Authors: Alexander G. Ororbia
In this survey, we examine algorithms for conducting credit assignment in artificial neural networks that are inspired or motivated by neurobiology, unifying these various processes under one possible taxonomy. Our proposed taxonomy is constructed based on how a learning algorithm answers a central question underpinning the mechanisms of synaptic plasticity in complex adaptive neuronal systems: where do the signals that drive the learning in individual elements of a network come from and how are they produced? In this unified treatment, we organize the ever-growing set of brain-inspired learning processes into six general families and consider these in the context of backpropagation of errors and its known criticisms. The results of this review are meant to encourage future developments in neuro-mimetic systems and their constituent learning processes, wherein lies the opportunity to build a strong bridge between machine learning, computational neuroscience, and cognitive science.
Authors: José Chelotti, Luciano Martinez-Rau, Mariano Ferrero, Leandro Vignolo, Julio Galli, Alejandra Planisich, H. Leonardo Rufiner, Leonardo Giovanini
Livestock feeding behavior is an influential research area for those involved in animal husbandry and agriculture. In recent years, there has been a growing interest in automated systems for monitoring the behavior of ruminants. Despite the developments accomplished in the last decade, there is still much to do and learn about the methods for measuring and analyzing livestock feeding behavior. Automated monitoring systems mainly use motion, acoustic, and image sensors to collect animal behavioral data. The performance evaluation of existing methods is a complex task and direct comparisons between studies are difficult. Several factors prevent a direct comparison, starting from the diversity of data and performance metrics used in the experiments. To the best of our knowledge, this work represents the first tutorial-style review on the analysis of the feeding behavior of ruminants, emphasizing the relationship between sensing methodologies, signal processing and computational intelligence methods. It assesses the main sensing methodologies (i.e. based on movement, sound, images/videos and pressure) and the main techniques to measure and analyze the signals associated with feeding behavior, evaluating their use in different settings and situations. It also highlights the potentiality of automated monitoring systems to provide valuable information that improves our understanding of livestock feeding behavior. The relevance of these systems is increasingly important due to their impact on production systems and research. Finally, the paper closes by discussing future challenges and opportunities in livestock feeding behavior monitoring.
Authors: Shaocong Wang, Yizhao Gao, Yi Li, Woyu Zhang, Yifei Yu, Bo Wang, Ning Lin, Hegan Chen, Yue Zhang, Yang Jiang, Dingchen Wang, Jia Chen, Peng Dai, Hao Jiang, Peng Lin, Xumeng Zhang, Xiaojuan Qi, Xiaoxin Xu, Hayden So, Zhongrui Wang, Dashan Shang, Qi Liu, Kwang-Ting Cheng, Ming Liu
Visual sensors, including 3D LiDAR, neuromorphic DVS sensors, and conventional frame cameras, are increasingly integrated into edge-side intelligent machines. Realizing intensive multi-sensory data analysis directly on edge intelligent machines is crucial for numerous emerging edge applications, such as augmented and virtual reality and unmanned aerial vehicles, which necessitates unified data representation, unprecedented hardware energy efficiency and rapid model training. However, multi-sensory data are intrinsically heterogeneous, causing significant complexity in the system development for edge-side intelligent machines. In addition, the performance of conventional digital hardware is limited by the physically separated processing and memory units, known as the von Neumann bottleneck, and the physical limit of transistor scaling, which contributes to the slowdown of Moore's law. These limitations are further intensified by the tedious training of models with ever-increasing sizes. We propose a novel hardware-software co-design, random resistive memory-based deep extreme point learning machine (DEPLM), that offers efficient unified point set analysis. We show the system's versatility across various data modalities and two different learning tasks. Compared to a conventional digital hardware-based system, our co-design system achieves huge energy efficiency improvements and training cost reduction when compared to conventional systems. Our random resistive memory-based deep extreme point learning machine may pave the way for energy-efficient and training-friendly edge AI across various data modalities and tasks.
Authors: Marcelo Matheus Gauy, Marcelo Finger
An acoustic model, trained on a significant amount of unlabeled data, consists of a self-supervised learned speech representation useful for solving downstream tasks, perhaps after a fine-tuning of the model in the respective downstream task. In this work, we build an acoustic model of Brazilian Portuguese Speech through a Transformer neural network. This model was pretrained on more than $800$ hours of Brazilian Portuguese Speech, using a combination of pretraining techniques. Using a labeled dataset collected for the detection of respiratory insufficiency in Brazilian Portuguese speakers, we fine-tune the pretrained Transformer neural network on the following tasks: respiratory insufficiency detection, gender recognition and age group classification. We compare the performance of pretrained Transformers on these tasks with that of Transformers without previous pretraining, noting a significant improvement. In particular, the performance of respiratory insufficiency detection obtains the best reported results so far, indicating this kind of acoustic model as a promising tool for speech-as-biomarker approach. Moreover, the performance of gender recognition is comparable to the state of the art models in English.
Authors: Drew Priebe, Burooj Ghani, Dan Stowell
The ongoing biodiversity crisis, driven by factors such as land-use change and global warming, emphasizes the need for effective ecological monitoring methods. Acoustic monitoring of biodiversity has emerged as an important monitoring tool. Detecting human voices in soundscape monitoring projects is useful both for analysing human disturbance and for privacy filtering. Despite significant strides in deep learning in recent years, the deployment of large neural networks on compact devices poses challenges due to memory and latency constraints. Our approach focuses on leveraging knowledge distillation techniques to design efficient, lightweight student models for speech detection in bioacoustics. In particular, we employed the MobileNetV3-Small-Pi model to create compact yet effective student architectures to compare against the larger EcoVAD teacher model, a well-regarded voice detection architecture in eco-acoustic monitoring. The comparative analysis included examining various configurations of the MobileNetV3-Small-Pi derived student models to identify optimal performance. Additionally, a thorough evaluation of different distillation techniques was conducted to ascertain the most effective method for model selection. Our findings revealed that the distilled models exhibited comparable performance to the EcoVAD teacher model, indicating a promising approach to overcoming computational barriers for real-time ecological monitoring.
Authors: Mohammad Samragh, Mehrdad Farajtabar, Sachin Mehta, Raviteja Vemulapalli, Fartash Faghri, Devang Naik, Oncel Tuzel, Mohammad Rastegari
Training large transformer models from scratch for a target task requires lots of data and is computationally demanding. The usual practice of transfer learning overcomes this challenge by initializing the model with weights of a pretrained model of the same size and specification to increase the convergence and training speed. However, what if no pretrained model of the required size is available? In this paper, we introduce a simple yet effective technique to transfer the knowledge of a pretrained model to smaller variants. Our approach called weight subcloning expedites the training of scaled-down transformers by initializing their weights from larger pretrained models.
Weight subcloning involves an operation on the pretrained model to obtain the equivalent initialized scaled-down model. It consists of two key steps: first, we introduce neuron importance ranking to decrease the embedding dimension per layer in the pretrained model. Then, we remove blocks from the transformer model to match the number of layers in the scaled-down network. The result is a network ready to undergo training, which gains significant improvements in training speed compared to random initialization. For instance, we achieve 4x faster training for vision transformers in image classification and language models designed for next token prediction.
Authors: Jie Ren, Yao Zhao, Tu Vu, Peter J. Liu, Balaji Lakshminarayanan
Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate. While likelihood-based metrics such as perplexity are widely employed, recent research has demonstrated the limitations of using sequence-level probability estimates given by LLMs as reliable indicators of generation quality. Conversely, LLMs have demonstrated strong calibration at the token level, particularly when it comes to choosing correct answers in multiple-choice questions or evaluating true/false statements. In this work, we reformulate open-ended generation tasks into token-level prediction tasks, and leverage LLMs' superior calibration at the token level. We instruct an LLM to self-evaluate its answers, employing either a multi-way comparison or a point-wise evaluation approach, with the option to include a ``None of the above'' option to express the model's uncertainty explicitly. We benchmark a range of scoring methods based on self-evaluation and evaluate their performance in selective generation using TruthfulQA and TL;DR. Through experiments with PaLM-2 and GPT-3, we demonstrate that self-evaluation based scores not only improve accuracy, but also correlate better with the overall quality of generated content.
Authors: Lysimachos Maltoudoglou, Andreas Paisios, Ladislav Lenc, Jiří Martínek, Pavel Král, Harris Papadopoulos
We extend our previous work on Inductive Conformal Prediction (ICP) for multi-label text classification and present a novel approach for addressing the computational inefficiency of the Label Powerset (LP) ICP, arrising when dealing with a high number of unique labels. We present experimental results using the original and the proposed efficient LP-ICP on two English and one Czech language data-sets. Specifically, we apply the LP-ICP on three deep Artificial Neural Network (ANN) classifiers of two types: one based on contextualised (bert) and two on non-contextualised (word2vec) word-embeddings. In the LP-ICP setting we assign nonconformity scores to label-sets from which the corresponding p-values and prediction-sets are determined. Our approach deals with the increased computational burden of LP by eliminating from consideration a significant number of label-sets that will surely have p-values below the specified significance level. This reduces dramatically the computational complexity of the approach while fully respecting the standard CP guarantees. Our experimental results show that the contextualised-based classifier surpasses the non-contextualised-based ones and obtains state-of-the-art performance for all data-sets examined. The good performance of the underlying classifiers is carried on to their ICP counterparts without any significant accuracy loss, but with the added benefits of ICP, i.e. the confidence information encapsulated in the prediction sets. We experimentally demonstrate that the resulting prediction sets can be tight enough to be practically useful even though the set of all possible label-sets contains more than $1e+16$ combinations. Additionally, the empirical error rates of the obtained prediction-sets confirm that our outputs are well-calibrated.
Authors: Micah Goldblum, Anima Anandkumar, Richard Baraniuk, Tom Goldstein, Kyunghyun Cho, Zachary C Lipton, Melanie Mitchell, Preetum Nakkiran, Max Welling, Andrew Gordon Wilson
The goal of this series is to chronicle opinions and issues in the field of machine learning as they stand today and as they change over time. The plan is to host this survey periodically until the AI singularity paperclip-frenzy-driven doomsday, keeping an updated list of topical questions and interviewing new community members for each edition. In this issue, we probed people's opinions on interpretable AI, the value of benchmarking in modern NLP, the state of progress towards understanding deep learning, and the future of academia.
Authors: Stephen Pasteris, Chris Hicks, Vasilios Mavroudis
In this paper we consider the adversarial contextual bandit problem in metric spaces. The paper "Nearest neighbour with bandit feedback" tackled this problem but when there are many contexts near the decision boundary of the comparator policy it suffers from a high regret. In this paper we eradicate this problem, designing an algorithm in which we can hold out any set of contexts when computing our regret term. Our algorithm builds on that of "Nearest neighbour with bandit feedback" and hence inherits its extreme computational efficiency.
Authors: Sahil Nokhwal, Nirman Kumar
We propose a novel exemplar selection approach based on Principal Component Analysis (PCA) and median sampling, and a neural network training regime in the setting of class-incremental learning. This approach avoids the pitfalls due to outliers in the data and is both simple to implement and use across various incremental machine learning models. It also has independent usage as a sampling algorithm. We achieve better performance compared to state-of-the-art methods.
Authors: Xenofon Vasilakos, Shadi Moazzeni, Anderson Bravalheri, Pratchaya Jaisudthi, Reza Nejabati, Dimitra Simeonidou
Leveraging the potential of Virtualised Network Functions (VNFs) requires a clear understanding of the link between resource consumption and performance. The current state of the art tries to do that by utilising Machine Learning (ML) and specifically Supervised Learning (SL) models for given network environments and VNF types assuming single-objective optimisation targets. Taking a different approach poses a novel VNF profiler optimising multi-resource type allocation and performance objectives using adapted Reinforcement Learning (RL). Our approach can meet Key Performance Indicator (KPI) targets while minimising multi-resource type consumption and optimising the VNF output rate compared to existing single-objective solutions. Our experimental evaluation with three real-world VNF types over a total of 39 study scenarios (13 per VNF), for three resource types (virtual CPU, memory, and network link capacity), verifies the accuracy of resource allocation predictions and corresponding successful profiling decisions via a benchmark comparison between our RL model and SL models. We also conduct a complementary exhaustive search-space study revealing that different resources impact performance in varying ways per VNF type, implying the necessity of multi-objective optimisation, individualised examination per VNF type, and adaptable online profile learning, such as with the autonomous online learning approach of iOn-Profiler.
Authors: Sahil Nokhwal, Nirman Kumar
Rehearsal-based techniques are commonly used to mitigate catastrophic forgetting (CF) in Incremental learning (IL). The quality of the exemplars selected is important for this purpose and most methods do not ensure the appropriate diversity of the selected exemplars. We propose a new technique "DSS" -- Diverse Selection of Samples from the input data stream in the Class-incremental learning (CIL) setup under both disjoint and fuzzy task boundary scenarios. Our method outperforms state-of-the-art methods and is much simpler to understand and implement.
Authors: Sahil Nokhwal, Nirman Kumar
Catastrophic forgetting(CF) is a significant challenge in continual learning (CL). In regularization-based approaches to mitigate CF, modifications to important training parameters are penalized in subsequent tasks using an appropriate loss function. We propose the RTRA, a modification to the widely used Elastic Weight Consolidation (EWC) regularization scheme, using the Natural Gradient for loss function optimization. Our approach improves the training of regularization-based methods without sacrificing test-data performance. We compare the proposed RTRA approach against EWC using the iFood251 dataset. We show that RTRA has a clear edge over the state-of-the-art approaches.
Authors: Xi Chen, Chang Gao, Zuowen Wang, Longbiao Cheng, Sheng Zhou, Shih-Chii Liu, Tobi Delbruck
Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses. Implementing online training of RNNs on the edge calls for optimized algorithms for an efficient deployment on hardware. Inspired by the spiking neuron model, the Delta RNN exploits temporal sparsity during inference by skipping over the update of hidden states from those inactivated neurons whose change of activation across two timesteps is below a defined threshold. This work describes a training algorithm for Delta RNNs that exploits temporal sparsity in the backward propagation phase to reduce computational requirements for training on the edge. Due to the symmetric computation graphs of forward and backward propagation during training, the gradient computation of inactivated neurons can be skipped. Results show a reduction of $\sim$80% in matrix operations for training a 56k parameter Delta LSTM on the Fluent Speech Commands dataset with negligible accuracy loss. Logic simulations of a hardware accelerator designed for the training algorithm show 2-10X speedup in matrix computations for an activation sparsity range of 50%-90%. Additionally, we show that the proposed Delta RNN training will be useful for online incremental learning on edge devices with limited computing resources.
Authors: Cody Rucker, Brittany A. Erickson
Direct observations of earthquake nucleation and propagation are few and yet the next decade will likely see an unprecedented increase in indirect, surface observations that must be integrated into modeling efforts. Machine learning (ML) excels in the presence of large data and is an actively growing field in seismology. However, not all ML methods incorporate rigorous physics, and purely data-driven models can predict physically unrealistic outcomes due to observational bias or extrapolation. Our work focuses on the recently emergent Physics-Informed Neural Network (PINN), which seamlessly integrates data while ensuring that model outcomes satisfy rigorous physical constraints. In this work we develop a multi-network PINN for both the forward problem as well as for direct inversion of nonlinear fault friction parameters, constrained by the physics of motion in the solid Earth, which have direct implications for assessing seismic hazard. We present the computational PINN framework for strike-slip faults in 1D and 2D subject to rate-and-state friction. Initial and boundary conditions define the data on which the PINN is trained. While the PINN is capable of approximating the solution to the governing equations to low-errors, our primary interest lies in the network's capacity to infer friction parameters during the training loop. We find that the network for the parameter inversion at the fault performs much better than the network for material displacements to which it is coupled. Additional training iterations and model tuning resolves this discrepancy, enabling a robust surrogate model for solving both forward and inverse problems relevant to seismic faulting.
Authors: Yikai Liu, Tushar K. Ghosh, Ming Chen
Biased enhanced sampling methods utilizing collective variables (CVs) are powerful tools for sampling conformational ensembles. Due to high intrinsic dimensions, efficiently generating conformational ensembles for complex systems requires enhanced sampling on high-dimensional free energy surfaces. While methods like temperature-accelerated molecular dynamics (TAMD) can adopt many CVs in a simulation, unbiasing the simulation requires accurate modeling of a high-dimensional CV probability distribution, which is challenging for traditional density estimation techniques. Here we propose an unbiasing method based on the score-based diffusion model, a deep generative learning method that excels in density estimation across complex data landscapes. We test the score-based diffusion unbiasing method on TAMD simulations. The results demonstrate that this unbiasing approach significantly outperforms traditional unbiasing methods, and can generate accurate unbiased conformational ensembles for simulations with a number of CVs higher than usual ranges.
Authors: Hadia Mecheri, Islam Benamirouche, Feriel Fass, Djemel Ziou, Nassima Kadri
In this study, we propose an approach for predicting rare events by exploiting time series in coevolution. Our approach involves a weighted autologistic regression model, where we leverage the temporal behavior of the data to enhance predictive capabilities. By addressing the issue of imbalanced datasets, we establish constraints leading to weight estimation and to improved performance. Evaluation on synthetic and real-world datasets confirms that our approach outperform state-of-the-art of predicting home equipment failure methods.
Authors: Tianyi Chen, Tianyu Ding, Zhihui Zhu, Zeyu Chen, HsiangTao Wu, Ilya Zharkov, Luming Liang
Compressing a predefined deep neural network (DNN) into a compact sub-network with competitive performance is crucial in the efficient machine learning realm. This topic spans various techniques, from structured pruning to neural architecture search, encompassing both pruning and erasing operators perspectives. Despite advancements, existing methods suffers from complex, multi-stage processes that demand substantial engineering and domain knowledge, limiting their broader applications. We introduce the third-generation Only-Train-Once (OTOv3), which first automatically trains and compresses a general DNN through pruning and erasing operations, creating a compact and competitive sub-network without the need of fine-tuning. OTOv3 simplifies and automates the training and compression process, minimizes the engineering efforts required from users. It offers key technological advancements: (i) automatic search space construction for general DNNs based on dependency graph analysis; (ii) Dual Half-Space Projected Gradient (DHSPG) and its enhanced version with hierarchical search (H2SPG) to reliably solve (hierarchical) structured sparsity problems and ensure sub-network validity; and (iii) automated sub-network construction using solutions from DHSPG/H2SPG and dependency graphs. Our empirical results demonstrate the efficacy of OTOv3 across various benchmarks in structured pruning and neural architecture search. OTOv3 produces sub-networks that match or exceed the state-of-the-arts. The source code will be available at https://github.com/tianyic/only_train_once.
Authors: Yan Pei, Jiahui Xu, Qianhao Chen, Chenhao Wang, Feng Yu, Lisan Zhang, Wei Luo
Electroencephalography (EEG) signals are easily corrupted by various artifacts, making artifact removal crucial for improving signal quality in scenarios such as disease diagnosis and brain-computer interface (BCI). In this paper, we present a fully convolutional neural architecture, called DTP-Net, which consists of a Densely Connected Temporal Pyramid (DTP) sandwiched between a pair of learnable time-frequency transformations for end-to-end electroencephalogram (EEG) denoising. The proposed method first transforms a single-channel EEG signal of arbitrary length into the time-frequency domain via an Encoder layer. Then, noises, such as ocular and muscle artifacts, are extracted by DTP in a multi-scale fashion and reduced. Finally, a Decoder layer is employed to reconstruct the artifact-reduced EEG signal. Additionally, we conduct an in-depth analysis of the representation learning behavior of each module in DTP-Net to substantiate its robustness and reliability. Extensive experiments conducted on two public semi-simulated datasets demonstrate the effective artifact removal performance of DTP-Net, which outperforms state-of-art approaches. Experimental results demonstrate cleaner waveforms and significant improvement in Signal-to-Noise Ratio (SNR) and Relative Root Mean Square Error (RRMSE) after denoised by the proposed model. Moreover, the proposed DTP-Net is applied in a specific BCI downstream task, improving the classification accuracy by up to 5.55% compared to that of the raw signals, validating its potential applications in the fields of EEG-based neuroscience and neuro-engineering.
Authors: Rajnish Kumar, Suriya Prakash Muthukrishnan, Lalan Kumar, Sitikantha Roy
In this research, we present an innovative method known as a physics-informed neural network (PINN) model to predict multi-joint kinematics using electromyography (EMG) signals recorded from the muscles surrounding these joints across various loads. The primary aim is to simultaneously predict both the shoulder and elbow joint angles while executing elbow flexion-extension (FE) movements, especially under varying load conditions. The PINN model is constructed by combining a feed-forward Artificial Neural Network (ANN) with a joint torque computation model. During the training process, the model utilizes a custom loss function derived from an inverse dynamics joint torque musculoskeletal model, along with a mean square angle loss. The training dataset for the PINN model comprises EMG and time data collected from four different subjects. To assess the model's performance, we conducted a comparison between the predicted joint angles and experimental data using a testing data set. The results demonstrated strong correlations of 58% to 83% in joint angle prediction. The findings highlight the potential of incorporating physical principles into the model, not only increasing its versatility but also enhancing its accuracy. The findings could have significant implications for the precise estimation of multi-joint kinematics in dynamic scenarios, particularly concerning the advancement of human-machine interfaces (HMIs) for exoskeletons and prosthetic control systems.
Authors: Vi Thanh Pham (1), Jonas Bille Nielsen (2), Klaus Fuglsang Kofoed (2 and 3), Jørgen Tobias Kühl (4), Andreas Kryger Jensen (1) ((1) Section of Biostatistics, Department of Public Health, Faculty of Health and Medical Sciences, University of Copenhagen, (2) Department of Cardiology and Radiology, Copenhagen University Hospital, (3) Department of Clinical Medicine, Faculty of Health and Medical Sciences, University of Copenhagen, (4) Department of Cardiology, Zealand University Hospital)
The joint alignment of multivariate functional data plays an important role in various fields such as signal processing, neuroscience and medicine, including the statistical analysis of data from wearable devices. Traditional methods often ignore the phase variability and instead focus on the variability in the observed amplitude. We present a novel method for joint alignment of multivariate quasi-periodic functions using deep neural networks, decomposing, but retaining all the information in the data by preserving both phase and amplitude variability. Our proposed neural network uses a special activation of the output that builds on the unit simplex transformation, and we utilize a loss function based on the Fisher-Rao metric to train our model. Furthermore, our method is unsupervised and can provide an optimal common template function as well as subject-specific templates. We demonstrate our method on two simulated datasets and one real example, comprising data from 12-lead 10s electrocardiogram recordings.
Authors: Dae-Hyeok Lee, Sung-Jin Kim, Si-Hyun Kim, Seong-Whan Lee
The detection of pilots' mental states is important due to the potential for their abnormal mental states to result in catastrophic accidents. This study introduces the feasibility of employing deep learning techniques to classify different workload levels, specifically normal state, low workload, and high workload. To the best of our knowledge, this study is the first attempt to classify workload levels of pilots. Our approach involves the hybrid deep neural network that consists of five convolutional blocks and one long short-term memory block to extract the significant features from electroencephalography signals. Ten pilots participated in the experiment, which was conducted within the simulated flight environment. In contrast to four conventional models, our proposed model achieved a superior grand--average accuracy of 0.8613, surpassing other conventional models by at least 0.0597 in classifying workload levels across all participants. Our model not only successfully classified workload levels but also provided valuable feedback to the participants. Hence, we anticipate that our study will make the significant contributions to the advancement of autonomous flight and driving leveraging artificial intelligence technology in the future.
Authors: Parshuram N. Aarotale, Ajita Rattani
Electrocardiograms (ECGs), a medical monitoring technology recording cardiac activity, are widely used for diagnosing cardiac arrhythmia. The diagnosis is based on the analysis of the deformation of the signal shapes due to irregular heart rates associated with heart diseases. Due to the infeasibility of manual examination of large volumes of ECG data, this paper aims to propose an automated AI based system for ECG-based arrhythmia classification. To this front, a deep learning based solution has been proposed for ECG-based arrhythmia classification. Twelve lead electrocardiograms (ECG) of length 10 sec from 45, 152 individuals from Shaoxing People's Hospital (SPH) dataset from PhysioNet with four different types of arrhythmias were used. The sampling frequency utilized was 500 Hz. Median filtering was used to preprocess the ECG signals. For every 1 sec of ECG signal, the time-frequency (TF) scalogram was estimated and stacked row wise to obtain a single image from 12 channels, resulting in 10 stacked TF scalograms for each ECG signal. These stacked TF scalograms are fed to the pretrained convolutional neural network (CNN), 1D CNN, and 1D CNN-LSTM (Long short-term memory) models, for arrhythmia classification. The fine-tuned CNN models obtained the best test accuracy of about 98% followed by 95% test accuracy by basic CNN-LSTM in arrhythmia classification.
