We provide system support for RoSA to complement the training algorithm, specifically in the form of sparse GPU kernels which enable memory- and computationally-efficient training. Our code will be made available at https://github.com/IST-DASLab/RoSA}
Authors: Violaine Courrier (MODAL), Christophe Biernacki (MODAL), Cristian Preda (MODAL), Benjamin Vittrant
In healthcare, patient data is often collected as multivariate time series, providing a comprehensive view of a patient's health status over time. While this data can be sparse, connected devices may enhance its frequency. The goal is to create patient profiles from these time series. In the absence of labels, a predictive model can be used to predict future values while forming a latent cluster space, evaluated based on predictive performance. We compare two models on Withing's datasets, M AGMAC LUST which clusters entire time series and DGM${}^2$ which allows the group affiliation of an individual to change over time (dynamic clustering).