Authors: Chih-Ning Tsai, Pei-Wen Yang, Tzu-Yen Huang, Jung-Chih Chen, Hsin-Yi Tseng, Che-Wei Wu, Amrit Sarmah, Tzu-En Lin
This study introduces an innovative 3D printed dry electrode tailored for biosensing in postoperative recovery scenarios. Fabricated through a drop coating process, the electrode incorporates a novel 2D material.
Authors: Hamza Amrani, Daniela Micucci, Paolo Napoletano
Previous research has demonstrated the potential of using pre-trained language models for decoding open vocabulary Electroencephalography (EEG) signals captured through a non-invasive Brain-Computer Interface (BCI). However, the impact of embedding EEG signals in the context of language models and the effect of subjectivity, remain unexplored, leading to uncertainty about the best approach to enhance decoding performance. Additionally, current evaluation metrics used to assess decoding effectiveness are predominantly syntactic and do not provide insights into the comprehensibility of the decoded output for human understanding. We present an end-to-end deep learning framework for non-invasive brain recordings that brings modern representational learning approaches to neuroscience. Our proposal introduces the following innovations: 1) an end-to-end deep learning architecture for open vocabulary EEG decoding, incorporating a subject-dependent representation learning module for raw EEG encoding, a BART language model, and a GPT-4 sentence refinement module; 2) a more comprehensive sentence-level evaluation metric based on the BERTScore; 3) an ablation study that analyses the contributions of each module within our proposal, providing valuable insights for future research. We evaluate our approach on two publicly available datasets, ZuCo v1.0 and v2.0, comprising EEG recordings of 30 subjects engaged in natural reading tasks. Our model achieves a BLEU-1 score of 42.75%, a ROUGE-1-F of 33.28%, and a BERTScore-F of 53.86%, outperforming the previous state-of-the-art methods by 3.38%, 8.43%, and 6.31%, respectively.
Authors: Mohsen Motie-Shirazi, Reza Sameni, Peter Rohloff, Nasim Katebi, Gari D. Clifford
In this study, we present a deep learning framework designed to integrate with our previously developed system that facilitates large-scale 1D fetal Doppler data collection, aiming to enhance data quality. This system, tailored for traditional Indigenous midwives in low-resource communities, leverages a cost-effective Android phone to improve the quality of recorded signals. We have shown that the Doppler data can be used to identify fetal growth restriction, hypertension, and other concerning issues during pregnancy. However, the quality of the signal is dependent on many factors, including radio frequency interference, position of the fetus, maternal body habitus, and usage of the Doppler by the birth attendants. In order to provide instant feedback to allow correction of the data at source, a signal quality metric is required that can run in real-time on the mobile phone.
In this study, 191 DUS signals with durations mainly in the range between 5 to 10 minutes were evaluated for quality and classified into five categories: Good, Poor, (Radiofrequency) Interference, Talking, and Silent, at a resolution of 3.75 seconds. A deep neural network was trained on each 3.75-second segment from these recordings and validated using five-fold cross-validation.
An average micro F1 = 97.4\% and macro F1 = 94.2\% were achieved, with F1 = 99.2\% for `Good' quality data. These results indicate that the algorithm, which will now be implemented in the midwives' app, should allow a significant increase in the quality of data at the time of capture.
Authors: Jung-Hoon Cho, Sirui Li, Jeongyun Kim, Cathy Wu
The recent development of connected and automated vehicle (CAV) technologies has spurred investigations to optimize dense urban traffic. This paper considers advisory autonomy, in which real-time driving advisories are issued to drivers, thus blending the CAV and the human driver. Due to the complexity of traffic systems, recent studies of coordinating CAVs have resorted to leveraging deep reinforcement learning (RL). Advisory autonomy is formalized as zero-order holds, and we consider a range of hold duration from 0.1 to 40 seconds. However, despite the similarity of the higher frequency tasks on CAVs, a direct application of deep RL fails to be generalized to advisory autonomy tasks. We introduce Temporal Transfer Learning (TTL) algorithms to select source tasks, systematically leveraging the temporal structure to solve the full range of tasks. TTL selects the most suitable source tasks to maximize the performance of the range of tasks. We validate our algorithms on diverse mixed-traffic scenarios, demonstrating that TTL more reliably solves the tasks than baselines. This paper underscores the potential of coarse-grained advisory autonomy with TTL in traffic flow optimization.
Authors: Muhammet Alkan, Gruschen Veldtman, Fani Deligianni
Congenital heart disease (CHD) is a relatively rare disease that affects patients at birth and results in extremely heterogeneous anatomical and functional defects. 12-lead ECG signal is routinely collected in CHD patients because it provides significant biomarkers for disease prognosis. However, developing accurate machine learning models is challenging due to the lack of large available datasets. Here, we suggest exploiting the Riemannian geometry of the spatial covariance structure of the ECG signal to improve classification. Firstly, we use covariance augmentation to mix samples across the Riemannian geodesic between corresponding classes. Secondly, we suggest to project the covariance matrices to their respective class Riemannian mean to enhance the quality of feature extraction via tangent space projection. We perform several ablation experiments and demonstrate significant improvement compared to traditional machine learning models and deep learning on ECG time series data.
Authors: Siyang Wu
Globally, cardiovascular diseases (CVDs) are the leading cause of mortality, accounting for an estimated 17.9 million deaths annually. One critical clinical objective is the early detection of CVDs using electrocardiogram (ECG) data, an area that has received significant attention from the research community. Recent advancements based on machine learning and deep learning have achieved great progress in this domain. However, existing methodologies exhibit inherent limitations, including inappropriate model evaluations and instances of data leakage. In this study, we present a streamlined workflow paradigm for preprocessing ECG signals into consistent 10-second durations, eliminating the need for manual feature extraction/beat detection. We also propose a hybrid model of Long Short-Term Memory (LSTM) with Support Vector Machine (SVM) for fraud detection. This architecture consists of two LSTM layers and an SVM classifier, which achieves a SOTA results with an Average precision score of 0.9402 on the MIT-BIH arrhythmia dataset and 0.9563 on the MIT-BIH atrial fibrillation dataset. Based on the results, we believe our method can significantly benefit the early detection and management of CVDs.
Authors: Tue Minh Cao, Nhat Hong Tran, Le Phi Nguyen, Hieu Huy Pham, Hung Thanh Nguyen
Our study focuses on the potential for modifications of Inception-like architecture within the electrocardiogram (ECG) domain. To this end, we introduce IncepSE, a novel network characterized by strategic architectural incorporation that leverages the strengths of both InceptionTime and channel attention mechanisms. Furthermore, we propose a training setup that employs stabilization techniques that are aimed at tackling the formidable challenges of severe imbalance dataset PTB-XL and gradient corruption. By this means, we manage to set a new height for deep learning model in a supervised learning manner across the majority of tasks. Our model consistently surpasses InceptionTime by substantial margins compared to other state-of-the-arts in this domain, noticeably 0.013 AUROC score improvement in the "all" task, while also mitigating the inherent dataset fluctuations during training.
Authors: Alberto Zancanaro, Giulia Cisotto, Italo Zoppis, Sara Lucia Manzoni
Electroencephalografic (EEG) data are complex multi-dimensional time-series that are very useful in many applications, from diagnostics to driving brain-computer interface systems. Their classification is still a challenging task, due to the inherent within- and between-subject variability and their low signal-to-noise ratio. On the other hand, the reconstruction of raw EEG data is even more difficult because of the high temporal resolution of these signals. Recent literature has proposed numerous machine and deep learning models that could classify, e.g., different types of movements, with an accuracy in the range 70% to 80% (with 4 classes). On the other hand, a limited number of works targeted the reconstruction problem, with very limited results. In this work, we propose vEEGNet, a DL architecture with two modules, i.e., an unsupervised module based on variational autoencoders to extract a latent representation of the data, and a supervised module based on a feed-forward neural network to classify different movements. To build the encoder and the decoder of VAE we exploited the well-known EEGNet network. We implemented two slightly different architectures of vEEGNet, thus showing state-of-the-art classification performance, and the ability to reconstruct both low-frequency and middle-range components of the raw EEG. Although preliminary, this work is promising as we found out that the low-frequency reconstructed signals are consistent with the so-called motor-related cortical potentials, well-known motor-related EEG patterns and we could improve over previous literature by reconstructing faster EEG components, too. Further investigations are needed to explore the potentialities of vEEGNet in reconstructing the full EEG data, generating new samples, and studying the relationship between classification and reconstruction performance.
Authors: Ivo Pascal de Jong, Andreea Ioana Sburlea, Matias Valdenegro-Toro
Uncertainty Quantification (UQ) has gained traction in an attempt to fix the black-box nature of Deep Learning. Specifically (medical) biosignals such as electroencephalography (EEG), electrocardiography (ECG), electroocculography (EOG) and electromyography (EMG) could benefit from good UQ, since these suffer from a poor signal to noise ratio, and good human interpretability is pivotal for medical applications and Brain Computer Interfaces. In this paper, we review the state of the art at the intersection of Uncertainty Quantification and Biosignal with Machine Learning. We present various methods, shortcomings, uncertainty measures and theoretical frameworks that currently exist in this application domain. Overall it can be concluded that promising UQ methods are available, but that research is needed on how people and systems may interact with an uncertainty model in a (clinical) environment.
Authors: Kang Yin, Hye-Bin Shin, Hee-Dong Kim, Seong-Whan Lee
The application of counterfactual explanation (CE) techniques in the realm of electroencephalography (EEG) classification has been relatively infrequent in contemporary research. In this study, we attempt to introduce and explore a novel non-generative approach to CE, specifically tailored for the analysis of EEG signals. This innovative approach assesses the model's decision-making process by strategically swapping patches derived from time-frequency analyses. By meticulously examining the variations and nuances introduced in the classification outcomes through this method, we aim to derive insights that can enhance interpretability. The empirical results obtained from our experimental investigations serve not only to validate the efficacy of our proposed approach but also to reinforce human confidence in the model's predictive capabilities. Consequently, these findings underscore the significance and potential value of conducting further, more extensive research in this promising direction.
Authors: Tristan Shah, Feruza Amirkulova, Stas Tiomkin
Controlling systems governed by partial differential equations is an inherently hard problem. Specifically, control of wave dynamics is challenging due to additional physical constraints and intrinsic properties of wave phenomena such as dissipation, attenuation, reflection, and scattering. In this work, we introduce an environment designed for the study of the control of acoustic waves by actuated metamaterial designs. We utilize this environment for the development of a novel machine-learning method, based on deep neural networks, for efficiently learning the dynamics of an acoustic PDE from samples. Our model is fully interpretable and maps physical constraints and intrinsic properties of the real acoustic environment into its latent representation of information. Within our model we use a trainable perfectly matched layer to explicitly learn the property of acoustic energy dissipation. Our model can be used to predict and control scattered wave energy. The capabilities of our model are demonstrated on an important problem in acoustics, which is the minimization of total scattered energy. Furthermore, we show that the prediction of scattered energy by our model generalizes in time and can be extended to long time horizons. We make our code repository publicly available.
Authors: Dong-Young Kim, Dong-Kyun Han, Seo-Hyeon Park, Geun-Deok Jang, Seong-Whan Lee
Abnormal driver states, particularly have been major concerns for road safety, emphasizing the importance of accurate drowsiness detection to prevent accidents. Electroencephalogram (EEG) signals are recognized for their effectiveness in monitoring a driver's mental state by monitoring brain activities. However, the challenge lies in the requirement for prior calibration due to the variation of EEG signals among and within individuals. The necessity of calibration has made the brain-computer interface (BCI) less accessible. We propose a practical generalized framework for classifying driver drowsiness states to improve accessibility and convenience. We separate the normalization process for each driver, treating them as individual domains. The goal of developing a general model is similar to that of domain generalization. The framework considers the statistics of each domain separately since they vary among domains. We experimented with various normalization methods to enhance the ability to generalize across subjects, i.e. the model's generalization performance of unseen domains. The experiments showed that applying individual domain-specific normalization yielded an outstanding improvement in generalizability. Furthermore, our framework demonstrates the potential and accessibility by removing the need for calibration in BCI applications.
Authors: Bappaditya Dey, Anh Tuan Ngo, Sara Sacchi, Victor Blanco, Philippe Leray, Sandip Halder
Moore Law states that transistor density will double every two years, which is sustained until today due to continuous multi-directional innovations, such as extreme ultraviolet lithography, novel patterning techniques etc., leading the semiconductor industry towards 3nm node and beyond. For any patterning scheme, the most important metric to evaluate the quality of printed patterns is EPE, with overlay being its largest contribution. Overlay errors can lead to fatal failures of IC devices such as short circuits or broken connections in terms of P2P electrical contacts. Therefore, it is essential to develop effective overlay analysis and control techniques to ensure good functionality of fabricated semiconductor devices. In this work we have used an imec N14 BEOL process flow using LELE patterning technique to print metal layers with minimum pitch of 48nm with 193i lithography. FF structures are decomposed into two mask layers (M1A and M1B) and then the LELE flow is carried out to make the final patterns. Since a single M1 layer is decomposed into two masks, control of overlay between the two masks is critical. The goal of this work is of two-fold as, (a) to quantify the impact of overlay on capacitance and (b) to see if we can predict the final capacitance measurements with selected machine learning models at an early stage. To do so, scatterometry spectra are collected on these electrical test structures at (a)post litho, (b)post TiN hardmask etch, and (c)post Cu plating and CMP. Critical Dimension and overlay measurements for line-space pattern are done with SEM post litho, post etch and post Cu CMP. Various machine learning models are applied to do the capacitance prediction with multiple metrology inputs at different steps of wafer processing. Finally, we demonstrate that by using appropriate machine learning models we are able to do better prediction of electrical results.
Authors: Pranav Singh Chib, Pravendra Singh
Trajectory prediction is an important task that involves modeling the indeterminate nature of traffic actors to forecast future trajectories given the observed trajectory sequences. However, current methods confine themselves to presumed data manifolds, assuming that trajectories strictly adhere to these manifolds, resulting in overly simplified predictions. To this end, we propose a novel approach called SSWNP (Self-Supervised Waypoint Noise Prediction). In our approach, we first create clean and noise-augmented views of past observed trajectories across the spatial domain of waypoints. We then compel the trajectory prediction model to maintain spatial consistency between predictions from these two views, in addition to the trajectory prediction task. Introducing the noise-augmented view mitigates the model's reliance on a narrow interpretation of the data manifold, enabling it to learn more plausible and diverse representations. We also predict the noise present in the two views of past observed trajectories as an auxiliary self-supervised task, enhancing the model's understanding of the underlying representation and future predictions. Empirical evidence demonstrates that the incorporation of SSWNP into the model learning process significantly improves performance, even in noisy environments, when compared to baseline methods. Our approach can complement existing trajectory prediction methods. To showcase the effectiveness of our approach, we conducted extensive experiments on three datasets: NBA Sports VU, ETH-UCY, and TrajNet++, with experimental results highlighting the substantial improvement achieved in trajectory prediction tasks.
Authors: Luka Kovač, Igor Farkaš
Reinforcement learning (RL) agents need to explore their environments in order to learn optimal policies. In many environments and tasks, safety is of critical importance. The widespread use of simulators offers a number of advantages, including safe exploration which will be inevitable in cases when RL systems need to be trained directly in the physical environment (e.g. in human-robot interaction). The popular Safety Gym library offers three mobile agent types that can learn goal-directed tasks while considering various safety constraints. In this paper, we extend the applicability of safe RL algorithms by creating a customized environment with Panda robotic arm where Safety Gym algorithms can be tested. We performed pilot experiments with the popular PPO algorithm comparing the baseline with the constrained version and show that the constrained version is able to learn the equally good policy while better complying with safety constraints and taking longer training time as expected.
Authors: Isotta Landi, Eugenia Alleva, Alissa A. Valentine, Lauren A. Lepow, Alexander W. Charney
Despite being a unique source of information on patients' status and disease progression, clinical notes are characterized by high levels of duplication and information redundancy. In general domain text, it has been shown that deduplication does not harm language model (LM) pretraining, thus helping reduce the training cost. Although large LMs have proven to learn medical knowledge, they still require specialized domain adaptation for improved downstream clinical tasks. By leveraging large real-world clinical corpora, we first provided a fine-grained characterization of duplicates stemming from common writing practices and clinical relevancy. Second, we demonstrated that deduplicating clinical text can help clinical LMs encode less redundant information in a more efficient manner and do not harm classification tasks via prompt-based learning.
Authors: Falih Gozi Febrinanto, Kristen Moore, Chandra Thapa, Mujie Liu, Vidya Saikrishna, Jiangang Ma, Feng Xia
Many multivariate time series anomaly detection frameworks have been proposed and widely applied. However, most of these frameworks do not consider intrinsic relationships between variables in multivariate time series data, thus ignoring the causal relationship among variables and degrading anomaly detection performance. This work proposes a novel framework called CGAD, an entropy Causal Graph for multivariate time series Anomaly Detection. CGAD utilizes transfer entropy to construct graph structures that unveil the underlying causal relationships among time series data. Weighted graph convolutional networks combined with causal convolutions are employed to model both the causal graph structures and the temporal patterns within multivariate time series data. Furthermore, CGAD applies anomaly scoring, leveraging median absolute deviation-based normalization to improve the robustness of the anomaly identification process. Extensive experiments demonstrate that CGAD outperforms state-of-the-art methods on real-world datasets with a 15% average improvement based on three different multivariate time series anomaly detection metrics.
Authors: Qian Wang, Yaoyao Liu, Hefei Ling, Yingwei Li, Qihao Liu, Ping Li, Jiazhong Chen, Alan Yuille, Ning Yu
In response to the rapidly evolving nature of adversarial attacks on a monthly basis, numerous defenses have been proposed to generalize against as many known attacks as possible. However, designing a defense method that can generalize to all types of attacks, including unseen ones, is not realistic because the environment in which defense systems operate is dynamic and comprises various unique attacks used by many attackers. The defense system needs to upgrade itself by utilizing few-shot defense feedback and efficient memory. Therefore, we propose the first continual adversarial defense (CAD) framework that adapts to any attacks in a dynamic scenario, where various attacks emerge stage by stage. In practice, CAD is modeled under four principles: (1) continual adaptation to new attacks without catastrophic forgetting, (2) few-shot adaptation, (3) memory-efficient adaptation, and (4) high accuracy on both clean and adversarial images. We leverage cutting-edge continual learning, few-shot learning, and ensemble learning techniques to qualify the principles. Experiments conducted on CIFAR-10 and ImageNet-100 validate the effectiveness of our approach against multiple stages of 10 modern adversarial attacks and significant improvements over 10 baseline methods. In particular, CAD is capable of quickly adapting with minimal feedback and a low cost of defense failure, while maintaining good performance against old attacks. Our research sheds light on a brand-new paradigm for continual defense adaptation against dynamic and evolving attacks.
Authors: Zixian Su, Jingwei Guo, Kai Yao, Xi Yang, Qiufeng Wang, Kaizhu Huang
While recent test-time adaptations exhibit efficacy by adjusting batch normalization to narrow domain disparities, their effectiveness diminishes with realistic mini-batches due to inaccurate target estimation. As previous attempts merely introduce source statistics to mitigate this issue, the fundamental problem of inaccurate target estimation still persists, leaving the intrinsic test-time domain shifts unresolved. This paper delves into the problem of mini-batch degradation. By unraveling batch normalization, we discover that the inexact target statistics largely stem from the substantially reduced class diversity in batch. Drawing upon this insight, we introduce a straightforward tool, Test-time Exponential Moving Average (TEMA), to bridge the class diversity gap between training and testing batches. Importantly, our TEMA adaptively extends the scope of typical methods beyond the current batch to incorporate a diverse set of class information, which in turn boosts an accurate target estimation. Built upon this foundation, we further design a novel layer-wise rectification strategy to consistently promote test-time performance. Our proposed method enjoys a unique advantage as it requires neither training nor tuning parameters, offering a truly hassle-free solution. It significantly enhances model robustness against shifted domains and maintains resilience in diverse real-world scenarios with various batch sizes, achieving state-of-the-art performance on several major benchmarks. Code is available at \url{https://github.com/kiwi12138/RealisticTTA}.
Authors: Mengze Gao, Xiaozhi Cao, Daniel Abraham, Zihan Zhou, Kawin Setsompop
$B_1^+$ and $B_0$ field-inhomogeneities can significantly reduce accuracy and robustness of MRF's quantitative parameter estimates. Additional $B_1^+$ and $B_0$ calibration scans can mitigate this but add scan time and cannot be applied retrospectively to previously collected data. Here, we proposed a calibration-free sequence-adaptive deep-learning framework, to estimate and correct for $B_1^+$ and $B_0$ effects of any MRF sequence. We demonstrate its capability on arbitrary MRF sequences at 3T, where no training data were previously obtained. Such approach can be applied to any previously-acquired and future MRF-scans. The flexibility in directly applying this framework to other quantitative sequences is also highlighted.
Authors: Zi Huang, Akila Pemasiri, Simon Denman, Clinton Fookes, Terrence Martin
Radio signal recognition is a crucial function in electronic warfare. Precise identification and localisation of radar pulse activities are required by electronic warfare systems to produce effective countermeasures. Despite the importance of these tasks, deep learning-based radar pulse activity recognition methods have remained largely underexplored. While deep learning for radar modulation recognition has been explored previously, classification tasks are generally limited to short and non-interleaved IQ signals, limiting their applicability to military applications. To address this gap, we introduce an end-to-end multi-stage learning approach to detect and localise pulse activities of interleaved radar signals across an extended time horizon. We propose a simple, yet highly effective multi-stage architecture for incrementally predicting fine-grained segmentation masks that localise radar pulse activities across multiple channels. We demonstrate the performance of our approach against several reference models on a novel radar dataset, while also providing a first-of-its-kind benchmark for radar pulse activity segmentation.
Authors: Xiaolong Fan, Maoguo Gong, Yue Wu, Zedong Tang, Jieyi Liu
Graph Structure Learning (GSL) has demonstrated considerable potential in the analysis of graph-unknown non-Euclidean data across a wide range of domains. However, constructing an end-to-end graph structure learning model poses a challenge due to the impediment of gradient flow caused by the nearest neighbor sampling strategy. In this paper, we construct a differential graph structure learning model by replacing the non-differentiable nearest neighbor sampling with a differentiable sampling using the reparameterization trick. Under this framework, we argue that the act of sampling \mbox{nearest} neighbors may not invariably be essential, particularly in instances where node features exhibit a significant degree of similarity. To alleviate this issue, the bell-shaped Gaussian Similarity (GauSim) modeling is proposed to sample non-nearest neighbors. To adaptively model the similarity, we further propose Neural Gaussian Similarity (NeuralGauSim) with learnable parameters featuring flexible sampling behaviors. In addition, we develop a scalable method by transferring the large-scale graph to the transition graph to significantly reduce the complexity. Experimental results demonstrate the effectiveness of the proposed methods.
Authors: Mustafa Hajij, Ghada Zamzmi, Theodore Papamarkou, Aldo Guzmán-Sáenz, Tolga Birdal, Michael T. Schaub
Graph-based signal processing techniques have become essential for handling data in non-Euclidean spaces. However, there is a growing awareness that these graph models might need to be expanded into `higher-order' domains to effectively represent the complex relations found in high-dimensional data. Such higher-order domains are typically modeled either as hypergraphs, or as simplicial, cubical or other cell complexes. In this context, cell complexes are often seen as a subclass of hypergraphs with additional algebraic structure that can be exploited, e.g., to develop a spectral theory. In this article, we promote an alternative perspective. We argue that hypergraphs and cell complexes emphasize \emph{different} types of relations, which may have different utility depending on the application context. Whereas hypergraphs are effective in modeling set-type, multi-body relations between entities, cell complexes provide an effective means to model hierarchical, interior-to-boundary type relations. We discuss the relative advantages of these two choices and elaborate on the previously introduced concept of a combinatorial complex that enables co-existing set-type and hierarchical relations. Finally, we provide a brief numerical experiment to demonstrate that this modelling flexibility can be advantageous in learning tasks.
Authors: Mengmeng Sheng, Zeren Sun, Zhenhuang Cai, Tao Chen, Yichao Zhou, Yazhou Yao
There has been significant attention devoted to the effectiveness of various domains, such as semi-supervised learning, contrastive learning, and meta-learning, in enhancing the performance of methods for noisy label learning (NLL) tasks. However, most existing methods still depend on prior assumptions regarding clean samples amidst different sources of noise (\eg, a pre-defined drop rate or a small subset of clean samples). In this paper, we propose a simple yet powerful idea called \textbf{NPN}, which revolutionizes \textbf{N}oisy label learning by integrating \textbf{P}artial label learning (PLL) and \textbf{N}egative learning (NL). Toward this goal, we initially decompose the given label space adaptively into the candidate and complementary labels, thereby establishing the conditions for PLL and NL. We propose two adaptive data-driven paradigms of label disambiguation for PLL: hard disambiguation and soft disambiguation. Furthermore, we generate reliable complementary labels using all non-candidate labels for NL to enhance model robustness through indirect supervision. To maintain label reliability during the later stage of model training, we introduce a consistency regularization term that encourages agreement between the outputs of multiple augmentations. Experiments conducted on both synthetically corrupted and real-world noisy datasets demonstrate the superiority of NPN compared to other state-of-the-art (SOTA) methods. The source code has been made available at {\color{purple}{\url{https://github.com/NUST-Machine-Intelligence-Laboratory/NPN}}}.
Authors: Rollin Omari, Junae Kim, Paul Montague
In this paper we explore the challenges and strategies for enhancing the robustness of $k$-means clustering algorithms against adversarial manipulations. We evaluate the vulnerability of clustering algorithms to adversarial attacks, emphasising the associated security risks. Our study investigates the impact of incremental attack strength on training, introduces the concept of transferability between supervised and unsupervised models, and highlights the sensitivity of unsupervised models to sample distributions. We additionally introduce and evaluate an adversarial training method that improves testing performance in adversarial scenarios, and we highlight the importance of various parameters in the proposed training method, such as continuous learning, centroid initialisation, and adversarial step-count.
Authors: Lujia Wang, Hairong Wang, Yi Su, Fleming Lure, Jing Li
Ordinal learning (OL) is a type of machine learning models with broad utility in health care applications such as diagnosis of different grades of a disease (e.g., mild, modest, severe) and prediction of the speed of disease progression (e.g., very fast, fast, moderate, slow). This paper aims to tackle a situation when precisely labeled samples are limited in the training set due to cost or availability constraints, whereas there could be an abundance of samples with imprecise labels. We focus on imprecise labels that are intervals, i.e., one can know that a sample belongs to an interval of labels but cannot know which unique label it has. This situation is quite common in health care datasets due to limitations of the diagnostic instrument, sparse clinical visits, or/and patient dropout. Limited research has been done to develop OL models with imprecise/interval labels. We propose a new Hybrid Ordinal Learner (HOL) to integrate samples with both precise and interval labels to train a robust OL model. We also develop a tractable and efficient optimization algorithm to solve the HOL formulation. We compare HOL with several recently developed OL methods on four benchmarking datasets, which demonstrate the superior performance of HOL. Finally, we apply HOL to a real-world dataset for predicting the speed of progressing to Alzheimer's Disease (AD) for individuals with Mild Cognitive Impairment (MCI) based on a combination of multi-modality neuroimaging and demographic/clinical datasets. HOL achieves high accuracy in the prediction and outperforms existing methods. The capability of accurately predicting the speed of progression to AD for each individual with MCI has the potential for helping facilitate more individually-optimized interventional strategies.
Authors: Krzysztof Czarnecki, Hiroshi Kuwajima
Driving Automation Systems (DAS) are subject to complex road environments and vehicle behaviors and increasingly rely on sophisticated sensors and Artificial Intelligence (AI). These properties give rise to unique safety faults stemming from specification insufficiencies and technological performance limitations, where sensors and AI introduce errors that vary in magnitude and temporal patterns, posing potential safety risks. The Safety of the Intended Functionality (SOTIF) standard emerges as a promising framework for addressing these concerns, focusing on scenario-based analysis to identify hazardous behaviors and their causes. Although the current standard provides a basic cause-and-effect model and high-level process guidance, it lacks concepts required to identify and evaluate hazardous errors, especially within the context of AI.
This paper introduces two key contributions to bridge this gap. First, it defines the SOTIF Temporal Error and Failure Model (STEAM) as a refinement of the SOTIF cause-and-effect model, offering a comprehensive system-design perspective. STEAM refines error definitions, introduces error sequences, and classifies them as error sequence patterns, providing particular relevance to systems employing advanced sensors and AI. Second, this paper proposes the Model-based SOTIF Analysis of Failures and Errors (MoSAFE) method, which allows instantiating STEAM based on system-design models by deriving hazardous error sequence patterns at module level from hazardous behaviors at vehicle level via weakest precondition reasoning. Finally, the paper presents a case study centered on an automated speed-control feature, illustrating the practical applicability of the refined model and the MoSAFE method in addressing complex safety challenges in DAS.
Authors: Kevin Wilkinghoff
State-of-the-art anomalous sound detection (ASD) systems are often trained by using an auxiliary classification task to learn an embedding space. Doing so enables the system to learn embeddings that are robust to noise and are ignoring non-target sound events but requires manually annotated meta information to be used as class labels. However, the less difficult the classification task becomes, the less informative are the embeddings and the worse is the resulting ASD performance. A solution to this problem is to utilize self-supervised learning (SSL). In this work, feature exchange (FeatEx), a simple yet effective SSL approach for ASD, is proposed. In addition, FeatEx is compared to and combined with existing SSL approaches. As the main result, a new state-of-the-art performance for the DCASE2023 ASD dataset is obtained that outperforms all other published results on this dataset by a large margin.
Authors: Hua Lan, Shijie Zhao, Jinjie Hu, Zengfu Wang, Jing Fu
In this article, the state estimation problems with unknown process noise and measurement noise covariances for both linear and nonlinear systems are considered. By formulating the joint estimation of system state and noise parameters into an optimization problem, a novel adaptive Kalman filter method based on conjugate-computation variational inference, referred to as CVIAKF, is proposed to approximate the joint posterior probability density function of the latent variables. Unlike the existing adaptive Kalman filter methods utilizing variational inference in natural-parameter space, CVIAKF performs optimization in expectation-parameter space, resulting in a faster and simpler solution. Meanwhile, CVIAKF divides optimization objectives into conjugate and non-conjugate parts of nonlinear dynamical models, whereas conjugate computations and stochastic mirror-descent are applied, respectively. Remarkably, the reparameterization trick is used to reduce the variance of stochastic gradients of the non-conjugate parts. The effectiveness of CVIAKF is validated through synthetic and real-world datasets of maneuvering target tracking.
Authors: Hosein Hashemi, Claudius Krause
In modern collider experiments, the quest to explore fundamental interactions between elementary particles has reached unparalleled levels of precision. Signatures from particle physics detectors are low-level objects encoding the physics of collisions. The complete simulation of them in a detector is a memory and storage-intensive task. To address this computational bottleneck in particle physics, "Fast Simulation" has been introduced and refined over the years. The field has seen a surge in interest in surrogate modeling the detector simulation, fueled by the advancements in deep generative models. These models aim to generate responses that are statistically identical to the observed data. In this paper, we conduct a comprehensive and exhaustive taxonomic review of the existing literature on the simulation of detector signatures from both methodological and application-wise perspectives. Initially, we formulate the problem of detector signature simulation and discuss its different variations that can be unified. Next, we classify the state-of-the-art methods into four distinct categories based on their underlying model architectures, summarizing their respective generation strategies. We then identify and discuss three key application areas. Finally, we shed light on the challenges and opportunities that lie ahead in detector signature simulation, setting the stage for future research and development.
Authors: Xin Jin, Jonathan Larson, Weiwei Yang, Zhiqiang Lin
Binary code summarization, while invaluable for understanding code semantics, is challenging due to its labor-intensive nature. This study delves into the potential of large language models (LLMs) for binary code comprehension. To this end, we present BinSum, a comprehensive benchmark and dataset of over 557K binary functions and introduce a novel method for prompt synthesis and optimization. To more accurately gauge LLM performance, we also propose a new semantic similarity metric that surpasses traditional exact-match approaches. Our extensive evaluation of prominent LLMs, including ChatGPT, GPT-4, Llama 2, and Code Llama, reveals 10 pivotal insights. This evaluation generates 4 billion inference tokens, incurred a total expense of 11,418 US dollars and 873 NVIDIA A100 GPU hours. Our findings highlight both the transformative potential of LLMs in this field and the challenges yet to be overcome.
Authors: June-Woo Kim, Sangmin Bae, Won-Yang Cho, Byungjo Lee, Ho-Young Jung
Despite the remarkable advances in deep learning technology, achieving satisfactory performance in lung sound classification remains a challenge due to the scarcity of available data. Moreover, the respiratory sound samples are collected from a variety of electronic stethoscopes, which could potentially introduce biases into the trained models. When a significant distribution shift occurs within the test dataset or in a practical scenario, it can substantially decrease the performance. To tackle this issue, we introduce cross-domain adaptation techniques, which transfer the knowledge from a source domain to a distinct target domain. In particular, by considering different stethoscope types as individual domains, we propose a novel stethoscope-guided supervised contrastive learning approach. This method can mitigate any domain-related disparities and thus enables the model to distinguish respiratory sounds of the recording variation of the stethoscope. The experimental results on the ICBHI dataset demonstrate that the proposed methods are effective in reducing the domain dependency and achieving the ICBHI Score of 61.71%, which is a significant improvement of 2.16% over the baseline.
Authors: Harris Papadopoulos, Haris Haralambous
This paper proposes an extension to conventional regression Neural Networks (NNs) for replacing the point predictions they produce with prediction intervals that satisfy a required level of confidence. Our approach follows a novel machine learning framework, called Conformal Prediction (CP), for assigning reliable confidence measures to predictions without assuming anything more than that the data are independent and identically distributed (i.i.d.). We evaluate the proposed method on four benchmark datasets and on the problem of predicting Total Electron Content (TEC), which is an important parameter in trans-ionospheric links; for the latter we use a dataset of more than 60000 TEC measurements collected over a period of 11 years. Our experimental results show that the prediction intervals produced by our method are both well-calibrated and tight enough to be useful in practice.
Authors: Heli Järvenpää, Patricia Lago, Justus Bogner, Grace Lewis, Henry Muccini, Ipek Ozkaya
The rapid adoption of artificial intelligence (AI) and machine learning (ML) has generated growing interest in understanding their environmental impact and the challenges associated with designing environmentally friendly ML-enabled systems. While Green AI research, i.e., research that tries to minimize the energy footprint of AI, is receiving increasing attention, very few concrete guidelines are available on how ML-enabled systems can be designed to be more environmentally sustainable. In this paper, we provide a catalog of 30 green architectural tactics for ML-enabled systems to fill this gap. An architectural tactic is a high-level design technique to improve software quality, in our case environmental sustainability. We derived the tactics from the analysis of 51 peer-reviewed publications that primarily explore Green AI, and validated them using a focus group approach with three experts. The 30 tactics we identified are aimed to serve as an initial reference guide for further exploration into Green AI from a software engineering perspective, and assist in designing sustainable ML-enabled systems. To enhance transparency and facilitate their widespread use and extension, we make the tactics available online in easily consumable formats. Wide-spread adoption of these tactics has the potential to substantially reduce the societal impact of ML-enabled systems regarding their energy and carbon footprint.
Authors: Hang Gao, Chengyu Yao, Jiangmeng Li, Lingyu Si, Yifan Jin, Fengge Wu, Changwen Zheng, Huaping Liu
Graph Neural Networks (GNNs) demonstrate their significance by effectively modeling complex interrelationships within graph-structured data. To enhance the credibility and robustness of GNNs, it becomes exceptionally crucial to bolster their ability to capture causal relationships. However, despite recent advancements that have indeed strengthened GNNs from a causal learning perspective, conducting an in-depth analysis specifically targeting the causal modeling prowess of GNNs remains an unresolved issue. In order to comprehensively analyze various GNN models from a causal learning perspective, we constructed an artificially synthesized dataset with known and controllable causal relationships between data and labels. The rationality of the generated data is further ensured through theoretical foundations. Drawing insights from analyses conducted using our dataset, we introduce a lightweight and highly adaptable GNN module designed to strengthen GNNs' causal learning capabilities across a diverse range of tasks. Through a series of experiments conducted on both synthetic datasets and other real-world datasets, we empirically validate the effectiveness of the proposed module.
Authors: Sergio Kazatzidis, Siamak Mehrkanoon
Self-supervised learning addresses the challenge encountered by many supervised methods, i.e. the requirement of large amounts of annotated data. This challenge is particularly pronounced in fields such as the electroencephalography (EEG) research domain. Self-supervised learning operates instead by utilizing pseudo-labels, which are generated by pretext tasks, to obtain a rich and meaningful data representation. In this study, we aim at introducing a dual-stream pretext task architecture that operates both in the time and frequency domains. In particular, we have examined the incorporation of the novel Frequency Similarity (FS) pretext task into two existing pretext tasks, Relative Positioning (RP) and Temporal Shuffling (TS). We assess the accuracy of these models using the Physionet Challenge 2018 (PC18) dataset in the context of the downstream task sleep stage classification. The inclusion of FS resulted in a notable improvement in downstream task accuracy, with a 1.28 percent improvement on RP and a 2.02 percent improvement on TS. Furthermore, when visualizing the learned embeddings using Uniform Manifold Approximation and Projection (UMAP), distinct clusters emerge, indicating that the learned representations carry meaningful information.
Authors: Chenyang Yu, Xuehu Liu, Yingquan Wang, Pingping Zhang, Huchuan Lu
Large-scale language-image pre-trained models (e.g., CLIP) have shown superior performances on many cross-modal retrieval tasks. However, the problem of transferring the knowledge learned from such models to video-based person re-identification (ReID) has barely been explored. In addition, there is a lack of decent text descriptions in current ReID benchmarks. To address these issues, in this work, we propose a novel one-stage text-free CLIP-based learning framework named TF-CLIP for video-based person ReID. More specifically, we extract the identity-specific sequence feature as the CLIP-Memory to replace the text feature. Meanwhile, we design a Sequence-Specific Prompt (SSP) module to update the CLIP-Memory online. To capture temporal information, we further propose a Temporal Memory Diffusion (TMD) module, which consists of two key components: Temporal Memory Construction (TMC) and Memory Diffusion (MD). Technically, TMC allows the frame-level memories in a sequence to communicate with each other, and to extract temporal information based on the relations within the sequence. MD further diffuses the temporal memories to each token in the original features to obtain more robust sequence features. Extensive experiments demonstrate that our proposed method shows much better results than other state-of-the-art methods on MARS, LS-VID and iLIDS-VID. The code is available at https://github.com/AsuradaYuci/TF-CLIP.
Authors: Léo Grinsztajn (SODA, MLIA, ISIR), Edouard Oyallon (MLIA, CNRS, ISIR, SU), Myung Jun Kim (SODA), Gaël Varoquaux (SODA)
There are increasingly efficient data processing pipelines that work on vectors of numbers, for instance most machine learning models, or vector databases for fast similarity search. These require converting the data to numbers. While this conversion is easy for simple numerical and categorical entries, databases are strife with text entries, such as names or descriptions. In the age of large language models, what's the best strategies to vectorize tables entries, baring in mind that larger models entail more operational complexity? We study the benefits of language models in 14 analytical tasks on tables while varying the training size, as well as for a fuzzy join benchmark. We introduce a simple characterization of a column that reveals two settings: 1) a dirty categories setting, where strings share much similarities across entries, and conversely 2) a diverse entries setting. For dirty categories, pretrained language models bring little-to-no benefit compared to simpler string models. For diverse entries, we show that larger language models improve data processing. For these we investigate the complexity-performance tradeoffs and show that they reflect those of classic text embedding: larger models tend to perform better, but it is useful to fine tune them for embedding purposes.
Authors: Mahesh Datta Sai Ponnuru, Likhitha Amasala, Tanu Sree Bhimavarapu, Guna Chaitanya Garikipati
As the number and complexity of malware attacks continue to increase, there is an urgent need for effective malware detection systems. While deep learning models are effective at detecting malware, they are vulnerable to adversarial attacks. Attacks like this can create malicious files that are resistant to detection, creating a significant cybersecurity risk. Recent research has seen the development of several adversarial attack and response approaches aiming at strengthening deep learning models' resilience to such attacks. This survey study offers an in-depth look at current research in adversarial attack and defensive strategies for malware classification in cybersecurity. The methods are classified into four categories: generative models, feature-based approaches, ensemble methods, and hybrid tactics. The article outlines cutting-edge procedures within each area, assessing their benefits and drawbacks. Each topic presents cutting-edge approaches and explores their advantages and disadvantages. In addition, the study discusses the datasets and assessment criteria that are often utilized on this subject. Finally, it identifies open research difficulties and suggests future study options. This document is a significant resource for malware categorization and cyber security researchers and practitioners.
Authors: Yao Zhao, Haipeng Zhang, Shiwei Lyu, Ruiying Jiang, Jinjie Gu, Guannan Zhang
Uplift modeling is widely used in performance marketing to estimate effects of promotion campaigns (e.g., increase of customer retention rate). Since it is impossible to observe outcomes of a recipient in treatment (e.g., receiving a certain promotion) and control (e.g., without promotion) groups simultaneously (i.e., counter-factual), uplift models are mainly trained on instances of treatment and control groups separately to form two models respectively, and uplifts are predicted by the difference of predictions from these two models (i.e., two-model method). When responses are noisy and the treatment effect is fractional, induced individual uplift predictions will be inaccurate, resulting in targeting undesirable customers. Though it is impossible to obtain the ideal ground-truth individual uplifts, known as Individual Treatment Effects (ITEs), alternatively, an average uplift of a group of users, called Average Treatment Effect (ATE), can be observed from experimental deliveries. Upon this, similar to Multiple Instance Learning (MIL) in which each training sample is a bag of instances, our framework sums up individual user uplift predictions for each bag of users as its bag-wise ATE prediction, and regularizes it to its ATE label, thus learning more accurate individual uplifts. Additionally, to amplify the fractional treatment effect, bags are composed of instances with adjacent individual uplift predictions, instead of random instances. Experiments conducted on two datasets show the effectiveness and universality of the proposed framework.
Authors: Xiaohui Zhang, Jiangyan Yi, Chenglong Wang, Chuyuan Zhang, Siding Zeng, Jianhua Tao
The rapid evolution of speech synthesis and voice conversion has raised substantial concerns due to the potential misuse of such technology, prompting a pressing need for effective audio deepfake detection mechanisms. Existing detection models have shown remarkable success in discriminating known deepfake audio, but struggle when encountering new attack types. To address this challenge, one of the emergent effective approaches is continual learning. In this paper, we propose a continual learning approach called Radian Weight Modification (RWM) for audio deepfake detection. The fundamental concept underlying RWM involves categorizing all classes into two groups: those with compact feature distributions across tasks, such as genuine audio, and those with more spread-out distributions, like various types of fake audio. These distinctions are quantified by means of the in-class cosine distance, which subsequently serves as the basis for RWM to introduce a trainable gradient modification direction for distinct data types. Experimental evaluations against mainstream continual learning methods reveal the superiority of RWM in terms of knowledge acquisition and mitigating forgetting in audio deepfake detection. Furthermore, RWM's applicability extends beyond audio deepfake detection, demonstrating its potential significance in diverse machine learning domains such as image recognition.
Authors: Alessandro Ilic Mezza, Riccardo Giampiccolo, Alberto Bernardini, Augusto Sarti
In the past, the field of drum source separation faced significant challenges due to limited data availability, hindering the adoption of cutting-edge deep learning methods that have found success in other related audio applications. In this manuscript, we introduce StemGMD, a large-scale audio dataset of isolated single-instrument drum stems. Each audio clip is synthesized from MIDI recordings of expressive drums performances using ten real-sounding acoustic drum kits. Totaling 1224 hours, StemGMD is the largest audio dataset of drums to date and the first to comprise isolated audio clips for every instrument in a canonical nine-piece drum kit. We leverage StemGMD to develop LarsNet, a novel deep drum source separation model. Through a bank of dedicated U-Nets, LarsNet can separate five stems from a stereo drum mixture faster than real-time and is shown to significantly outperform state-of-the-art nonnegative spectro-temporal factorization methods.
Authors: Xiaoming Wang, Zhiguo Gong
Robot calligraphy is an emerging exploration of artificial intelligence in the fields of art and education. Traditional calligraphy generation researches mainly focus on methods such as tool-based image processing, generative models, and style transfer. Unlike the English alphabet, the number of Chinese characters is tens of thousands, which leads to difficulties in the generation of a style consistent Chinese calligraphic font with over 6000 characters. Due to the lack of high-quality data sets, formal definitions of calligraphy knowledge, and scientific art evaluation methods, The results generated are frequently of low quality and falls short of professional-level requirements. To address the above problem, this paper proposes an automatic calligraphy generation model based on deep generative adversarial networks (deepGAN) that can generate style calligraphy fonts with professional standards. The key highlights of the proposed method include: (1) The datasets use a high-precision calligraphy synthesis method to ensure its high quality and sufficient quantity; (2) Professional calligraphers are invited to conduct a series of Turing tests to evaluate the gap between model generation results and human artistic level; (3) Experimental results indicate that the proposed model is the state-of-the-art among current calligraphy generation methods. The Turing tests and similarity evaluations validate the effectiveness of the proposed method.
Authors: Amitis Shidani, Sattar Vakili
We consider regret minimization in a general collaborative multi-agent multi-armed bandit model, in which each agent faces a finite set of arms and may communicate with other agents through a central controller. The optimal arm for each agent in this model is the arm with the largest expected mixed reward, where the mixed reward of each arm is a weighted average of its rewards across all agents, making communication among agents crucial. While near-optimal sample complexities for best arm identification are known under this collaborative model, the question of optimal regret remains open. In this work, we address this problem and propose the first algorithm with order optimal regret bounds under this collaborative bandit model. Furthermore, we show that only a small constant number of expected communication rounds is needed.
Authors: Zechen Li, Weiming Huang, Kai Zhao, Min Yang, Yongshun Gong, Meng Chen
Recently, learning urban region representations utilizing multi-modal data (information views) has become increasingly popular, for deep understanding of the distributions of various socioeconomic features in cities. However, previous methods usually blend multi-view information in a posteriors stage, falling short in learning coherent and consistent representations across different views. In this paper, we form a new pipeline to learn consistent representations across varying views, and propose the multi-view Contrastive Prediction model for urban Region embedding (ReCP), which leverages the multiple information views from point-of-interest (POI) and human mobility data. Specifically, ReCP comprises two major modules, namely an intra-view learning module utilizing contrastive learning and feature reconstruction to capture the unique information from each single view, and inter-view learning module that perceives the consistency between the two views using a contrastive prediction learning scheme. We conduct thorough experiments on two downstream tasks to assess the proposed model, i.e., land use clustering and region popularity prediction. The experimental results demonstrate that our model outperforms state-of-the-art baseline methods significantly in urban region representation learning.
Authors: Minsu Kim, Seong-Hyeon Hwang, Steven Euijong Whang
Continuous machine learning pipelines are common in industrial settings where models are periodically trained on data streams. Unfortunately, concept drifts may occur in data streams where the joint distribution of the data X and label y, P(X, y), changes over time and possibly degrade model accuracy. Existing concept drift adaptation approaches mostly focus on updating the model to the new data possibly using ensemble techniques of previous models and tend to discard the drifted historical data. However, we contend that explicitly utilizing the drifted data together leads to much better model accuracy and propose Quilt, a data-centric framework for identifying and selecting data segments that maximize model accuracy. To address the potential downside of efficiency, Quilt extends existing data subset selection techniques, which can be used to reduce the training data without compromising model accuracy. These techniques cannot be used as is because they only assume virtual drifts where the posterior probabilities P(y|X) are assumed not to change. In contrast, a key challenge in our setup is to also discard undesirable data segments with concept drifts. Quilt thus discards drifted data segments and selects data segment subsets holistically for accurate and efficient model training. The two operations use gradient-based scores, which have little computation overhead. In our experiments, we show that Quilt outperforms state-of-the-art drift adaptation and data selection baselines on synthetic and real datasets.
Authors: Tianhao Peng, Wenjun Wu, Haitao Yuan, Zhifeng Bao, Zhao Pengrui, Xin Yu, Xuetao Lin, Yu Liang, Yanjun Pu
Graph neural networks (GNNs) have shown advantages in graph-based analysis tasks. However, most existing methods have the homogeneity assumption and show poor performance on heterophilic graphs, where the linked nodes have dissimilar features and different class labels, and the semantically related nodes might be multi-hop away. To address this limitation, this paper presents GraphRARE, a general framework built upon node relative entropy and deep reinforcement learning, to strengthen the expressive capability of GNNs. An innovative node relative entropy, which considers node features and structural similarity, is used to measure mutual information between node pairs. In addition, to avoid the sub-optimal solutions caused by mixing useful information and noises of remote nodes, a deep reinforcement learning-based algorithm is developed to optimize the graph topology. This algorithm selects informative nodes and discards noisy nodes based on the defined node relative entropy. Extensive experiments are conducted on seven real-world datasets. The experimental results demonstrate the superiority of GraphRARE in node classification and its capability to optimize the original graph topology.
Authors: Torbjørn Smith, Olav Egeland
This paper presents a method for learning Hamiltonian dynamics from a limited set of data points. The Hamiltonian vector field is found by regularized optimization over a reproducing kernel Hilbert space of vector fields that are inherently Hamiltonian, and where the vector field is required to be odd or even. This is done with a symplectic kernel, and it is shown how this symplectic kernel can be modified to be odd or even. The performance of the method is validated in simulations for two Hamiltonian systems. It is shown that the learned dynamics are Hamiltonian, and that the learned Hamiltonian vector field can be prescribed to be odd or even.
Authors: Wenjun Zhou, Artem Polyvyanyy, James Bailey
Process mining, a data-driven approach for analyzing, visualizing, and improving business processes using event logs, has emerged as a powerful technique in the field of business process management. Process forecasting is a sub-field of process mining that studies how to predict future processes and process models. In this paper, we introduce and motivate the problem of event log prediction and present our approach to solving the event log prediction problem, in particular, using the sequence-to-sequence deep learning approach. We evaluate and analyze the prediction outcomes on a variety of synthetic logs and seven real-life logs and show that our approach can generate perfect predictions on synthetic logs and that deep learning techniques have the potential to be applied in real-world event log prediction tasks. We further provide practical recommendations for event log predictions grounded in the outcomes of the conducted experiments.
Authors: Guangxuan Song, Dongmei Fu, Zhongwei Qiu, Zijiang Yang, Jiaxin Dai, Lingwei Ma, Dawei Zhang
Using machine learning (ML) techniques to predict material properties is a crucial research topic. These properties depend on numerical data and semantic factors. Due to the limitations of small-sample datasets, existing methods typically adopt ML algorithms to regress numerical properties or transfer other pre-trained knowledge graphs (KGs) to the material. However, these methods cannot simultaneously handle semantic and numerical information. In this paper, we propose a numerical reasoning method for material KGs (NR-KG), which constructs a cross-modal KG using semantic nodes and numerical proxy nodes. It captures both types of information by projecting KG into a canonical KG and utilizes a graph neural network to predict material properties. In this process, a novel projection prediction loss is proposed to extract semantic features from numerical information. NR-KG facilitates end-to-end processing of cross-modal data, mining relationships and cross-modal information in small-sample datasets, and fully utilizes valuable experimental data to enhance material prediction. We further propose two new High-Entropy Alloys (HEA) property datasets with semantic descriptions. NR-KG outperforms state-of-the-art (SOTA) methods, achieving relative improvements of 25.9% and 16.1% on two material datasets. Besides, NR-KG surpasses SOTA methods on two public physical chemistry molecular datasets, showing improvements of 22.2% and 54.3%, highlighting its potential application and generalizability. We hope the proposed datasets, algorithms, and pre-trained models can facilitate the communities of KG and AI for materials.
Authors: Anahita Baninajjar, Ahmed Rezine, Amir Aminifar
Machine learning techniques often lack formal correctness guarantees. This is evidenced by the widespread adversarial examples that plague most deep-learning applications. This resulted in several research efforts that aim at verifying deep neural networks, with a particular focus on safety-critical applications. However, formal verification techniques still face major scalability and precision challenges when dealing with the complexity of such networks. The over-approximation introduced during the formal verification process to tackle the scalability challenge often results in inconclusive analysis. To address this challenge, we propose a novel framework to generate Verification-friendly Neural Networks (VNNs). We present a post-training optimization framework to achieve a balance between preserving prediction performance and robustness in the resulting networks. Our proposed framework proves to result in networks that are comparable to the original ones in terms of prediction performance, while amenable to verification. This essentially enables us to establish robustness for more VNNs than their deep neural network counterparts, in a more time-efficient manner.
Authors: Ziliang Chen, Yongsen Zheng, Zhao-Rong Lai, Quanlong Guan, Liang Lin
Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels de-confounded from the environments, advancing the technical roadmap of out-of-distribution (OOD) generalization. Despite spotlights around, recent theoretical results verified that some causal features recovered by IRLs merely pretend domain-invariantly in the training environments but fail in unseen domains. The \emph{fake invariance} severely endangers OOD generalization since the trustful objective can not be diagnosed and existing causal surgeries are invalid to rectify. In this paper, we review a IRL family (InvRat) under the Partially and Fully Informative Invariant Feature Structural Causal Models (PIIF SCM /FIIF SCM) respectively, to certify their weaknesses in representing fake invariant features, then, unify their causal diagrams to propose ReStructured SCM (RS-SCM). RS-SCM can ideally rebuild the spurious and the fake invariant features simultaneously. Given this, we further develop an approach based on conditional mutual information with respect to RS-SCM, then rigorously rectify the spurious and fake invariant effects. It can be easily implemented by a small feature selection subnet introduced in the IRL family, which is alternatively optimized to achieve our goal. Experiments verified the superiority of our approach to fight against the fake invariant issue across a variety of OOD generalization benchmarks.
Authors: Zi-Yu Khoo, Abel Yang, Jonathan Sze Choong Low, Stéphane Bressan
Can a machine or algorithm discover or learn Kepler's first law from astronomical sightings alone? We emulate Johannes Kepler's discovery of the equation of the orbit of Mars with the Rudolphine tables using AI Feynman, a physics-inspired tool for symbolic regression.
Authors: Zi-Yu Khoo, Jonathan Sze Choong Low, Stéphane Bressan
Many functions characterising physical systems are additively separable. This is the case, for instance, of mechanical Hamiltonian functions in physics, population growth equations in biology, and consumer preference and utility functions in economics. We consider the scenario in which a surrogate of a function is to be tested for additive separability. The detection that the surrogate is additively separable can be leveraged to improve further learning. Hence, it is beneficial to have the ability to test for such separability in surrogates. The mathematical approach is to test if the mixed partial derivative of the surrogate is zero; or empirically, lower than a threshold. We present and comparatively and empirically evaluate the eight methods to compute the mixed partial derivative of a surrogate function.
Authors: Bohan Tang, Siheng Chen, Xiaowen Dong
Hypergraphs are vital in modelling data with higher-order relations containing more than two entities, gaining prominence in machine learning and signal processing. Many hypergraph neural networks leverage message passing over hypergraph structures to enhance node representation learning, yielding impressive performances in tasks like hypergraph node classification. However, these message-passing-based models face several challenges, including oversmoothing as well as high latency and sensitivity to structural perturbations at inference time. To tackle those challenges, we propose an alternative approach where we integrate the information about hypergraph structures into training supervision without explicit message passing, thus also removing the reliance on it at inference. Specifically, we introduce Hypergraph-MLP, a novel learning framework for hypergraph-structured data, where the learning model is a straightforward multilayer perceptron (MLP) supervised by a loss function based on a notion of signal smoothness on hypergraphs. Experiments on hypergraph node classification tasks demonstrate that Hypergraph-MLP achieves competitive performance compared to existing baselines, and is considerably faster and more robust against structural perturbations at inference.
Authors: Tom Nuno Wolf, Fabian Bongratz, Anne-Marie Rickmann, Sebastian Pölsterl, Christian Wachinger
Explaining predictions of black-box neural networks is crucial when applied to decision-critical tasks. Thus, attribution maps are commonly used to identify important image regions, despite prior work showing that humans prefer explanations based on similar examples. To this end, ProtoPNet learns a set of class-representative feature vectors (prototypes) for case-based reasoning. During inference, similarities of latent features to prototypes are linearly classified to form predictions and attribution maps are provided to explain the similarity. In this work, we evaluate whether architectures for case-based reasoning fulfill established axioms required for faithful explanations using the example of ProtoPNet. We show that such architectures allow the extraction of faithful explanations. However, we prove that the attribution maps used to explain the similarities violate the axioms. We propose a new procedure to extract explanations for trained ProtoPNets, named ProtoPFaith. Conceptually, these explanations are Shapley values, calculated on the similarity scores of each prototype. They allow to faithfully answer which prototypes are present in an unseen image and quantify each pixel's contribution to that presence, thereby complying with all axioms. The theoretical violations of ProtoPNet manifest in our experiments on three datasets (CUB-200-2011, Stanford Dogs, RSNA) and five architectures (ConvNet, ResNet, ResNet50, WideResNet50, ResNeXt50). Our experiments show a qualitative difference between the explanations given by ProtoPNet and ProtoPFaith. Additionally, we quantify the explanations with the Area Over the Perturbation Curve, on which ProtoPFaith outperforms ProtoPNet on all experiments by a factor $>10^3$.
Authors: Federica Caforio, Francesco Regazzoni, Stefano Pagani, Elias Karabelas, Christoph Augustin, Gundolf Haase, Gernot Plank, Alfio Quarteroni
The development of biophysical models for clinical applications is rapidly advancing in the research community, thanks to their predictive nature and their ability to assist the interpretation of clinical data. However, high-resolution and accurate multi-physics computational models are computationally expensive and their personalisation involves fine calibration of a large number of parameters, which may be space-dependent, challenging their clinical translation. In this work, we propose a new approach which relies on the combination of physics-informed neural networks (PINNs) with three-dimensional soft tissue nonlinear biomechanical models, capable of reconstructing displacement fields and estimating heterogeneous patient-specific biophysical properties. The proposed learning algorithm encodes information from a limited amount of displacement and, in some cases, strain data, that can be routinely acquired in the clinical setting, and combines it with the physics of the problem, represented by a mathematical model based on partial differential equations, to regularise the problem and improve its convergence properties. Several benchmarks are presented to show the accuracy and robustness of the proposed method and its great potential to enable the robust and effective identification of patient-specific, heterogeneous physical properties, s.a. tissue stiffness properties. In particular, we demonstrate the capability of the PINN to detect the presence, location and severity of scar tissue, which is beneficial to develop personalised simulation models for disease diagnosis, especially for cardiac applications.
Authors: Yasser Benigmim, Subhankar Roy, Slim Essid, Vicky Kalogeiton, Stéphane Lathuilière
Domain Generalized Semantic Segmentation (DGSS) deals with training a model on a labeled source domain with the aim of generalizing to unseen domains during inference. Existing DGSS methods typically effectuate robust features by means of Domain Randomization (DR). Such an approach is often limited as it can only account for style diversification and not content. In this work, we take an orthogonal approach to DGSS and propose to use an assembly of CoLlaborative FOUndation models for Domain Generalized Semantic Segmentation (CLOUDS). In detail, CLOUDS is a framework that integrates FMs of various kinds: (i) CLIP backbone for its robust feature representation, (ii) generative models to diversify the content, thereby covering various modes of the possible target distribution, and (iii) Segment Anything Model (SAM) for iteratively refining the predictions of the segmentation model. Extensive experiments show that our CLOUDS excels in adapting from synthetic to real DGSS benchmarks and under varying weather conditions, notably outperforming prior methods by 5.6% and 6.7% on averaged miou, respectively. The code is available at : https://github.com/yasserben/CLOUDS
Authors: Veronica Piccialli, Jan Schwiddessen, Antonio M. Sudoso
Support vector machines (SVMs) are well-studied supervised learning models for binary classification. In many applications, large amounts of samples can be cheaply and easily obtained. What is often a costly and error-prone process is to manually label these instances. Semi-supervised support vector machines (S3VMs) extend the well-known SVM classifiers to the semi-supervised approach, aiming at maximizing the margin between samples in the presence of unlabeled data. By leveraging both labeled and unlabeled data, S3VMs attempt to achieve better accuracy and robustness compared to traditional SVMs. Unfortunately, the resulting optimization problem is non-convex and hence difficult to solve exactly. In this paper, we present a new branch-and-cut approach for S3VMs using semidefinite programming (SDP) relaxations. We apply optimality-based bound tightening to bound the feasible set. Box constraints allow us to include valid inequalities, strengthening the lower bound. The resulting SDP relaxation provides bounds significantly stronger than the ones available in the literature. For the upper bound, instead, we define a local search exploiting the solution of the SDP relaxation. Computational results highlight the efficiency of the algorithm, showing its capability to solve instances with a number of data points 10 times larger than the ones solved in the literature.
Authors: Christian Oswald, Mate Toth, Paul Meissner, Franz Pernkopf
In this paper we propose a new method for training neural networks (NNs) for frequency modulated continuous wave (FMCW) radar mutual interference mitigation. Instead of training NNs to regress from interfered to clean radar signals as in previous work, we train NNs directly on object detection maps. We do so by performing a continuous relaxation of the cell-averaging constant false alarm rate (CA-CFAR) peak detector, which is a well-established algorithm for object detection using radar. With this new training objective we are able to increase object detection performance by a large margin. Furthermore, we introduce separable convolution kernels to strongly reduce the number of parameters and computational complexity of convolutional NN architectures for radar applications. We validate our contributions with experiments on real-world measurement data and compare them against signal processing interference mitigation methods.
Authors: Pedro Osorio, Guillermo Jimenez-Perez, Javier Montalt-Tordera, Jens Hooge, Guillem Duran-Ballester, Shivam Singh, Moritz Radbruch, Ute Bach, Sabrina Schroeder, Krystyna Siudak, Julia Vienenkoetter, Bettina Lawrenz, Sadegh Mohammadi
Artificial Intelligence (AI) based image analysis has an immense potential to support diagnostic histopathology, including cancer diagnostics. However, developing supervised AI methods requires large-scale annotated datasets. A potentially powerful solution is to augment training data with synthetic data. Latent diffusion models, which can generate high-quality, diverse synthetic images, are promising. However, the most common implementations rely on detailed textual descriptions, which are not generally available in this domain. This work proposes a method that constructs structured textual prompts from automatically extracted image features. We experiment with the PCam dataset, composed of tissue patches only loosely annotated as healthy or cancerous. We show that including image-derived features in the prompt, as opposed to only healthy and cancerous labels, improves the Fr\'echet Inception Distance (FID) from 178.8 to 90.2. We also show that pathologists find it challenging to detect synthetic images, with a median sensitivity/specificity of 0.55/0.55. Finally, we show that synthetic data effectively trains AI models.
Authors: Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Mihaly Petreczky
In this paper, we derive a PAC-Bayes bound on the generalisation gap, in a supervised time-series setting for a special class of discrete-time non-linear dynamical systems. This class includes stable recurrent neural networks (RNN), and the motivation for this work was its application to RNNs. In order to achieve the results, we impose some stability constraints, on the allowed models. Here, stability is understood in the sense of dynamical systems. For RNNs, these stability conditions can be expressed in terms of conditions on the weights. We assume the processes involved are essentially bounded and the loss functions are Lipschitz. The proposed bound on the generalisation gap depends on the mixing coefficient of the data distribution, and the essential supremum of the data. Furthermore, the bound converges to zero as the dataset size increases. In this paper, we 1) formalize the learning problem, 2) derive a PAC-Bayesian error bound for such systems, 3) discuss various consequences of this error bound, and 4) show an illustrative example, with discussions on computing the proposed bound. Unlike other available bounds the derived bound holds for non i.i.d. data (time-series) and it does not grow with the number of steps of the RNN.
Authors: Shang Gao, Chenyang Yu, Pingping Zhang, Huchuan Lu
Occluded person re-identification (ReID) is a very challenging task due to the occlusion disturbance and incomplete target information. Leveraging external cues such as human pose or parsing to locate and align part features has been proven to be very effective in occluded person ReID. Meanwhile, recent Transformer structures have a strong ability of long-range modeling. Considering the above facts, we propose a Teacher-Student Decoder (TSD) framework for occluded person ReID, which utilizes the Transformer decoder with the help of human parsing. More specifically, our proposed TSD consists of a Parsing-aware Teacher Decoder (PTD) and a Standard Student Decoder (SSD). PTD employs human parsing cues to restrict Transformer's attention and imparts this information to SSD through feature distillation. Thereby, SSD can learn from PTD to aggregate information of body parts automatically. Moreover, a mask generator is designed to provide discriminative regions for better ReID. In addition, existing occluded person ReID benchmarks utilize occluded samples as queries, which will amplify the role of alleviating occlusion interference and underestimate the impact of the feature absence issue. Contrastively, we propose a new benchmark with non-occluded queries, serving as a complement to the existing benchmark. Extensive experiments demonstrate that our proposed method is superior and the new benchmark is essential. The source codes are available at https://github.com/hh23333/TSD.
Authors: Xiran Qu, Xuequn Shang, Yupei Zhang
This paper studies the problem of CPRP, concept prerequisite relation prediction, which is a fundamental task in using AI for education. CPRP is usually formulated into a link-prediction task on a relationship graph of concepts and solved by training the graph neural network (GNN) model. However, current directed GNNs fail to manage graph isomorphism which refers to the invariance of non-isomorphic graphs, reducing the expressivity of resulting representations. We present a permutation-equivariant directed GNN model by introducing the Weisfeiler-Lehman test into directed GNN learning. Our method is then used for CPRP and evaluated on three public datasets. The experimental results show that our model delivers better prediction performance than the state-of-the-art methods.
Authors: Zhenxi Lin, Ziheng Zhang, Xian Wu, Yefeng Zheng
Biomedical entity linking (BioEL) has achieved remarkable progress with the help of pre-trained language models. However, existing BioEL methods usually struggle to handle rare and difficult entities due to long-tailed distribution. To address this limitation, we introduce a new scheme $k$NN-BioEL, which provides a BioEL model with the ability to reference similar instances from the entire training corpus as clues for prediction, thus improving the generalization capabilities. Moreover, we design a contrastive learning objective with dynamic hard negative sampling (DHNS) that improves the quality of the retrieved neighbors during inference. Extensive experimental results show that $k$NN-BioEL outperforms state-of-the-art baselines on several datasets.
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/betaPredBayes_FL
Authors: Ximeng Ye, Hongyu Li, Jingjie Huang, Guoliang Qin
This paper launches a thorough discussion on the locality of local neural operator (LNO), which is the core that enables LNO great flexibility on varied computational domains in solving transient partial differential equations (PDEs). We investigate the locality of LNO by looking into its receptive field and receptive range, carrying a main concern about how the locality acts in LNO training and applications. In a large group of LNO training experiments for learning fluid dynamics, it is found that an initial receptive range compatible with the learning task is crucial for LNO to perform well. On the one hand, an over-small receptive range is fatal and usually leads LNO to numerical oscillation; on the other hand, an over-large receptive range hinders LNO from achieving the best accuracy. We deem rules found in this paper general when applying LNO to learn and solve transient PDEs in diverse fields. Practical examples of applying the pre-trained LNOs in flow prediction are presented to confirm the findings further. Overall, with the architecture properly designed with a compatible receptive range, the pre-trained LNO shows commendable accuracy and efficiency in solving practical cases.
Authors: Chandresh Pravin, Ivan Martino, Giuseppe Nicosia, Varun Ojha
We propose a systematic analysis of deep neural networks (DNNs) based on a signal processing technique for network parameter removal, in the form of synaptic filters that identifies the fragility, robustness and antifragility characteristics of DNN parameters. Our proposed analysis investigates if the DNN performance is impacted negatively, invariantly, or positively on both clean and adversarially perturbed test datasets when the DNN undergoes synaptic filtering. We define three \textit{filtering scores} for quantifying the fragility, robustness and antifragility characteristics of DNN parameters based on the performances for (i) clean dataset, (ii) adversarial dataset, and (iii) the difference in performances of clean and adversarial datasets. We validate the proposed systematic analysis on ResNet-18, ResNet-50, SqueezeNet-v1.1 and ShuffleNet V2 x1.0 network architectures for MNIST, CIFAR10 and Tiny ImageNet datasets. The filtering scores, for a given network architecture, identify network parameters that are invariant in characteristics across different datasets over learning epochs. Vice-versa, for a given dataset, the filtering scores identify the parameters that are invariant in characteristics across different network architectures. We show that our synaptic filtering method improves the test accuracy of ResNet and ShuffleNet models on adversarial datasets when only the robust and antifragile parameters are selectively retrained at any given epoch, thus demonstrating applications of the proposed strategy in improving model robustness.
Authors: June Moh Goo
This report proposes a model to predict the location of the most deprived areas in a city using data from the census. A census data is very high dimensional and needs to be simplified. We use a novel algorithm to reduce dimensionality and find patterns: The diffusion map. Features are defined by eigenvectors of the Laplacian matrix that defines the diffusion map. Eigenvectors corresponding to the smallest eigenvalues indicate specific population features. Previous work has found qualitatively that the second most important dimension for describing the census data in Bristol is linked to deprivation. In this report, we analyse how good this dimension is as a model for predicting deprivation by comparing with the recognised measures. The Pearson correlation coefficient was found to be over 0.7. The top 10 per cent of deprived areas in the UK which also locate in Bristol are extracted to test the accuracy of the model. There are 52 most deprived areas, and 38 areas are correctly identified by comparing to the model. The influence of scores of IMD domains that do not correlate with the models, Eigenvector 2 entries of non-deprived OAs and orthogonality of Eigenvectors cause the model to fail the prediction of 14 deprived areas.
However, overall, the model shows a high performance to predict the future deprivation of overall areas where the project considers. This project is expected to support the government to allocate resources and funding.
Authors: Gul Sena Altintas, Gregor Bachmann, Lorenzo Noci, Thomas Hofmann
Linear mode-connectivity (LMC) (or lack thereof) is one of the intriguing characteristics of neural network loss landscapes. While empirically well established, it unfortunately still lacks a proper theoretical understanding. Even worse, although empirical data points are abound, a systematic study of when networks exhibit LMC is largely missing in the literature. In this work we aim to close this gap. We explore how LMC is affected by three factors: (1) architecture (sparsity, weight-sharing), (2) training strategy (optimization setup) as well as (3) the underlying dataset. We place particular emphasis on minimal but non-trivial settings, removing as much unnecessary complexity as possible. We believe that our insights can guide future theoretical works on uncovering the inner workings of LMC.
Authors: Girolamo Macaluso, Alessandro Sestini, Andrew D. Bagdanov
Offline reinforcement learning leverages pre-collected datasets of transitions to train policies. It can serve as effective initialization for online algorithms, enhancing sample efficiency and speeding up convergence. However, when such datasets are limited in size and quality, offline pre-training can produce sub-optimal policies and lead to degraded online reinforcement learning performance. In this paper we propose a model-based data augmentation strategy to maximize the benefits of offline reinforcement learning pre-training and reduce the scale of data needed to be effective. Our approach leverages a world model of the environment trained on the offline dataset to augment states during offline pre-training. We evaluate our approach on a variety of MuJoCo robotic tasks and our results show it can jump-start online fine-tuning and substantially reduce - in some cases by an order of magnitude - the required number of environment interactions.
Authors: Martin Burger, Samira Kabri
The aim of this paper is to provide a theoretically founded investigation of state-of-the-art learning approaches for inverse problems. We give an extended definition of regularization methods and their convergence in terms of the underlying data distributions, which paves the way for future theoretical studies. Based on a simple spectral learning model previously introduced for supervised learning, we investigate some key properties of different learning paradigms for inverse problems, which can be formulated independently of specific architectures. In particular we investigate the regularization properties, bias, and critical dependence on training data distributions. Moreover, our framework allows to highlight and compare the specific behavior of the different paradigms in the infinite-dimensional limit.
Authors: Peter Sorrenson, Felix Draxler, Armand Rousselot, Sander Hummerich, Ullrich Köthe
Many real world data, particularly in the natural sciences and computer vision, lie on known Riemannian manifolds such as spheres, tori or the group of rotation matrices. The predominant approaches to learning a distribution on such a manifold require solving a differential equation in order to sample from the model and evaluate densities. The resulting sampling times are slowed down by a high number of function evaluations. In this work, we propose an alternative approach which only requires a single function evaluation followed by a projection to the manifold. Training is achieved by an adaptation of the recently proposed free-form flow framework to Riemannian manifolds. The central idea is to estimate the gradient of the negative log-likelihood via a trace evaluated in the tangent space. We evaluate our method on various manifolds, and find significantly faster inference at competitive performance compared to previous work. We make our code public at https://github.com/vislearn/FFF.
Authors: Hassan Ismail Fawaz, Ganesh Del Grosso, Tanguy Kerdoncuff, Aurelie Boisbunon, Illyyne Saffar
Unsupervised Domain Adaptation (UDA) aims to harness labeled source data to train models for unlabeled target data. Despite extensive research in domains like computer vision and natural language processing, UDA remains underexplored for time series data, which has widespread real-world applications ranging from medicine and manufacturing to earth observation and human activity recognition. Our paper addresses this gap by introducing a comprehensive benchmark for evaluating UDA techniques for time series classification, with a focus on deep learning methods. We provide seven new benchmark datasets covering various domain shifts and temporal dynamics, facilitating fair and standardized UDA method assessments with state of the art neural network backbones (e.g. Inception) for time series data. This benchmark offers insights into the strengths and limitations of the evaluated approaches while preserving the unsupervised nature of domain adaptation, making it directly applicable to practical problems. Our paper serves as a vital resource for researchers and practitioners, advancing domain adaptation solutions for time series data and fostering innovation in this critical field. The implementation code of this benchmark is available at https://github.com/EricssonResearch/UDA-4-TSC.
Authors: Waïss Azizian, Guillaume Baudart, Marc Lelarge
Exact Bayesian inference on state-space models~(SSM) is in general untractable, and unfortunately, basic Sequential Monte Carlo~(SMC) methods do not yield correct approximations for complex models. In this paper, we propose a mixed inference algorithm that computes closed-form solutions using belief propagation as much as possible, and falls back to sampling-based SMC methods when exact computations fail. This algorithm thus implements automatic Rao-Blackwellization and is even exact for Gaussian tree models.
Authors: Marius Urbonas, Temitope Ajileye, Paul Gainer, Douglas Pires
Designing reward functions that guide generative molecular design (GMD) algorithms to desirable areas of chemical space is of critical importance in AI-driven drug discovery. Traditionally, this has been a manual and error-prone task; the selection of appropriate computational methods to approximate biological assays is challenging and the aggregation of computed values into a single score even more so, leading to potential reliance on trial-and-error approaches. We propose a novel approach for automated reward configuration that relies solely on experimental data, mitigating the challenges of manual reward adjustment on drug discovery projects. Our method achieves this by constructing a ranking over experimental data based on Pareto dominance over the multi-objective space, then training a neural network to approximate the reward function such that rankings determined by the predicted reward correlate with those determined by the Pareto dominance relation. We validate our method using two case studies. In the first study we simulate Design-Make-Test-Analyse (DMTA) cycles by alternating reward function updates and generative runs guided by that function. We show that the learned function adapts over time to yield compounds that score highly with respect to evaluation functions taken from the literature. In the second study we apply our algorithm to historical data from four real drug discovery projects. We show that our algorithm yields reward functions that outperform the predictive accuracy of human-defined functions, achieving an improvement of up to 0.4 in Spearman's correlation against a ground truth evaluation function that encodes the target drug profile for that project. Our method provides an efficient data-driven way to configure reward functions for GMD, and serves as a strong baseline for future research into transformative approaches for the automation of drug discovery.
Authors: Minbiao Han, Michael Albert, Haifeng Xu
We study a ubiquitous learning challenge in online principal-agent problems during which the principal learns the agent's private information from the agent's revealed preferences in historical interactions. This paradigm includes important special cases such as pricing and contract design, which have been widely studied in recent literature. However, existing work considers the case where the principal can only choose a single strategy at every round to interact with the agent and then observe the agent's revealed preference through their actions. In this paper, we extend this line of study to allow the principal to offer a menu of strategies to the agent and learn additionally from observing the agent's selection from the menu. We provide a thorough investigation of several online principal-agent problem settings and characterize their sample complexities, accompanied by the corresponding algorithms we have developed. We instantiate this paradigm to several important design problems $-$ including Stackelberg (security) games, contract design, and information design. Finally, we also explore the connection between our findings and existing results about online learning in Stackelberg games, and we offer a solution that can overcome a key hard instance of Peng et al. (2019).
Authors: Alexander M. Moore, Randy C. Paffenroth, Kenneth T. Ngo, Joshua R. Uzarski
Multivariate time series data are ubiquitous in the application of machine learning to problems in the physical sciences. Chemiresistive sensor arrays are highly promising in chemical detection tasks relevant to industrial, safety, and military applications. Sensor arrays are an inherently multivariate time series data collection tool which demand rapid and accurate classification of arbitrary chemical analytes. Previous research has benchmarked data-agnostic multivariate time series classifiers across diverse multivariate time series supervised tasks in order to find general-purpose classification algorithms. To our knowledge, there has yet to be an effort to survey machine learning and time series classification approaches to chemiresistive hardware sensor arrays for the detection of chemical analytes. In addition to benchmarking existing approaches to multivariate time series classifiers, we incorporate findings from a model survey to propose the novel \textit{ChemTime} approach to sensor array classification for chemical sensing. We design experiments addressing the unique challenges of hardware sensor arrays classification including the rapid classification ability of classifiers and minimization of inference time while maintaining performance for deployed lightweight hardware sensing devices. We find that \textit{ChemTime} is uniquely positioned for the chemical sensing task by combining rapid and early classification of time series with beneficial inference and high accuracy.
Authors: Faïcel Chamroukhi, Nhat Thien Pham
In modern machine learning problems we deal with datasets that are either distributed by nature or potentially large for which distributing the computations is usually a standard way to proceed, since centralized algorithms are in general ineffective. We propose a distributed learning approach for mixtures of experts (MoE) models with an aggregation strategy to construct a reduction estimator from local estimators fitted parallelly to distributed subsets of the data. The aggregation is based on an optimal minimization of an expected transportation divergence between the large MoE composed of local estimators and the unknown desired MoE model. We show that the provided reduction estimator is consistent as soon as the local estimators to be aggregated are consistent, and its construction is performed by a proposed majorization-minimization (MM) algorithm that is computationally effective. We study the statistical and numerical properties for the proposed reduction estimator on experiments that demonstrate its performance compared to namely the global estimator constructed in a centralized way from the full dataset. For some situations, the computation time is more than ten times faster, for a comparable performance. Our source codes are publicly available on Github.
Authors: Shunxin Guo, Hongsong Wang, Xin Geng
Federated learning shows promise as a privacy-preserving collaborative learning technique. Existing heterogeneous federated learning mainly focuses on skewing the label distribution across clients. However, most approaches suffer from catastrophic forgetting and concept drift, mainly when the global distribution of all classes is extremely unbalanced and the data distribution of the client dynamically evolves over time. In this paper, we study the new task, i.e., Dynamic Heterogeneous Federated Learning (DHFL), which addresses the practical scenario where heterogeneous data distributions exist among different clients and dynamic tasks within the client. Accordingly, we propose a novel federated learning framework named Federated Multi-Level Prototypes (FedMLP) and design federated multi-level regularizations. To mitigate concept drift, we construct prototypes and semantic prototypes to provide fruitful generalization knowledge and ensure the continuity of prototype spaces. To maintain the model stability and consistency of convergence, three regularizations are introduced as training losses, i.e., prototype-based regularization, semantic prototype-based regularization, and federated inter-task regularization. Extensive experiments show that the proposed method achieves state-of-the-art performance in various settings.
Authors: Jayesh Malaviya, Anirban Dasgupta, Rachit Chhaya
While coresets have been growing in terms of their application, barring few exceptions, they have mostly been limited to unsupervised settings. We consider supervised classification problems, and non-decomposable evaluation measures in such settings. We show that stratified uniform sampling based coresets have excellent empirical performance that are backed by theoretical guarantees too. We focus on the F1 score and Matthews Correlation Coefficient, two widely used non-decomposable objective functions that are nontrivial to optimize for and show that uniform coresets attain a lower bound for coreset size, and have good empirical performance, comparable with ``smarter'' coreset construction strategies.
Authors: Felipe Álvarez-Barrientos, Mariana Salinas-Camus, Simone Pezzuto, Francisco Sahli Costabal
The identification of the Purkinje conduction system in the heart is a challenging task, yet essential for a correct definition of cardiac digital twins for precision cardiology. Here, we propose a probabilistic approach for identifying the Purkinje network from non-invasive clinical data such as the standard electrocardiogram (ECG). We use cardiac imaging to build an anatomically accurate model of the ventricles; we algorithmically generate a rule-based Purkinje network tailored to the anatomy; we simulate physiological electrocardiograms with a fast model; we identify the geometrical and electrical parameters of the Purkinje-ECG model with Bayesian optimization and approximate Bayesian computation. The proposed approach is inherently probabilistic and generates a population of plausible Purkinje networks, all fitting the ECG within a given tolerance. In this way, we can estimate the uncertainty of the parameters, thus providing reliable predictions. We test our methodology in physiological and pathological scenarios, showing that we are able to accurately recover the ECG with our model. We propagate the uncertainty in the Purkinje network parameters in a simulation of conduction system pacing therapy. Our methodology is a step forward in creation of digital twins from non-invasive data in precision medicine. An open source implementation can be found at this http URL
Authors: Yizhe Zhang, Shuo Wang, Tao Zhou, Qi Dou, Danny Z. Chen
Segmentation quality assessment (SQA) plays a critical role in the deployment of a medical image based AI system. Users need to be informed/alerted whenever an AI system generates unreliable/incorrect predictions. With the introduction of the Segment Anything Model (SAM), a general foundation segmentation model, new research opportunities emerged in how one can utilize SAM for medical image segmentation. In this paper, we propose a novel SQA method, called SQA-SAM, which exploits SAM to enhance the accuracy of quality assessment for medical image segmentation. When a medical image segmentation model (MedSeg) produces predictions for a test image, we generate visual prompts based on the predictions, and SAM is utilized to generate segmentation maps corresponding to the visual prompts. How well MedSeg's segmentation aligns with SAM's segmentation indicates how well MedSeg's segmentation aligns with the general perception of objectness and image region partition. We develop a score measure for such alignment. In experiments, we find that the generated scores exhibit moderate to strong positive correlation (in Pearson correlation and Spearman correlation) with Dice coefficient scores reflecting the true segmentation quality.
Authors: Harris Papadopoulos
Venn Prediction (VP) is a new machine learning framework for producing well-calibrated probabilistic predictions. In particular it provides well-calibrated lower and upper bounds for the conditional probability of an example belonging to each possible class of the problem at hand. This paper proposes five VP methods based on Neural Networks (NNs), which is one of the most widely used machine learning techniques. The proposed methods are evaluated experimentally on four benchmark datasets and the obtained results demonstrate the empirical well-calibratedness of their outputs and their superiority over the outputs of the traditional NN classifier.
Authors: Lei Chen, Xiaohui Zhong, Jie Wu, Deliang Chen, Shangping Xie, Qingchen Chao, Chensen Lin, Zixin Hu, Bo Lu, Hao Li, Yuan Qi
Skillful subseasonal forecasts beyond 2 weeks are crucial for a wide range of applications across various sectors of society. Recently, state-of-the-art machine learning based weather forecasting models have made significant advancements, outperforming the high-resolution forecast (HRES) from the European Centre for Medium-Range Weather Forecasts (ECMWF). However, the full potential of machine learning models in subseasonal forecasts has yet to be fully explored. In this study, we introduce FuXi Subseasonal-to-Seasonal (FuXi-S2S), a machine learning based subseasonal forecasting model that provides global daily mean forecasts up to 42 days, covering 5 upper-air atmospheric variables at 13 pressure levels and 11 surface variables. FuXi-S2S integrates an enhanced FuXi base model with a perturbation module for flow-dependent perturbations in hidden features, and incorporates Perlin noise to perturb initial conditions. The model is developed using 72 years of daily statistics from ECMWF ERA5 reanalysis data. When compared to the ECMWF Subseasonal-to-Seasonal (S2S) reforecasts, the FuXi-S2S forecasts demonstrate superior deterministic and ensemble forecasts for total precipitation (TP), outgoing longwave radiation (OLR), and geopotential at 500 hPa (Z500). Although it shows slightly inferior performance in predicting 2-meter temperature (T2M), it has clear advantages over land area. Regarding the extreme forecasts, FuXi-S2S outperforms ECMWF S2S globally for TP. Furthermore, FuXi-S2S forecasts surpass the ECMWF S2S reforecasts in predicting the Madden Julian Oscillation (MJO), a key source of subseasonal predictability. They extend the skillful prediction of MJO from 30 days to 36 days.
Authors: Milad Kazemi, Mateo Perez, Fabio Somenzi, Sadegh Soudjani, Ashutosh Trivedi, Alvaro Velasquez
We present a modular approach to \emph{reinforcement learning} (RL) in environments consisting of simpler components evolving in parallel. A monolithic view of such modular environments may be prohibitively large to learn, or may require unrealizable communication between the components in the form of a centralized controller. Our proposed approach is based on the assume-guarantee paradigm where the optimal control for the individual components is synthesized in isolation by making \emph{assumptions} about the behaviors of neighboring components, and providing \emph{guarantees} about their own behavior. We express these \emph{assume-guarantee contracts} as regular languages and provide automatic translations to scalar rewards to be used in RL. By combining local probabilities of satisfaction for each component, we provide a lower bound on the probability of satisfaction of the complete system. By solving a Markov game for each component, RL can produce a controller for each component that maximizes this lower bound. The controller utilizes the information it receives through communication, observations, and any knowledge of a coarse model of other agents. We experimentally demonstrate the efficiency of the proposed approach on a variety of case studies.
Authors: Sahil Nokhwal, Suman Nokhwal, Ram Swaroop, Raj Bala, Ankit Chaudhary
In this pioneering research paper, we present a groundbreaking exploration into the synergistic fusion of classical and quantum computing paradigms within the realm of Generative Adversarial Networks (GANs). Our objective is to seamlessly integrate quantum computational elements into the conventional GAN architecture, thereby unlocking novel pathways for enhanced training processes.
Drawing inspiration from the inherent capabilities of quantum bits (qubits), we delve into the incorporation of quantum data representation methodologies within the GAN framework. By capitalizing on the unique quantum features, we aim to accelerate the training process of GANs, offering a fresh perspective on the optimization of generative models.
Our investigation deals with theoretical considerations and evaluates the potential quantum advantages that may manifest in terms of training efficiency and generative quality. We confront the challenges inherent in the quantum-classical amalgamation, addressing issues related to quantum hardware constraints, error correction mechanisms, and scalability considerations. This research is positioned at the forefront of quantum-enhanced machine learning, presenting a critical stride towards harnessing the computational power of quantum systems to expedite the training of Generative Adversarial Networks. Through our comprehensive examination of the interface between classical and quantum realms, we aim to uncover transformative insights that will propel the field forward, fostering innovation and advancing the frontier of quantum machine learning.
Authors: Ayoub Belhadji, Rémi Gribonval
Compressive learning is an emerging approach to drastically reduce the memory footprint of large-scale learning, by first summarizing a large dataset into a low-dimensional sketch vector, and then decoding from this sketch the latent information needed for learning. In light of recent progress on information preservation guarantees for sketches based on random features, a major objective is to design easy-to-tune algorithms (called decoders) to robustly and efficiently extract this information. To address the underlying non-convex optimization problems, various heuristics have been proposed. In the case of compressive clustering, the standard heuristic is CL-OMPR, a variant of sliding Frank-Wolfe. Yet, CL-OMPR is hard to tune, and the examination of its robustness was overlooked. In this work, we undertake a scrutinized examination of CL-OMPR to circumvent its limitations. In particular, we show how this algorithm can fail to recover the clusters even in advantageous scenarios. To gain insight, we show how the deficiencies of this algorithm can be attributed to optimization difficulties related to the structure of a correlation function appearing at core steps of the algorithm. To address these limitations, we propose an alternative decoder offering substantial improvements over CL-OMPR. Its design is notably inspired from the mean shift algorithm, a classic approach to detect the local maxima of kernel density estimators. The proposed algorithm can extract clustering information from a sketch of the MNIST dataset that is 10 times smaller than previously.
Authors: Cedric Derstroff, Mattia Cerrato, Jannis Brugger, Jan Peters, Stefan Kramer
Peer learning is a novel high-level reinforcement learning framework for agents learning in groups. While standard reinforcement learning trains an individual agent in trial-and-error fashion, all on its own, peer learning addresses a related setting in which a group of agents, i.e., peers, learns to master a task simultaneously together from scratch. Peers are allowed to communicate only about their own states and actions recommended by others: "What would you do in my situation?". Our motivation is to study the learning behavior of these agents. We formalize the teacher selection process in the action advice setting as a multi-armed bandit problem and therefore highlight the need for exploration. Eventually, we analyze the learning behavior of the peers and observe their ability to rank the agents' performance within the study group and understand which agents give reliable advice. Further, we compare peer learning with single agent learning and a state-of-the-art action advice baseline. We show that peer learning is able to outperform single-agent learning and the baseline in several challenging discrete and continuous OpenAI Gym domains. Doing so, we also show that within such a framework complex policies from action recommendations beyond discrete action spaces can evolve.
Authors: Jose A. Ayala-Romero, Andres Garcia-Saavedra, Xavier Costa-Perez
Recent advances in learning techniques have garnered attention for their applicability to a diverse range of real-world sequential decision-making problems. Yet, many practical applications have critical constraints for operation in real environments. Most learning solutions often neglect the risk of failing to meet these constraints, hindering their implementation in real-world contexts. In this paper, we propose a risk-aware decision-making framework for contextual bandit problems, accommodating constraints and continuous action spaces. Our approach employs an actor multi-critic architecture, with each critic characterizing the distribution of performance and constraint metrics. Our framework is designed to cater to various risk levels, effectively balancing constraint satisfaction against performance. To demonstrate the effectiveness of our approach, we first compare it against state-of-the-art baseline methods in a synthetic environment, highlighting the impact of intrinsic environmental noise across different risk configurations. Finally, we evaluate our framework in a real-world use case involving a 5G mobile network where only our approach consistently satisfies the system constraint (a signal processing reliability target) with a small performance toll (8.5% increase in power consumption).
Authors: François Portier, Lionel Truquet, Ikko Yamane
Many existing covariate shift adaptation methods estimate sample weights to be used in the risk estimation in order to mitigate the gap between the source and the target distribution. However, non-parametrically estimating the optimal weights typically involves computationally expensive hyper-parameter tuning that is crucial to the final performance. In this paper, we propose a new non-parametric approach to covariate shift adaptation which avoids estimating weights and has no hyper-parameter to be tuned. Our basic idea is to label unlabeled target data according to the $k$-nearest neighbors in the source dataset. Our analysis indicates that setting $k = 1$ is an optimal choice. Thanks to this property, there is no need to tune any hyper-parameters, unlike other non-parametric methods. Moreover, our method achieves a running time quasi-linear in the sample size with a theoretical guarantee, for the first time in the literature to the best of our knowledge. Our results include sharp rates of convergence for estimating the joint probability distribution of the target data. In particular, the variance of our estimators has the same rate of convergence as for standard parametric estimation despite their non-parametric nature. Our numerical experiments show that proposed method brings drastic reduction in the running time with accuracy comparable to that of the state-of-the-art methods.
Authors: Jose Duato, Jose I. Mestre, Manuel F. Dolz, Enrique S. Quintana-Ortí
The number and complexity of artificial intelligence (AI) applications is growing relentlessly. As a result, even with the many algorithmic and mathematical advances experienced over past decades as well as the impressive energy efficiency and computational capacity of current hardware accelerators, training the most powerful and popular deep neural networks comes at very high economic and environmental costs. Recognising that additional optimisations of conventional neural network training is very difficult, this work takes a radically different approach by proposing GreenLightningAI, a new AI system design consisting of a linear model that is capable of emulating the behaviour of deep neural networks by subsetting the model for each particular sample. The new AI system stores the information required to select the system subset for a given sample (referred to as structural information) separately from the linear model parameters (referred to as quantitative knowledge). In this paper we present a proof of concept, showing that the structural information stabilises far earlier than the quantitative knowledge. Additionally, we show experimentally that the structural information can be kept unmodified when re-training the AI system with new samples while still achieving a validation accuracy similar to that obtained when re-training a neural network with similar size. Since the proposed AI system is based on a linear model, multiple copies of the model, trained with different datasets, can be easily combined. This enables faster and greener (re)-training algorithms, including incremental re-training and federated incremental re-training.
Authors: C. J. Wright, N. Biederman, B. Gyovai, D. J. Gauthier, J. P. Wilhelm
Machine learning was applied to create a digital twin of a numerical simulation of a single-scroll jet engine. A similar model based on the insights gained from this numerical study was used to create a digital twin of a JetCat P100-RX jet engine using only experimental data. Engine data was collected from a custom sensor system measuring parameters such as thrust, exhaust gas temperature, shaft speed, weather conditions, etc. Data was gathered while the engine was placed under different test conditions by controlling shaft speed. The machine learning model was generated (trained) using a next-generation reservoir computer, a best-in-class machine learning algorithm for dynamical systems. Once the model was trained, it was used to predict behavior it had never seen with an accuracy of better than 1.8% when compared to the testing data.
Authors: Amir H. Ashouri, Muhammad Asif Manzoor, Duc Minh Vu, Raymond Zhang, Ziwen Wang, Angel Zhang, Bryan Chan, Tomasz S. Czajkowski, Yaoqing Gao
The key to performance optimization of a program is to decide correctly when a certain transformation should be applied by a compiler. Traditionally, such profitability decisions are made by hand-coded algorithms tuned for a very small number of benchmarks, usually requiring a great deal of effort to be retuned when the benchmark suite changes. This is an ideal opportunity to apply machine-learning models to speed up the tuning process; while this realization has been around since the late 90s, only recent advancements in ML enabled a practical application of ML to compilers as an end-to-end framework. Even so, seamless integration of ML into the compiler would require constant rebuilding of the compiler when models are updated.
This paper presents ACPO: \textbf{\underline{A}}I-Enabled \textbf{\underline{C}}ompiler-driven \textbf{\underline{P}}rogram \textbf{\underline{O}}ptimization; a novel framework to provide LLVM with simple and comprehensive tools to benefit from employing ML models for different optimization passes. We first showcase the high-level view, class hierarchy, and functionalities of ACPO and subsequently, demonstrate \taco{a couple of use cases of ACPO by ML-enabling the Loop Unroll and Function Inlining passes and describe how ACPO can be leveraged to optimize other passes. Experimental results reveal that ACPO model for Loop Unroll is able to gain on average 4\% and 3\%, 5.4\%, 0.2\% compared to LLVM's O3 optimization when deployed on Polybench, Coral-2, CoreMark, and Graph-500, respectively. Furthermore, by adding the Inliner model as well, ACPO is able to provide up to 4.5\% and 2.4\% on Polybench and Cbench compared with LLVM's O3 optimization, respectively.
Authors: Lauren H. Cooke, Harvey Klyne, Edwin Zhang, Cassidy Laidlaw, Milind Tambe, Finale Doshi-Velez
Inverse reinforcement learning (IRL) is computationally challenging, with common approaches requiring the solution of multiple reinforcement learning (RL) sub-problems. This work motivates the use of potential-based reward shaping to reduce the computational burden of each RL sub-problem. This work serves as a proof-of-concept and we hope will inspire future developments towards computationally efficient IRL.
Authors: Mikołaj Małkiński, Jacek Mańdziuk
Abstract Visual Reasoning (AVR) comprises a wide selection of various problems similar to those used in human IQ tests. Recent years have brought dynamic progress in solving particular AVR tasks, however, in the contemporary literature AVR problems are largely dealt with in isolation, leading to highly specialized task-specific methods. With the aim of developing universal learning systems in the AVR domain, we propose the unified model for solving Single-Choice Abstract visual Reasoning tasks (SCAR), capable of solving various single-choice AVR tasks, without making any a priori assumptions about the task structure, in particular the number and location of panels. The proposed model relies on a novel Structure-Aware dynamic Layer (SAL), which adapts its weights to the structure of the considered AVR problem. Experiments conducted on Raven's Progressive Matrices, Visual Analogy Problems, and Odd One Out problems show that SCAR (SAL-based models, in general) effectively solves diverse AVR tasks, and its performance is on par with the state-of-the-art task-specific baselines. What is more, SCAR demonstrates effective knowledge reuse in multi-task and transfer learning settings. To our knowledge, this work is the first successful attempt to construct a general single-choice AVR solver relying on self-configurable architecture and unified solving method. With this work we aim to stimulate and foster progress on task-independent research paths in the AVR domain, with the long-term goal of development of a general AVR solver.
Authors: Zhongshu Xu, Yuan Chen, Qifan Chen, Dongbin Xiu
We present a numerical method to learn an accurate predictive model for an unknown stochastic dynamical system from its trajectory data. The method seeks to approximate the unknown flow map of the underlying system. It employs the idea of autoencoder to identify the unobserved latent random variables. In our approach, we design an encoding function to discover the latent variables, which are modeled as unit Gaussian, and a decoding function to reconstruct the future states of the system. Both the encoder and decoder are expressed as deep neural networks (DNNs). Once the DNNs are trained by the trajectory data, the decoder serves as a predictive model for the unknown stochastic system. Through an extensive set of numerical examples, we demonstrate that the method is able to produce long-term system predictions by using short bursts of trajectory data. It is also applicable to systems driven by non-Gaussian noises.
Authors: Benedikt Brantner, Michael Kraus
Many applications, such as optimization, uncertainty quantification and inverse problems, require repeatedly performing simulations of large-dimensional physical systems for different choices of parameters. This can be prohibitively expensive.
In order to save computational cost, one can construct surrogate models by expressing the system in a low-dimensional basis, obtained from training data. This is referred to as model reduction.
Past investigations have shown that, when performing model reduction of Hamiltonian systems, it is crucial to preserve the symplectic structure associated with the system in order to ensure long-term numerical stability.
Up to this point structure-preserving reductions have largely been limited to linear transformations. We propose a new neural network architecture in the spirit of autoencoders, which are established tools for dimension reduction and feature extraction in data science, to obtain more general mappings.
In order to train the network, a non-standard gradient descent approach is applied that leverages the differential-geometric structure emerging from the network design.
The new architecture is shown to significantly outperform existing designs in accuracy.
Authors: Pegah Jandaghi, XiangHai Sheng, Xinyi Bai, Jay Pujara, Hakim Sidahmed
High-quality conversational datasets are essential for developing AI models that can communicate with users. One way to foster deeper interactions between a chatbot and its user is through personas, aspects of the user's character that provide insights into their personality, motivations, and behaviors. Training Natural Language Processing (NLP) models on a diverse and comprehensive persona-based dataset can lead to conversational models that create a deeper connection with the user, and maintain their engagement. In this paper, we leverage the power of Large Language Models (LLMs) to create a large, high-quality conversational dataset from a seed dataset. We propose a Generator-Critic architecture framework to expand the initial dataset, while improving the quality of its conversations. The Generator is an LLM prompted to output conversations. The Critic consists of a mixture of expert LLMs that control the quality of the generated conversations. These experts select the best generated conversations, which we then use to improve the Generator. We release Synthetic-Persona-Chat, consisting of 20k conversations seeded from Persona-Chat. We evaluate the quality of Synthetic-Persona-Chat and our generation framework on different dimensions through extensive experiments, and observe that the losing rate of Synthetic-Persona-Chat against Persona-Chat during Turing test decreases from 17.2% to 8.8% over three iterations.
Authors: Paul Maria Scheikl, Nicolas Schreiber, Christoph Haas, Niklas Freymuth, Gerhard Neumann, Rudolf Lioutikov, Franziska Mathis-Ullrich
Policy learning in robot-assisted surgery (RAS) lacks data efficient and versatile methods that exhibit the desired motion quality for delicate surgical interventions. To this end, we introduce Movement Primitive Diffusion (MPD), a novel method for imitation learning (IL) in RAS that focuses on gentle manipulation of deformable objects. The approach combines the versatility of diffusion-based imitation learning (DIL) with the high-quality motion generation capabilities of Probabilistic Dynamic Movement Primitives (ProDMPs). This combination enables MPD to achieve gentle manipulation of deformable objects, while maintaining data efficiency critical for RAS applications where demonstration data is scarce. We evaluate MPD across various simulated tasks and a real world robotic setup on both state and image observations. MPD outperforms state-of-the-art DIL methods in success rate, motion quality, and data efficiency.
Authors: Kwanghee Choi, Jee-weon Jung, Shinji Watanabe
With the success of self-supervised representations, researchers seek a better understanding of the information encapsulated within a representation. Among various interpretability methods, we focus on classification-based linear probing. We aim to foster a solid understanding and provide guidelines for linear probing by constructing a novel mathematical framework leveraging information theory. First, we connect probing with the variational bounds of mutual information (MI) to relax the probe design, equating linear probing with fine-tuning. Then, we investigate empirical behaviors and practices of probing through our mathematical framework. We analyze the layer-wise performance curve being convex, which seemingly violates the data processing inequality. However, we show that the intermediate representations can have the biggest MI estimate because of the tradeoff between better separability and decreasing MI. We further suggest that the margin of linearly separable representations can be a criterion for measuring the "goodness of representation." We also compare accuracy with MI as the measuring criteria. Finally, we empirically validate our claims by observing the self-supervised speech models on retaining word and phoneme information.
Authors: Yu Duan, Matthew Eaton, Michael Bluck
In this paper, we introduce an efficient sparse Gaussian process (E-SGP) for the surrogate modelling of fluid mechanics. This novel Bayesian machine learning algorithm allows efficient model training using databases of different structures. It is a further development of the approximated sparse GP algorithm, combining the concept of efficient GP (E-GP) and variational energy free sparse Gaussian process (VEF-SGP). The developed E-SGP approach exploits the arbitrariness of inducing points and the monotonically increasing nature of the objective function with respect to the number of inducing points in VEF-SGP. By specifying the inducing points on the orthogonal grid/input subspace and using the Kronecker product, E-SGP significantly improves computational efficiency without imposing any constraints on the covariance matrix or increasing the number of parameters that need to be optimised during training.
The E-SGP algorithm developed in this paper outperforms E-GP not only in scalability but also in model quality in terms of mean standardized logarithmic loss (MSLL). The computational complexity of E-GP suffers from the cubic growth regarding the growing structured training database. However, E-SGP maintains computational efficiency whilst the resolution of the model, (i.e., the number of inducing points) remains fixed. The examples show that E-SGP produces more accurate predictions in comparison with E-GP when the model resolutions are similar in both. E-GP benefits from more training data but comes with higher computational demands, while E-SGP achieves a comparable level of accuracy but is more computationally efficient, making E-SGP a potentially preferable choice for fluid mechanic problems. Furthermore, E-SGP can produce more reasonable estimates of model uncertainty, whilst E-GP is more likely to produce over-confident predictions.
Authors: Sahil Nokhwal, Priyanka Chilakalapudi, Preeti Donekal, Manoj Chandrasekharan, Suman Nokhwal, Ram Swaroop, Raj Bala, Saurabh Pahune, Ankit Chaudhary
The process of training a deep neural network is characterized by significant time requirements and associated costs. Although researchers have made considerable progress in this area, further work is still required due to resource constraints. This study examines innovative approaches to expedite the training process of deep neural networks (DNN), with specific emphasis on three state-of-the-art models such as ResNet50, Vision Transformer (ViT), and EfficientNet. The research utilizes sophisticated methodologies, including Gradient Accumulation (GA), Automatic Mixed Precision (AMP), and Pin Memory (PM), in order to optimize performance and accelerate the training procedure.
The study examines the effects of these methodologies on the DNN models discussed earlier, assessing their efficacy with regard to training rate and computational efficacy. The study showcases the efficacy of including GA as a strategic approach, resulting in a noteworthy decrease in the duration required for training. This enables the models to converge at a faster pace. The utilization of AMP enhances the speed of computations by taking advantage of the advantages offered by lower precision arithmetic while maintaining the correctness of the model.
Furthermore, this study investigates the application of Pin Memory as a strategy to enhance the efficiency of data transmission between the central processing unit and the graphics processing unit, thereby offering a promising opportunity for enhancing overall performance. The experimental findings demonstrate that the combination of these sophisticated methodologies significantly accelerates the training of DNNs, offering vital insights for experts seeking to improve the effectiveness of deep learning processes.
Authors: Sebastian Farquhar, Vikrant Varma, Zachary Kenton, Johannes Gasteiger, Vladimir Mikulik, Rohin Shah
We show that existing unsupervised methods on large language model (LLM) activations do not discover knowledge -- instead they seem to discover whatever feature of the activations is most prominent. The idea behind unsupervised knowledge elicitation is that knowledge satisfies a consistency structure, which can be used to discover knowledge. We first prove theoretically that arbitrary features (not just knowledge) satisfy the consistency structure of a particular leading unsupervised knowledge-elicitation method, contrast-consistent search (Burns et al. - arXiv:2212.03827). We then present a series of experiments showing settings in which unsupervised methods result in classifiers that do not predict knowledge, but instead predict a different prominent feature. We conclude that existing unsupervised methods for discovering latent knowledge are insufficient, and we contribute sanity checks to apply to evaluating future knowledge elicitation methods. Conceptually, we hypothesise that the identification issues explored here, e.g. distinguishing a model's knowledge from that of a simulated character's, will persist for future unsupervised methods.
Authors: Nina M. Gottschling, Vegard Antun, Anders C. Hansen, Ben Adcock
Methods inspired by Artificial Intelligence (AI) are starting to fundamentally change computational science and engineering through breakthrough performances on challenging problems. However, reliability and trustworthiness of such techniques is becoming a major concern. In inverse problems in imaging, the focus of this paper, there is increasing empirical evidence that methods may suffer from hallucinations, i.e., false, but realistic-looking artifacts; instability, i.e., sensitivity to perturbations in the data; and unpredictable generalization, i.e., excellent performance on some images, but significant deterioration on others. This paper presents a theoretical foundation for these phenomena. We give a mathematical framework describing how and when such effects arise in arbitrary reconstruction methods, not just AI-inspired techniques. Several of our results take the form of `no free lunch' theorems. Specifically, we show that (i) methods that overperform on a single image can wrongly transfer details from one image to another, creating a hallucination, (ii) methods that overperform on two or more images can hallucinate or be unstable, (iii) optimizing the accuracy-stability trade-off is generally difficult, (iv) hallucinations and instabilities, if they occur, are not rare events, and may be encouraged by standard training, (v) it may be impossible to construct optimal reconstruction maps for certain problems. Our results trace these effects to the kernel of the forward operator whenever it is nontrivial, but also extend to the case when the forward operator is ill-conditioned. Based on these insights, our work aims to spur research into new ways to develop robust and reliable AI-inspired methods for inverse problems in imaging.
Authors: Hamid Mousavi, Jakob Drefs, Florian Hirschberger, Jörg Lücke
Latent variable models (LVMs) represent observed variables by parameterized functions of latent variables. Prominent examples of LVMs for unsupervised learning are probabilistic PCA or probabilistic SC which both assume a weighted linear summation of the latents to determine the mean of a Gaussian distribution for the observables. In many cases, however, observables do not follow a Gaussian distribution. For unsupervised learning, LVMs which assume specific non-Gaussian observables have therefore been considered. Already for specific choices of distributions, parameter optimization is challenging and only a few previous contributions considered LVMs with more generally defined observable distributions. Here, we consider LVMs that are defined for a range of different distributions, i.e., observables can follow any (regular) distribution of the exponential family. The novel class of LVMs presented is defined for binary latents, and it uses maximization in place of summation to link the latents to observables. To derive an optimization procedure, we follow an EM approach for maximum likelihood parameter estimation. We show that a set of very concise parameter update equations can be derived which feature the same functional form for all exponential family distributions. The derived generic optimization can consequently be applied to different types of metric data as well as to different types of discrete data. Also, the derived optimization equations can be combined with a recently suggested variational acceleration which is likewise generically applicable to the LVMs considered here. So, the combination maintains generic and direct applicability of the derived optimization procedure, but, crucially, enables efficient scalability. We numerically verify our analytical results and discuss some potential applications such as learning of variance structure, noise type estimation and denoising.
Authors: Ruan de Kock, Omayma Mahjoub, Sasha Abramowitz, Wiem Khlifi, Callum Rhys Tilbury, Claude Formanek, Andries Smit, Arnu Pretorius
Multi-agent reinforcement learning (MARL) research is inherently computationally expensive and it is often difficult to obtain a sufficient number of experiment samples to test hypotheses and make robust statistical claims. Furthermore, MARL algorithms are typically complex in their design and can be tricky to implement correctly. These aspects of MARL present a difficult challenge when it comes to creating useful software for advanced research. Our criteria for such software is that it should be simple enough to use to implement new ideas quickly, while at the same time be scalable and fast enough to test those ideas in a reasonable amount of time. In this preliminary technical report, we introduce Mava, a research library for MARL written purely in JAX, that aims to fulfill these criteria. We discuss the design and core features of Mava, and demonstrate its use and performance across a variety of environments. In particular, we show Mava's substantial speed advantage, with improvements of 10-100x compared to other popular MARL frameworks, while maintaining strong performance. This allows for researchers to test ideas in a few minutes instead of several hours. Finally, Mava forms part of an ecosystem of libraries that seamlessly integrate with each other to help facilitate advanced research in MARL. We hope Mava will benefit the community and help drive scientifically sound and statistically robust research in the field. The open-source repository for Mava is available at https://github.com/instadeepai/Mava.
Authors: Ruijie Jiang, Prakash Ishwar, Shuchin Aeron
We study the problem of designing hard negative sampling distributions for unsupervised contrastive representation learning. We propose and analyze a novel min-max framework that seeks a representation which minimizes the maximum (worst-case) generalized contrastive learning loss over all couplings (joint distributions between positive and negative samples subject to marginal constraints) and prove that the resulting min-max optimum representation will be degenerate. This provides the first theoretical justification for incorporating additional regularization constraints on the couplings. We re-interpret the min-max problem through the lens of Optimal Transport (OT) theory and utilize regularized transport couplings to control the degree of hardness of negative examples. Through experiments we demonstrate that the negative samples generated from our designed negative distribution are more similar to the anchor than those generated from the baseline negative distribution. We also demonstrate that entropic regularization yields negative sampling distributions with parametric form similar to that in a recent state-of-the-art negative sampling design and has similar performance in multiple datasets. Utilizing the uncovered connection with OT, we propose a new ground cost for designing the negative distribution and show improved performance of the learned representation on downstream tasks compared to the representation learned when using squared Euclidean cost.
Authors: Raphaël Pestourie, Youssef Mroueh, Chris Rackauckas, Payel Das, Steven G. Johnson
Many physics and engineering applications demand Partial Differential Equations (PDE) property evaluations that are traditionally computed with resource-intensive high-fidelity numerical solvers. Data-driven surrogate models provide an efficient alternative but come with a significant cost of training. Emerging applications would benefit from surrogates with an improved accuracy-cost tradeoff, while studied at scale. Here we present a "physics-enhanced deep-surrogate" ("PEDS") approach towards developing fast surrogate models for complex physical systems, which is described by PDEs. Specifically, a combination of a low-fidelity, explainable physics simulator and a neural network generator is proposed, which is trained end-to-end to globally match the output of an expensive high-fidelity numerical solver. Experiments on three exemplar testcases, diffusion, reaction-diffusion, and electromagnetic scattering models, show that a PEDS surrogate can be up to 3$\times$ more accurate than an ensemble of feedforward neural networks with limited data ($\approx 10^3$ training points), and reduces the training data need by at least a factor of 100 to achieve a target error of 5%. Experiments reveal that PEDS provides a general, data-driven strategy to bridge the gap between a vast array of simplified physical models with corresponding brute-force numerical solvers modeling complex systems, offering accuracy, speed, data efficiency, as well as physical insights into the process.
Authors: Mariel Werner, Anastasios Angelopoulos, Stephen Bates, Michael I. Jordan
The blessing of ubiquitous data also comes with a curse: the communication, storage, and labeling of massive, mostly redundant datasets. We seek to solve this problem at its core, collecting only valuable data and throwing out the rest via submodular maximization. Specifically, we develop algorithms for the online and distributed version of the problem, where data selection occurs in an uncoordinated fashion across multiple data streams. We design a general and flexible core selection routine for our algorithms which, given any stream of data, any assessment of its value, and any formulation of its selection cost, extracts the most valuable subset of the stream up to a constant factor while using minimal memory. Notably, our methods have the same theoretical guarantees as their offline counterparts, and, as far as we know, provide the first guarantees for online distributed submodular optimization in the literature. Finally, in learning tasks on ImageNet and MNIST, we show that our selection methods outperform random selection by $5-20\%$.
Authors: Zhiqin Zhu, Zheng Yao, Guanqiu Qi, Neal Mazur, Baisen Cong
As a necessary process in drug development, finding a drug compound that can selectively bind to a specific protein is highly challenging and costly. Drug-target affinity (DTA), which represents the strength of drug-target interaction (DTI), has played an important role in the DTI prediction task over the past decade. Although deep learning has been applied to DTA-related research, existing solutions ignore fundamental correlations between molecular substructures in molecular representation learning of drug compound molecules/protein targets. Moreover, traditional methods lack the interpretability of the DTA prediction process. This results in missing feature information of intermolecular interactions, thereby affecting prediction performance. Therefore, this paper proposes a DTA prediction method with interactive learning and an autoencoder mechanism. The proposed model enhances the corresponding ability to capture the feature information of a single molecular sequence by the drug/protein molecular representation learning module and supplements the information interaction between molecular sequence pairs by the interactive information learning module. The DTA value prediction module fuses the drug-target pair interaction information to output the predicted value of DTA. Additionally, this paper theoretically proves that the proposed method maximizes evidence lower bound (ELBO) for the joint distribution of the DTA prediction model, which enhances the consistency of the probability distribution between the actual value and the predicted value. The experimental results confirm mutual transformer-drug target affinity (MT-DTA) achieves better performance than other comparative methods.
Authors: Florian Krach, Marc Nübel, Josef Teichmann
This paper studies the problem of forecasting general stochastic processes using a path-dependent extension of the Neural Jump ODE (NJ-ODE) framework \citep{herrera2021neural}. While NJ-ODE was the first framework to establish convergence guarantees for the prediction of irregularly observed time series, these results were limited to data stemming from It\^o-diffusions with complete observations, in particular Markov processes, where all coordinates are observed simultaneously. In this work, we generalise these results to generic, possibly non-Markovian or discontinuous, stochastic processes with incomplete observations, by utilising the reconstruction properties of the signature transform. These theoretical results are supported by empirical studies, where it is shown that the path-dependent NJ-ODE outperforms the original NJ-ODE framework in the case of non-Markovian data. Moreover, we show that PD-NJ-ODE can be applied successfully to classical stochastic filtering problems and to limit order book (LOB) data.
Authors: Brandon Victor, Zhen He, Aiden Nibali
Agricultural research is essential for increasing food production to meet the requirements of an increasing population in the coming decades. Recently, satellite technology has been improving rapidly and deep learning has seen much success in generic computer vision tasks and many application areas which presents an important opportunity to improve analysis of agricultural land. Here we present a systematic review of 150 studies to find the current uses of deep learning on satellite imagery for agricultural research. Although we identify 5 categories of agricultural monitoring tasks, the majority of the research interest is in crop segmentation and yield prediction. We found that, when used, modern deep learning methods consistently outperformed traditional machine learning across most tasks; the only exception was that Long Short-Term Memory (LSTM) Recurrent Neural Networks did not consistently outperform Random Forests (RF) for yield prediction. The reviewed studies have largely adopted methodologies from generic computer vision, except for one major omission: benchmark datasets are not utilised to evaluate models across studies, making it difficult to compare results. Additionally, some studies have specifically utilised the extra spectral resolution available in satellite imagery, but other divergent properties of satellite images - such as the hugely different scales of spatial patterns - are not being taken advantage of in the reviewed studies.
Authors: Ernesto Arganda, Andres D. Perez, Martin de los Rios, Rosa María Sandá Seoane
Machine-Learned Likelihoods (MLL) combines machine-learning classification techniques with likelihood-based inference tests to estimate the experimental sensitivity of high-dimensional data sets. We extend the MLL method by including Kernel Density Estimators (KDE) to avoid binning the classifier output to extract the resulting one-dimensional signal and background probability density functions. We first test our method on toy models generated with multivariate Gaussian distributions, where the true probability distribution functions are known. Later, we apply the method to two cases of interest at the LHC: a search for exotic Higgs bosons, and a $Z'$ boson decaying into lepton pairs. In contrast to physical-based quantities, the typical fluctuations of the ML outputs give non-smooth probability distributions for pure-signal and pure-background samples. The non-smoothness is propagated into the density estimation due to the good performance and flexibility of the KDE method. We study its impact on the final significance computation, and we compare the results using the average of several independent ML output realizations, which allows us to obtain smoother distributions. We conclude that the significance estimation turns out to be not sensible to this issue.
Authors: Xin Wen, Bingchen Zhao, Xiaojuan Qi
Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. Previous studies argued that parametric classifiers are prone to overfitting to seen categories, and endorsed using a non-parametric classifier formed with semi-supervised k-means. However, in this study, we investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We demonstrate that two prediction biases exist: the classifier tends to predict seen classes more often, and produces an imbalanced distribution across seen and novel categories. Based on these findings, we propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers. We hope the investigation and proposed simple framework can serve as a strong baseline to facilitate future studies in this field. Our code is available at: https://github.com/CVMI-Lab/SimGCD.
Authors: Maxwell A. Xu, Alexander Moreno, Supriya Nagesh, V. Burak Aydemir, David W. Wetter, Santosh Kumar, James M. Rehg
The promise of Mobile Health (mHealth) is the ability to use wearable sensors to monitor participant physiology at high frequencies during daily life to enable temporally-precise health interventions. However, a major challenge is frequent missing data. Despite a rich imputation literature, existing techniques are ineffective for the pulsative signals which comprise many mHealth applications, and a lack of available datasets has stymied progress. We address this gap with PulseImpute, the first large-scale pulsative signal imputation challenge which includes realistic mHealth missingness models, an extensive set of baselines, and clinically-relevant downstream tasks. Our baseline models include a novel transformer-based architecture designed to exploit the structure of pulsative signals. We hope that PulseImpute will enable the ML community to tackle this significant and challenging task.
Authors: Samira Kabri, Alexander Auras, Danilo Riccio, Hartmut Bauermeister, Martin Benning, Michael Moeller, Martin Burger
The reconstruction of images from their corresponding noisy Radon transform is a typical example of an ill-posed linear inverse problem as arising in the application of computerized tomography (CT). As the (naive) solution does not depend on the measured data continuously, regularization is needed to re-establish a continuous dependence. In this work, we investigate simple, but yet still provably convergent approaches to learning linear regularization methods from data. More specifically, we analyze two approaches: One generic linear regularization that learns how to manipulate the singular values of the linear operator in an extension of our previous work, and one tailored approach in the Fourier domain that is specific to CT-reconstruction. We prove that such approaches become convergent regularization methods as well as the fact that the reconstructions they provide are typically much smoother than the training data they were trained on. Finally, we compare the spectral as well as the Fourier-based approaches for CT-reconstruction numerically, discuss their advantages and disadvantages and investigate the effect of discretization errors at different resolutions.
Authors: Bile Peng, Karl-Ludwig Besser, Ramprasad Raghunath, Eduard A. Jorswieck
This work presents a machine learning approach to optimize the energy efficiency (EE) in a multi-cell wireless network. This optimization problem is non-convex and its global optimum is difficult to find. In the literature, either simple but suboptimal approaches or optimal methods with high complexity and poor scalability are proposed. In contrast, we propose a machine learning framework to approach the global optimum. While the neural network (NN) training takes moderate time, application with the trained model requires very low computational complexity. In particular, we introduce a novel objective function based on stochastic actions to solve the non-convex optimization problem. Besides, we design a dedicated NN architecture for the multi-cell network optimization problems that is permutation-equivariant. It classifies channels according to their roles in the EE computation. In this way, we encode our domain knowledge into the NN design and shed light into the black box of machine learning. Training and testing results show that the proposed method without supervision and with reasonable computational effort achieves an EE close to the global optimum found by the branch-and-bound algorithm. Hence, the proposed approach balances between computational complexity and performance.
Authors: Sonny Achten, Francesco Tonin, Panagiotis Patrinos, Johan A. K. Suykens
We present a deep Graph Convolutional Kernel Machine (GCKM) for semi-supervised node classification in graphs. The method is built of two main types of blocks: (i) We introduce unsupervised kernel machine layers propagating the node features in a one-hop neighborhood, using implicit node feature mappings. (ii) We specify a semi-supervised classification kernel machine through the lens of the Fenchel-Young inequality. We derive an effective initialization scheme and efficient end-to-end training algorithm in the dual variables for the full architecture. The main idea underlying GCKM is that, because of the unsupervised core, the final model can achieve higher performance in semi-supervised node classification when few labels are available for training. Experimental results demonstrate the effectiveness of the proposed framework.
Authors: Xuechen Liu, Md Sahidullah, Tomi Kinnunen
Even though deep speaker models have demonstrated impressive accuracy in speaker verification tasks, this often comes at the expense of increased model size and computation time, presenting challenges for deployment in resource-constrained environments. Our research focuses on addressing this limitation through the development of small footprint deep speaker embedding extraction using knowledge distillation. While previous work in this domain has concentrated on speaker embedding extraction at the utterance level, our approach involves amalgamating embeddings from different levels of the x-vector model (teacher network) to train a compact student network. The results highlight the significance of frame-level information, with the student models exhibiting a remarkable size reduction of 85%-91% compared to their teacher counterparts, depending on the size of the teacher embeddings. Notably, by concatenating teacher embeddings, we achieve student networks that maintain comparable performance to the teacher while enjoying a substantial 75% reduction in model size. These findings and insights extend to other x-vector variants, underscoring the broad applicability of our approach.
Authors: Hyungjin Chung, Suhyeon Lee, Jong Chul Ye
Krylov subspace, which is generated by multiplying a given vector by the matrix of a linear transformation and its successive powers, has been extensively studied in classical optimization literature to design algorithms that converge quickly for large linear inverse problems. For example, the conjugate gradient method (CG), one of the most popular Krylov subspace methods, is based on the idea of minimizing the residual error in the Krylov subspace. However, with the recent advancement of high-performance diffusion solvers for inverse problems, it is not clear how classical wisdom can be synergistically combined with modern diffusion models. In this study, we propose a novel and efficient diffusion sampling strategy that synergistically combine the diffusion sampling and Krylov subspace methods. Specifically, we prove that if the tangent space at a denoised sample by Tweedie's formula forms a Krylov subspace, then the CG initialized with the denoised data ensures the data consistency update to remain in the tangent space. This negates the need to compute the manifold-constrained gradient (MCG), leading to a more efficient diffusion sampling method. Our method is applicable regardless of the parametrization and setting (i.e., VE, VP). Notably, we achieve state-of-the-art reconstruction quality on challenging real-world medical inverse imaging problems, including multi-coil MRI reconstruction and 3D CT reconstruction. Moreover, our proposed method achieves more than 80 times faster inference time than the previous state-of-the-art method.
Authors: Jiawei Shao, Fangzhao Wu, Jun Zhang
While federated learning is promising for privacy-preserving collaborative learning without revealing local data, it remains vulnerable to white-box attacks and struggles to adapt to heterogeneous clients. Federated distillation (FD), built upon knowledge distillation--an effective technique for transferring knowledge from a teacher model to student models--emerges as an alternative paradigm, which provides enhanced privacy guarantees and addresses model heterogeneity. Nevertheless, challenges arise due to variations in local data distributions and the absence of a well-trained teacher model, which leads to misleading and ambiguous knowledge sharing that significantly degrades model performance. To address these issues, this paper proposes a selective knowledge sharing mechanism for FD, termed Selective-FD. It includes client-side selectors and a server-side selector to accurately and precisely identify knowledge from local and ensemble predictions, respectively. Empirical studies, backed by theoretical insights, demonstrate that our approach enhances the generalization capabilities of the FD framework and consistently outperforms baseline methods.
Authors: Hyeonsu Kim, Jeheon Woo, Seonghwan Kim, Seokhyun Moon, Jun Hyeong Kim, Woo Youn Kim
As quantum chemical properties have a dependence on their geometries, graph neural networks (GNNs) using 3D geometric information have achieved high prediction accuracy in many tasks. However, they often require 3D geometries obtained from high-level quantum mechanical calculations, which are practically infeasible, limiting their applicability to real-world problems. To tackle this, we propose a new training framework, GeoTMI, that employs denoising process to predict properties accurately using easy-to-obtain geometries (corrupted versions of correct geometries, such as those obtained from low-level calculations). Our starting point was the idea that the correct geometry is the best description of the target property. Hence, to incorporate information of the correct, GeoTMI aims to maximize mutual information between three variables: the correct and the corrupted geometries and the property. GeoTMI also explicitly updates the corrupted input to approach the correct geometry as it passes through the GNN layers, contributing to more effective denoising. We investigated the performance of the proposed method using 3D GNNs for three prediction tasks: molecular properties, a chemical reaction property, and relaxed energy in a heterogeneous catalytic system. Our results showed consistent improvements in accuracy across various tasks, demonstrating the effectiveness and robustness of GeoTMI.
Authors: Xiaojin Zhang, Lixin Fan, Siwei Wang, Wenjie Li, Kai Chen, Qiang Yang
In federated learning, benign participants aim to optimize a global model collaboratively. However, the risk of \textit{privacy leakage} cannot be ignored in the presence of \textit{semi-honest} adversaries. Existing research has focused either on designing protection mechanisms or on inventing attacking mechanisms. While the battle between defenders and attackers seems never-ending, we are concerned with one critical question: is it possible to prevent potential attacks in advance? To address this, we propose the first game-theoretic framework that considers both FL defenders and attackers in terms of their respective payoffs, which include computational costs, FL model utilities, and privacy leakage risks. We name this game the federated learning privacy game (FLPG), in which neither defenders nor attackers are aware of all participants' payoffs.
To handle the \textit{incomplete information} inherent in this situation, we propose associating the FLPG with an \textit{oracle} that has two primary responsibilities. First, the oracle provides lower and upper bounds of the payoffs for the players. Second, the oracle acts as a correlation device, privately providing suggested actions to each player. With this novel framework, we analyze the optimal strategies of defenders and attackers. Furthermore, we derive and demonstrate conditions under which the attacker, as a rational decision-maker, should always follow the oracle's suggestion \textit{not to attack}.
Authors: Jamie Tolan, Hung-I Yang, Ben Nosarzewski, Guillaume Couairon, Huy Vo, John Brandt, Justine Spore, Sayantan Majumdar, Daniel Haziza, Janaki Vamaraju, Theo Moutakanni, Piotr Bojanowski, Tracy Johns, Brian White, Tobias Tiecke, Camille Couprie
Vegetation structure mapping is critical for understanding the global carbon cycle and monitoring nature-based approaches to climate adaptation and mitigation. Repeated measurements of these data allow for the observation of deforestation or degradation of existing forests, natural forest regeneration, and the implementation of sustainable agricultural practices like agroforestry. Assessments of tree canopy height and crown projected area at a high spatial resolution are also important for monitoring carbon fluxes and assessing tree-based land uses, since forest structures can be highly spatially heterogeneous, especially in agroforestry systems. Very high resolution satellite imagery (less than one meter (1m) Ground Sample Distance) makes it possible to extract information at the tree level while allowing monitoring at a very large scale. This paper presents the first high-resolution canopy height map concurrently produced for multiple sub-national jurisdictions. Specifically, we produce very high resolution canopy height maps for the states of California and Sao Paulo, a significant improvement in resolution over the ten meter (10m) resolution of previous Sentinel / GEDI based worldwide maps of canopy height. The maps are generated by the extraction of features from a self-supervised model trained on Maxar imagery from 2017 to 2020, and the training of a dense prediction decoder against aerial lidar maps. We also introduce a post-processing step using a convolutional network trained on GEDI observations. We evaluate the proposed maps with set-aside validation lidar data as well as by comparing with other remotely sensed maps and field-collected data, and find our model produces an average Mean Absolute Error (MAE) of 2.8 meters and Mean Error (ME) of 0.6 meters.
Authors: Xin Man, Chenghong Zhang, Jin Feng, Changyu Li, Jie Shao
Weather forecasting is a long-standing computational challenge with direct societal and economic impacts. This task involves a large amount of continuous data collection and exhibits rich spatiotemporal dependencies over long periods, making it highly suitable for deep learning models. In this paper, we apply pre-training techniques to weather forecasting and propose W-MAE, a Weather model with Masked AutoEncoder pre-training for weather forecasting. W-MAE is pre-trained in a self-supervised manner to reconstruct spatial correlations within meteorological variables. On the temporal scale, we fine-tune the pre-trained W-MAE to predict the future states of meteorological variables, thereby modeling the temporal dependencies present in weather data. We conduct our experiments using the fifth-generation ECMWF Reanalysis (ERA5) data, with samples selected every six hours. Experimental results show that our W-MAE framework offers three key benefits: 1) when predicting the future state of meteorological variables, the utilization of our pre-trained W-MAE can effectively alleviate the problem of cumulative errors in prediction, maintaining stable performance in the short-to-medium term; 2) when predicting diagnostic variables (e.g., total precipitation), our model exhibits significant performance advantages over FourCastNet; 3) Our task-agnostic pre-training schema can be easily integrated with various task-specific models. When our pre-training framework is applied to FourCastNet, it yields an average 20% performance improvement in Anomaly Correlation Coefficient (ACC).
Authors: Yuhua Jiang, Qihan Liu, Xiaoteng Ma, Chenghao Li, Yiqin Yang, Jun Yang, Bin Liang, Qianchuan Zhao
Among the great successes of Reinforcement Learning (RL), self-play algorithms play an essential role in solving competitive games. Current self-play algorithms optimize the agent to maximize expected win-rates against its current or historical copies, making it often stuck in the local optimum and its strategy style simple and homogeneous. A possible solution is to improve the diversity of policies, which helps the agent break the stalemate and enhances its robustness when facing different opponents. However, enhancing diversity in the self-play algorithms is not trivial. In this paper, we aim to introduce diversity from the perspective that agents could have diverse risk preferences in the face of uncertainty. Specifically, we design a novel reinforcement learning algorithm called Risk-sensitive Proximal Policy Optimization (RPPO), which smoothly interpolates between worst-case and best-case policy learning and allows for policy learning with desired risk preferences. Seamlessly integrating RPPO with population-based self-play, agents in the population optimize dynamic risk-sensitive objectives with experiences from playing against diverse opponents. Empirical results show that our method achieves comparable or superior performance in competitive games and that diverse modes of behaviors emerge. Our code is public online at \url{https://github.com/Jackory/RPBT}.
Authors: Lijun Zhang, Xiao Liu, Kaleel Mahmood, Caiwen Ding, Hui Guan
Multi-task learning (MTL) creates a single machine learning model called multi-task model to simultaneously perform multiple tasks. Although the security of single task classifiers has been extensively studied, there are several critical security research questions for multi-task models including 1) How secure are multi-task models to single task adversarial machine learning attacks, 2) Can adversarial attacks be designed to attack multiple tasks simultaneously, and 3) Does task sharing and adversarial training increase multi-task model robustness to adversarial attacks? In this paper, we answer these questions through careful analysis and rigorous experimentation. First, we develop na\"ive adaptation of single-task white-box attacks and analyze their inherent drawbacks. We then propose a novel attack framework, Dynamic Gradient Balancing Attack (DGBA). Our framework poses the problem of attacking a multi-task model as an optimization problem based on averaged relative loss change, which can be solved by approximating the problem as an integer linear programming problem. Extensive evaluation on two popular MTL benchmarks, NYUv2 and Tiny-Taxonomy, demonstrates the effectiveness of DGBA compared to na\"ive multi-task attack baselines on both clean and adversarially trained multi-task models. The results also reveal a fundamental trade-off between improving task accuracy by sharing parameters across tasks and undermining model robustness due to increased attack transferability from parameter sharing. DGBA is open-sourced and available at https://github.com/zhanglijun95/MTLAttack-DGBA.
Authors: Keisuke Fujii, Kazushi Tsutsui, Atom Scott, Hiroshi Nakahara, Naoya Takeishi, Yoshinobu Kawahara
Modeling of real-world biological multi-agents is a fundamental problem in various scientific and engineering fields. Reinforcement learning (RL) is a powerful framework to generate flexible and diverse behaviors in cyberspace; however, when modeling real-world biological multi-agents, there is a domain gap between behaviors in the source (i.e., real-world data) and the target (i.e., cyberspace for RL), and the source environment parameters are usually unknown. In this paper, we propose a method for adaptive action supervision in RL from real-world demonstrations in multi-agent scenarios. We adopt an approach that combines RL and supervised learning by selecting actions of demonstrations in RL based on the minimum distance of dynamic time warping for utilizing the information of the unknown source dynamics. This approach can be easily applied to many existing neural network architectures and provide us with an RL model balanced between reproducibility as imitation and generalization ability to obtain rewards in cyberspace. In the experiments, using chase-and-escape and football tasks with the different dynamics between the unknown source and target environments, we show that our approach achieved a balance between the reproducibility and the generalization ability compared with the baselines. In particular, we used the tracking data of professional football players as expert demonstrations in football and show successful performances despite the larger gap between behaviors in the source and target environments than the chase-and-escape task.
Authors: Lean Wang, Lei Li, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun
In-context learning (ICL) emerges as a promising capability of large language models (LLMs) by providing them with demonstration examples to perform diverse tasks. However, the underlying mechanism of how LLMs learn from the provided context remains under-explored. In this paper, we investigate the working mechanism of ICL through an information flow lens. Our findings reveal that label words in the demonstration examples function as anchors: (1) semantic information aggregates into label word representations during the shallow computation layers' processing; (2) the consolidated information in label words serves as a reference for LLMs' final predictions. Based on these insights, we introduce an anchor re-weighting method to improve ICL performance, a demonstration compression technique to expedite inference, and an analysis framework for diagnosing ICL errors in GPT2-XL. The promising applications of our findings again validate the uncovered ICL working mechanism and pave the way for future studies.
Authors: Yige Yuan, Bingbing Xu, Bo Lin, Liang Hou, Fei Sun, Huawei Shen, Xueqi Cheng
The generalization of neural networks is a central challenge in machine learning, especially concerning the performance under distributions that differ from training ones. Current methods, mainly based on the data-driven paradigm such as data augmentation, adversarial training, and noise injection, may encounter limited generalization due to model non-smoothness. In this paper, we propose to investigate generalization from a Partial Differential Equation (PDE) perspective, aiming to enhance it directly through the underlying function of neural networks, rather than focusing on adjusting input data. Specifically, we first establish the connection between neural network generalization and the smoothness of the solution to a specific PDE, namely "transport equation". Building upon this, we propose a general framework that introduces adaptive distributional diffusion into transport equation to enhance the smoothness of its solution, thereby improving generalization. In the context of neural networks, we put this theoretical framework into practice as $\textbf{PDE+}$ ($\textbf{PDE}$ with $\textbf{A}$daptive $\textbf{D}$istributional $\textbf{D}$iffusion) which diffuses each sample into a distribution covering semantically similar inputs. This enables better coverage of potentially unobserved distributions in training, thus improving generalization beyond merely data-driven methods. The effectiveness of PDE+ is validated through extensive experimental settings, demonstrating its superior performance compared to SOTA methods.
Authors: Xuanqi Liu, Zhuotao Liu
The community explored to build private inference frameworks for transformer-based large language models (LLMs) in a server-client setting, where the server holds the model parameters and the client inputs its private data (or prompt) for inference. However, these frameworks impose significant overhead when the private inputs are forward propagated through the original LLMs. In this paper, we show that substituting the computation- and communication-heavy operators in the transformer architecture with privacy-computing friendly approximations can greatly reduce the private inference costs while incurring very minor impact on model performance. Compared to state-of-the-art Iron (NeurIPS 2022), our privacy-computing friendly model inference pipeline achieves a $5\times$ acceleration in computation and an 80% reduction in communication overhead, while retaining nearly identical accuracy.
Authors: Jiyuan Tu, Weidong Liu, Xiaojun Mao, Mingyue Xu
The debiased estimator is a crucial tool in statistical inference for high-dimensional model parameters. However, constructing such an estimator involves estimating the high-dimensional inverse Hessian matrix, incurring significant computational costs. This challenge becomes particularly acute in distributed setups, where traditional methods necessitate computing a debiased estimator on every machine. This becomes unwieldy, especially with a large number of machines. In this paper, we delve into semi-supervised sparse statistical inference in a distributed setup. An efficient multi-round distributed debiased estimator, which integrates both labeled and unlabelled data, is developed. We will show that the additional unlabeled data helps to improve the statistical rate of each round of iteration. Our approach offers tailored debiasing methods for $M$-estimation and generalized linear models according to the specific form of the loss function. Our method also applies to a non-smooth loss like absolute deviation loss. Furthermore, our algorithm is computationally efficient since it requires only one estimation of a high-dimensional inverse covariance matrix. We demonstrate the effectiveness of our method by presenting simulation studies and real data applications that highlight the benefits of incorporating unlabeled data.
Authors: Jan Trieschmann, Luca Vialetto, Tobias Gergs
Machine learning has had an enormous impact in many scientific disciplines. Also in the field of low-temperature plasma modeling and simulation it has attracted significant interest within the past years. Whereas its application should be carefully assessed in general, many aspects of plasma modeling and simulation have benefited substantially from recent developments within the field of machine learning and data-driven modeling. In this survey, we approach two main objectives: (a) We review the state-of-the-art focusing on approaches to low-temperature plasma modeling and simulation. By dividing our survey into plasma physics, plasma chemistry, plasma-surface interactions, and plasma process control, we aim to extensively discuss relevant examples from literature. (b) We provide a perspective of potential advances to plasma science and technology. We specifically elaborate on advances possibly enabled by adaptation from other scientific disciplines. We argue that not only the known unknowns, but also unknown unknowns may be discovered due to the inherent propensity of data-driven methods to spotlight hidden patterns in data.
Authors: John Andrew Raine, Matthew Leigh, Knut Zoch, Tobias Golling
In this work we introduce $\nu^2$-Flows, an extension of the $\nu$-Flows method to final states containing multiple neutrinos. The architecture can natively scale for all combinations of object types and multiplicities in the final state for any desired neutrino multiplicities. In $t\bar{t}$ dilepton events, the momenta of both neutrinos and correlations between them are reconstructed more accurately than when using the most popular standard analytical techniques, and solutions are found for all events. Inference time is significantly faster than competing methods, and can be reduced further by evaluating in parallel on graphics processing units. We apply $\nu^2$-Flows to $t\bar{t}$ dilepton events and show that the per-bin uncertainties in unfolded distributions is much closer to the limit of performance set by perfect neutrino reconstruction than standard techniques. For the chosen double differential observables $\nu^2$-Flows results in improved statistical precision for each bin by a factor of 1.5 to 2 in comparison to the Neutrino Weighting method and up to a factor of four in comparison to the Ellipse approach.
Authors: Dimitri Meunier, Zhu Li, Arthur Gretton, Samory Kpotufe
Many recent theoretical works on \emph{meta-learning} aim to achieve guarantees in leveraging similar representational structures from related tasks towards simplifying a target task. Importantly, the main aim in theory works on the subject is to understand the extent to which convergence rates -- in learning a common representation -- \emph{may scale with the number $N$ of tasks} (as well as the number of samples per task). First steps in this setting demonstrate this property when both the shared representation amongst tasks, and task-specific regression functions, are linear. This linear setting readily reveals the benefits of aggregating tasks, e.g., via averaging arguments. In practice, however, the representation is often highly nonlinear, introducing nontrivial biases in each task that cannot easily be averaged out as in the linear case. In the present work, we derive theoretical guarantees for meta-learning with nonlinear representations. In particular, assuming the shared nonlinearity maps to an infinite-dimensional RKHS, we show that additional biases can be mitigated with careful regularization that leverages the smoothness of task-specific regression functions,
Authors: Philip Amortila, Nan Jiang, Csaba Szepesvári
Theoretical guarantees in reinforcement learning (RL) are known to suffer multiplicative blow-up factors with respect to the misspecification error of function approximation. Yet, the nature of such \emph{approximation factors} -- especially their optimal form in a given learning problem -- is poorly understood. In this paper we study this question in linear off-policy value function estimation, where many open questions remain. We study the approximation factor in a broad spectrum of settings, such as with the weighted $L_2$-norm (where the weighting is the offline state distribution), the $L_\infty$ norm, the presence vs. absence of state aliasing, and full vs. partial coverage of the state space. We establish the optimal asymptotic approximation factors (up to constants) for all of these settings. In particular, our bounds identify two instance-dependent factors for the $L_2(\mu)$ norm and only one for the $L_\infty$ norm, which are shown to dictate the hardness of off-policy evaluation under misspecification.
Authors: Meiyi Zhu, Matteo Zecchin, Sangwoo Park, Caili Guo, Chunyan Feng, Osvaldo Simeone
In this paper, we consider a wireless federated inference scenario in which devices and a server share a pre-trained machine learning model. The devices communicate statistical information about their local data to the server over a common wireless channel, aiming to enhance the quality of the inference decision at the server. Recent work has introduced federated conformal prediction (CP), which leverages devices-to-server communication to improve the reliability of the server's decision. With federated CP, devices communicate to the server information about the loss accrued by the shared pre-trained model on the local data, and the server leverages this information to calibrate a decision interval, or set, so that it is guaranteed to contain the correct answer with a pre-defined target reliability level. Previous work assumed noise-free communication, whereby devices can communicate a single real number to the server. In this paper, we study for the first time federated CP in a wireless setting. We introduce a novel protocol, termed wireless federated conformal prediction (WFCP), which builds on type-based multiple access (TBMA) and on a novel quantile correction strategy. WFCP is proved to provide formal reliability guarantees in terms of coverage of the predicted set produced by the server. Using numerical results, we demonstrate the significant advantages of WFCP against digital implementations of existing federated CP schemes, especially in regimes with limited communication resources and/or large number of devices.
Authors: Aizhan Akhmetzhanova, Siddharth Mishra-Sharma, Cora Dvorkin
The influx of massive amounts of data from current and upcoming cosmological surveys necessitates compression schemes that can efficiently summarize the data with minimal loss of information. We introduce a method that leverages the paradigm of self-supervised machine learning in a novel manner to construct representative summaries of massive datasets using simulation-based augmentations. Deploying the method on hydrodynamical cosmological simulations, we show that it can deliver highly informative summaries, which can be used for a variety of downstream tasks, including precise and accurate parameter inference. We demonstrate how this paradigm can be used to construct summary representations that are insensitive to prescribed systematic effects, such as the influence of baryonic physics. Our results indicate that self-supervised machine learning techniques offer a promising new approach for compression of cosmological data as well its analysis.
Authors: Hao Wen, Jie Wang, Xiaodong Qiao
The recognition of abstracts is crucial for effectively locating the content and clarifying the article. Existing move recognition algorithms lack the ability to learn word position information to obtain contextual semantics. This paper proposes a novel enhanced move recognition algorithm with an improved pre-trained model and a gated network with attention mechanism for unstructured abstracts of Chinese scientific and technological papers. The proposed algorithm first performs summary data segmentation and vocabulary training. The EP-ERNIE$\_$AT-GRU framework is leveraged to incorporate word positional information, facilitating deep semantic learning and targeted feature extraction. Experimental results demonstrate that the proposed algorithm achieves 13.37$\%$ higher accuracy on the split dataset than on the original dataset and a 7.55$\%$ improvement in accuracy over the basic comparison model.
Authors: Haochen Wu, Shubham Sharma, Sunandita Patra, Sriram Gopalakrishnan
With the growing use of machine learning (ML) models in critical domains such as finance and healthcare, the need to offer recourse for those adversely affected by the decisions of ML models has become more important; individuals ought to be provided with recommendations on actions to take for improving their situation and thus receiving a favorable decision. Prior work on sequential algorithmic recourse -- which recommends a series of changes -- focuses on action feasibility and uses the proximity of feature changes to determine action costs. However, the uncertainties of feature changes and the risk of higher than average costs in recourse have not been considered. It is undesirable if a recourse could (with some probability) result in a worse situation from which recovery requires an extremely high cost. It is essential to incorporate risks when computing and evaluating recourse. We call the recourse computed with such risk considerations as Safer Algorithmic Recourse (SafeAR). The objective is to empower people to choose a recourse based on their risk tolerance. In this work, we discuss and show how existing recourse desiderata can fail to capture the risk of higher costs. We present a method to compute recourse policies that consider variability in cost and connect algorithmic recourse literature with risk-sensitive reinforcement learning. We also adopt measures "Value at Risk" and "Conditional Value at Risk" from the financial literature to summarize risk concisely. We apply our method to two real-world datasets and compare policies with different risk-aversion levels using risk measures and recourse desiderata (sparsity and proximity).
Authors: Yiqun Diao, Yutong Yang, Qinbin Li, Bingsheng He, Mian Lu
How to get insights from relational data streams in a timely manner is a hot research topic. Data streams can present unique challenges, such as distribution drifts, outliers, emerging classes, and changing features, which have recently been described as open environment challenges for machine learning. While existing studies have been done on incremental learning for data streams, their evaluations are mostly conducted with synthetic datasets. Thus, a natural question is how those open environment challenges look like and how existing incremental learning algorithms perform on real-world relational data streams. To fill this gap, we develop an Open Environment Benchmark named OEBench to evaluate open environment challenges in real-world relational data streams. Specifically, we investigate 55 real-world relational data streams and establish that open environment scenarios are indeed widespread, which presents significant challenges for stream learning algorithms. Through benchmarks with existing incremental learning algorithms, we find that increased data quantity may not consistently enhance the model accuracy when applied in open environment scenarios, where machine learning models can be significantly compromised by missing values, distribution drifts, or anomalies in real-world data streams. The current techniques are insufficient in effectively mitigating these challenges brought by open environments. More researches are needed to address real-world open environment challenges. All datasets and code are open-sourced in https://github.com/sjtudyq/OEBench.
Authors: Urs Waldmann, Alex Hoi Hang Chan, Hemal Naik, Máté Nagy, Iain D. Couzin, Oliver Deussen, Bastian Goldluecke, Fumihiro Kano
Markerless methods for animal posture tracking have been rapidly developing recently, but frameworks and benchmarks for tracking large animal groups in 3D are still lacking. To overcome this gap in the literature, we present 3D-MuPPET, a framework to estimate and track 3D poses of up to 10 pigeons at interactive speed using multiple camera views. We train a pose estimator to infer 2D keypoints and bounding boxes of multiple pigeons, then triangulate the keypoints to 3D. For identity matching of individuals in all views, we first dynamically match 2D detections to global identities in the first frame, then use a 2D tracker to maintain IDs across views in subsequent frames. We achieve comparable accuracy to a state of the art 3D pose estimator in terms of median error and Percentage of Correct Keypoints. Additionally, we benchmark the inference speed of 3D-MuPPET, with up to 9.45 fps in 2D and 1.89 fps in 3D, and perform quantitative tracking evaluation, which yields encouraging results. Finally, we showcase two novel applications for 3D-MuPPET. First, we train a model with data of single pigeons and achieve comparable results in 2D and 3D posture estimation for up to 5 pigeons. Second, we show that 3D-MuPPET also works in outdoors without additional annotations from natural environments. Both use cases simplify the domain shift to new species and environments, largely reducing annotation effort needed for 3D posture tracking. To the best of our knowledge we are the first to present a framework for 2D/3D animal posture and trajectory tracking that works in both indoor and outdoor environments for up to 10 individuals. We hope that the framework can open up new opportunities in studying animal collective behaviour and encourages further developments in 3D multi-animal posture tracking.
Authors: Felix Wagner, Florian Nachtigall, Lukas Franken, Nikola Milojevic-Dupont, Rafael H.M. Pereira, Nicolas Koch, Jakob Runge, Marta Gonzalez, Felix Creutzig
Climate change mitigation in urban mobility requires policies reconfiguring urban form to increase accessibility and facilitate low-carbon modes of transport. However, current policy research has insufficiently assessed urban form effects on car travel at three levels: (1) Causality -- Can causality be established beyond theoretical and correlation-based analyses? (2) Generalizability -- Do relationships hold across different cities and world regions? (3) Context specificity -- How do relationships vary across neighborhoods of a city? Here, we address all three gaps via causal graph discovery and explainable machine learning to detect urban form effects on intra-city car travel, based on mobility data of six cities across three continents. We find significant causal effects of urban form on trip emissions and inter-feature effects, which had been neglected in previous work. Our results demonstrate that destination accessibility matters most overall, while low density and low connectivity also sharply increase CO$_2$ emissions. These general trends are similar across cities but we find idiosyncratic effects that can lead to substantially different recommendations. In more monocentric cities, we identify spatial corridors -- about 10--50 km from the city center -- where subcenter-oriented development is more relevant than increased access to the main center. Our work demonstrates a novel application of machine learning that enables new research addressing the needs of causality, generalizability, and contextual specificity for scaling evidence-based urban climate solutions.
Authors: Shota Horiguchi, Kota Dohi, Yohei Kawaguchi
One of the challenges in deploying a machine learning model is that the model's performance degrades as the operating environment changes. To maintain the performance, streaming active learning is used, in which the model is retrained by adding a newly annotated sample to the training dataset if the prediction of the sample is not certain enough. Although many streaming active learning methods have been proposed for classification, few efforts have been made for regression problems, which are often handled in the industrial field. In this paper, we propose to use the regression-via-classification framework for streaming active learning for regression. Regression-via-classification transforms regression problems into classification problems so that streaming active learning methods proposed for classification problems can be applied directly to regression problems. Experimental validation on four real data sets shows that the proposed method can perform regression with higher accuracy at the same annotation cost.
Authors: Tareq Si-Salem, Gözde Özcan, Iasonas Nikolaou, Evimaria Terzi, Stratis Ioannidis
We study monotone submodular maximization under general matroid constraints in the online setting. We prove that online optimization of a large class of submodular functions, namely, weighted threshold potential functions, reduces to online convex optimization (OCO). This is precisely because functions in this class admit a concave relaxation; as a result, OCO policies, coupled with an appropriate rounding scheme, can be used to achieve sublinear regret in the combinatorial setting. We show that our reduction extends to many different versions of the online learning problem, including the dynamic regret, bandit, and optimistic-learning settings.
Authors: Zheng Nan, Ting Dang, Vidhyasaharan Sethu, Beena Ahmed
Connectionist temporal classification (CTC) is commonly adopted for sequence modeling tasks like speech recognition, where it is necessary to preserve order between the input and target sequences. However, CTC is only applied to deterministic sequence models, where the latent space is discontinuous and sparse, which in turn makes them less capable of handling data variability when compared to variational models. In this paper, we integrate CTC with a variational model and derive loss functions that can be used to train more generalizable sequence models that preserve order. Specifically, we derive two versions of the novel variational CTC based on two reasonable assumptions, the first being that the variational latent variables at each time step are conditionally independent; and the second being that these latent variables are Markovian. We show that both loss functions allow direct optimization of the variational lower bound for the model log-likelihood, and present computationally tractable forms for implementing them.
Authors: Zhanhui Zhou, Jie Liu, Chao Yang, Jing Shao, Yu Liu, Xiangyu Yue, Wanli Ouyang, Yu Qiao
A single language model (LM), despite aligning well with an average labeler through reinforcement learning from human feedback (RLHF), may not universally suit diverse human preferences. Recent approaches therefore opt for customization by collecting multi-dimensional feedback and creating distinct reward models (RMs) for each dimension (e.g., helpfulness, harmlessness, or honesty). Different LMs can then be optimized for different preferences using multi-objective RLHF (MORLHF) with different reward weightings. Yet, RL fine-tuning is unstable and resource-heavy, especially for MORLHF with diverse and usually conflicting objectives. In this paper, we present Multi-Objective Direct Preference Optimization (MODPO), an RL-free algorithm that extends Direct Preference Optimization (DPO) for multiple alignment objectives with minimal overheads. Essentially, MODPO folds language modeling directly into reward modeling, training LMs as implicit collective reward models (cRMs) that combine all objectives with specific weightings. While theoretically guaranteed to produce the same optimal solutions as MORLHF, MODPO is practically more stable and computationally efficient. Empirical results from safety alignment and long-form question answering confirm that MODPO matches or outperforms existing methods, consistently producing a Pareto front of LMs that cater to diverse preferences with 3 times less computational resources compared to MORLHF.
Authors: Michael S. Albergo, Mark Goldstein, Nicholas M. Boffi, Rajesh Ranganath, Eric Vanden-Eijnden
Generative models inspired by dynamical transport of measure -- such as flows and diffusions -- construct a continuous-time map between two probability densities. Conventionally, one of these is the target density, only accessible through samples, while the other is taken as a simple base density that is data-agnostic. In this work, using the framework of stochastic interpolants, we formalize how to \textit{couple} the base and the target densities, whereby samples from the base are computed conditionally given samples from the target in a way that is different from (but does preclude) incorporating information about class labels or continuous embeddings. This enables us to construct dynamical transport maps that serve as conditional generative models. We show that these transport maps can be learned by solving a simple square loss regression problem analogous to the standard independent setting. We demonstrate the usefulness of constructing dependent couplings in practice through experiments in super-resolution and in-painting.
Authors: Zih-Jyun Lin, Yi-Ju Chen, Po-Chih Kuo, Likai Huang, Chaur-Jong Hu, Cheng-Yu Chen
Dementia diagnosis requires a series of different testing methods, which is complex and time-consuming. Early detection of dementia is crucial as it can prevent further deterioration of the condition. This paper utilizes a speech recognition model to construct a dementia assessment system tailored for Mandarin speakers during the picture description task. By training an attention-based speech recognition model on voice data closely resembling real-world scenarios, we have significantly enhanced the model's recognition capabilities. Subsequently, we extracted the encoder from the speech recognition model and added a linear layer for dementia assessment. We collected Mandarin speech data from 99 subjects and acquired their clinical assessments from a local hospital. We achieved an accuracy of 92.04% in Alzheimer's disease detection and a mean absolute error of 9% in clinical dementia rating score prediction.
Authors: Kaican Li, Yifan Zhang, Lanqing Hong, Zhenguo Li, Nevin L. Zhang
Out-of-distribution (OOD) generalization is a complicated problem due to the idiosyncrasies of possible distribution shifts between training and test domains. Most benchmarks employ diverse datasets to address this issue; however, the degree of the distribution shift between the training domains and the test domains of each dataset remains largely fixed. This may lead to biased conclusions that either underestimate or overestimate the actual OOD performance of a model. Our study delves into a more nuanced evaluation setting that covers a broad range of shift degrees. We show that the robustness of models can be quite brittle and inconsistent under different degrees of distribution shifts, and therefore one should be more cautious when drawing conclusions from evaluations under a limited range of degrees. In addition, we observe that large-scale pre-trained models, such as CLIP, are sensitive to even minute distribution shifts of novel downstream tasks. This indicates that while pre-trained representations may help improve downstream in-distribution performance, they could have minimal or even adverse effects on generalization in certain OOD scenarios of the downstream task if not used properly. In light of these findings, we encourage future research to conduct evaluations across a broader range of shift degrees whenever possible.
Authors: Md Mahbubur Rahman, Ira Ceka, Chengzhi Mao, Saikat Chakraborty, Baishakhi Ray, Wei Le
Deep learning vulnerability detection has shown promising results in recent years. However, an important challenge that still blocks it from being very useful in practice is that the model is not robust under perturbation and it cannot generalize well over the out-of-distribution (OOD) data, e.g., applying a trained model to unseen projects in real world. We hypothesize that this is because the model learned non-robust features, e.g., variable names, that have spurious correlations with labels. When the perturbed and OOD datasets no longer have the same spurious features, the model prediction fails. To address the challenge, in this paper, we introduced causality into deep learning vulnerability detection. Our approach CausalVul consists of two phases. First, we designed novel perturbations to discover spurious features that the model may use to make predictions. Second, we applied the causal learning algorithms, specifically, do-calculus, on top of existing deep learning models to systematically remove the use of spurious features and thus promote causal based prediction. Our results show that CausalVul consistently improved the model accuracy, robustness and OOD performance for all the state-of-the-art models and datasets we experimented. To the best of our knowledge, this is the first work that introduces do calculus based causal learning to software engineering models and shows it's indeed useful for improving the model accuracy, robustness and generalization. Our replication package is located at https://figshare.com/s/0ffda320dcb96c249ef2.
Authors: Zhengcong Yin, Diya Li, Daniel W. Goldberg
The remarkable success of GPT models across various tasks, including toponymy recognition motivates us to assess the performance of the GPT-3 model in the geocoding address parsing task. To ensure that the evaluation more accurately mirrors performance in real-world scenarios with diverse user input qualities and resolve the pressing need for a 'gold standard' evaluation dataset for geocoding systems, we introduce a benchmark dataset of low-quality address descriptions synthesized based on human input patterns mining from actual input logs of a geocoding system in production. This dataset has 21 different input errors and variations; contains over 239,000 address records that are uniquely selected from streets across all U.S. 50 states and D.C.; and consists of three subsets to be used as training, validation, and testing sets. Building on this, we train and gauge the performance of the GPT-3 model in extracting address components, contrasting its performance with transformer-based and LSTM-based models. The evaluation results indicate that Bidirectional LSTM-CRF model has achieved the best performance over these transformer-based models and GPT-3 model. Transformer-based models demonstrate very comparable results compared to the Bidirectional LSTM-CRF model. The GPT-3 model, though trailing in performance, showcases potential in the address parsing task with few-shot examples, exhibiting room for improvement with additional fine-tuning. We open source the code and data of this presented benchmark so that researchers can utilize it for future model development or extend it to evaluate similar tasks, such as document geocoding.
Authors: Sergio Calvo-Ordonez, Chun-Wun Cheng, Jiahao Huang, Lipei Zhang, Guang Yang, Carola-Bibiane Schonlieb, Angelica I Aviles-Rivero
Diffusion Probabilistic Models stand as a critical tool in generative modelling, enabling the generation of complex data distributions. This family of generative models yields record-breaking performance in tasks such as image synthesis, video generation, and molecule design. Despite their capabilities, their efficiency, especially in the reverse process, remains a challenge due to slow convergence rates and high computational costs. In this paper, we introduce an approach that leverages continuous dynamical systems to design a novel denoising network for diffusion models that is more parameter-efficient, exhibits faster convergence, and demonstrates increased noise robustness. Experimenting with Denoising Diffusion Probabilistic Models (DDPMs), our framework operates with approximately a quarter of the parameters, and $\sim$ 30\% of the Floating Point Operations (FLOPs) compared to standard U-Nets in DDPMs. Furthermore, our model is notably faster in inference than the baseline when measured in fair and equal conditions. We also provide a mathematical intuition as to why our proposed reverse process is faster as well as a mathematical discussion of the empirical tradeoffs in the denoising downstream task. Finally, we argue that our method is compatible with existing performance enhancement techniques, enabling further improvements in efficiency, quality, and speed.
Authors: Nianli Peng, Brandon Fain
We describe RA-E3 (Reward-Aware Explicit Explore or Exploit), an algorithm with provable guarantees for solving a single or multi-objective Markov Decision Process (MDP) where we want to maximize the expected value of a nonlinear function over accumulated rewards. This allows us to model fairness-aware welfare optimization for multi-objective reinforcement learning as well as risk-aware reinforcement learning with nonlinear Von Neumann-Morgenstern utility functions in the single objective setting. RA-E3 extends the classic E3 algorithm that solves MDPs with scalar rewards and linear preferences. We first state a distinct reward-aware version of value iteration that calculates a non-stationary policy that is approximately optimal for a given model of the environment. This sub-procedure is based on an extended form of Bellman optimality for nonlinear optimization that explicitly considers time and current accumulated reward. We then describe how to use this optimization procedure in a larger algorithm that must simultaneously learn a model of the environment. The algorithm learns an approximately optimal policy in time that depends polynomially on the MDP size, desired approximation, and smoothness of the nonlinear function, and exponentially on the number of objectives.
Authors: Alok Tripathy, Katherine Yelick, Aydin Buluc
The primary contribution of this paper is new methods for reducing communication in the sampling step for distributed GNN training. Here, we propose a matrix-based bulk sampling approach that expresses sampling as a sparse matrix multiplication (SpGEMM) and samples multiple minibatches at once. When the input graph topology does not fit on a single device, our method distributes the graph and use communication-avoiding SpGEMM algorithms to scale GNN minibatch sampling, enabling GNN training on much larger graphs than those that can fit into a single device memory. When the input graph topology (but not the embeddings) fits in the memory of one GPU, our approach (1) performs sampling without communication, (2) amortizes the overheads of sampling a minibatch, and (3) can represent multiple sampling algorithms by simply using different matrix constructions. In addition to new methods for sampling, we show that judiciously replicating feature data with a simple all-to-all exchange can outperform current methods for the feature extraction step in distributed GNN training. We provide experimental results on the largest Open Graph Benchmark (OGB) datasets on $128$ GPUs, and show that our pipeline is $2.5\times$ faster Quiver (a distributed extension to PyTorch-Geometric) on a $3$-layer GraphSAGE network. On datasets outside of OGB, we show a $8.46\times$ speedup on $128$ GPUs in-per epoch time. Finally, we show scaling when the graph is distributed across GPUs and scaling for both node-wise and layer-wise sampling algorithms
Authors: Zoltan Csaki, Pian Pawakapan, Urmish Thakker, Qiantong Xu
Recent large language models (LLM) exhibit sub-optimal performance on low-resource languages, as the training data of these models is usually dominated by English and other high-resource languages. Furthermore, it is challenging to train models for low-resource languages, especially from scratch, due to a lack of high quality training data. Adapting pretrained LLMs reduces the need for data in the new language while also providing cross lingual transfer capabilities. However, naively adapting to new languages leads to catastrophic forgetting and poor tokenizer efficiency. In this work, we study how to efficiently adapt any existing pretrained LLM to a new language without running into these issues. In particular, we improve the encoding efficiency of the tokenizer by adding new tokens from the target language and study the data mixing recipe to mitigate forgetting. Our experiments on adapting an English LLM to Hungarian and Thai show that our recipe can reach better performance than open source models on the target language, with minimal regressions on English.
Authors: Jing Hu, Qinrui Fan, Shu Hu, Siwei Lyu, Xi Wu, Xin Wang
In the field of clinical medicine, computed tomography (CT) is an effective medical imaging modality for the diagnosis of various pathologies. Compared with X-ray images, CT images can provide more information, including multi-planar slices and three-dimensional structures for clinical diagnosis. However, CT imaging requires patients to be exposed to large doses of ionizing radiation for a long time, which may cause irreversible physical harm. In this paper, we propose an Uncertainty-aware MedNeRF (UMedNeRF) network based on generated radiation fields. The network can learn a continuous representation of CT projections from 2D X-ray images by obtaining the internal structure and depth information and using adaptive loss weights to ensure the quality of the generated images. Our model is trained on publicly available knee and chest datasets, and we show the results of CT projection rendering with a single X-ray and compare our method with other methods based on generated radiation fields.
Authors: Daesoo Lee, Sara Malacarne, Erlend Aune
We present a novel time series anomaly detection method that achieves excellent detection accuracy while offering a superior level of explainability. Our proposed method, TimeVQVAE-AD, leverages masked generative modeling adapted from the cutting-edge time series generation method known as TimeVQVAE. The prior model is trained on the discrete latent space of a time-frequency domain. Notably, the dimensional semantics of the time-frequency domain are preserved in the latent space, enabling us to compute anomaly scores across different frequency bands, which provides a better insight into the detected anomalies. Additionally, the generative nature of the prior model allows for sampling likely normal states for detected anomalies, enhancing the explainability of the detected anomalies through counterfactuals. Our experimental evaluation on the UCR Time Series Anomaly archive demonstrates that TimeVQVAE-AD significantly surpasses the existing methods in terms of detection accuracy and explainability. We provide our implementation on GitHub: \url{https://github.com/ML4ITS/TimeVQVAE-AnomalyDetection}.
Authors: Ruoyi Du, Dongliang Chang, Timothy Hospedales, Yi-Zhe Song, Zhanyu Ma
High-resolution image generation with Generative Artificial Intelligence (GenAI) has immense potential but, due to the enormous capital investment required for training, it is increasingly centralised to a few large corporations, and hidden behind paywalls. This paper aims to democratise high-resolution GenAI by advancing the frontier of high-resolution generation while remaining accessible to a broad audience. We demonstrate that existing Latent Diffusion Models (LDMs) possess untapped potential for higher-resolution image generation. Our novel DemoFusion framework seamlessly extends open-source GenAI models, employing Progressive Upscaling, Skip Residual, and Dilated Sampling mechanisms to achieve higher-resolution image generation. The progressive nature of DemoFusion requires more passes, but the intermediate results can serve as "previews", facilitating rapid prompt iteration.
Authors: Dayu Hu, Ke Liang, Hao Yu, Xinwang Liu
In recent years, the field of single-cell data analysis has seen a marked advancement in the development of clustering methods. Despite advancements, most of these algorithms still concentrate on analyzing the provided single-cell matrix data. However, in medical applications, single-cell data often involves a wealth of exogenous information, including gene networks. Overlooking this aspect could lead to information loss and clustering results devoid of significant clinical relevance. An innovative single-cell deep clustering method, incorporating exogenous gene information, has been proposed to overcome this limitation. This model leverages exogenous gene network information to facilitate the clustering process, generating discriminative representations. Specifically, we have developed an attention-enhanced graph autoencoder, which is designed to efficiently capture the topological features between cells. Concurrently, we conducted a random walk on an exogenous Protein-Protein Interaction (PPI) network, thereby acquiring the gene's topological features. Ultimately, during the clustering process, we integrated both sets of information and reconstructed the features of both cells and genes to generate a discriminative representation. Extensive experiments have validated the effectiveness of our proposed method. This research offers enhanced insights into the characteristics and distribution of cells, thereby laying the groundwork for early diagnosis and treatment of diseases.
Authors: Xiangyu Meng, Xue Li, Qing Yang, Huanhuan Dai, Lian Qiao, Hongzhen Ding, Long Hao, Xun Wang
Benefiting from the advancements in deep learning, various genomic analytical techniques, such as survival analysis, classification of tumors and their subtypes, and exploration of specific pathways, have significantly enhanced our understanding of the biological mechanisms driving cancer. However, the overfitting issue, arising from the limited number of patient samples, poses a challenge in improving the accuracy of genome analysis by deepening the neural network. Furthermore, it remains uncertain whether novel approaches such as the sparsely gated mixture of expert (MOE) and self-attention mechanisms can improve the accuracy of genomic analysis. In this paper, we introduce a novel sparsely gated RNA-seq analysis framework called Gene-MOE. This framework exploits the potential of the MOE layers and the proposed mixture of attention expert (MOAE) layers to enhance the analysis accuracy. Additionally, it addresses overfitting challenges by integrating pan-cancer information from 33 distinct cancer types through pre-training.We pre-trained Gene-MOE on TCGA pan-cancer RNA-seq dataset with 33 cancer types. Subsequently, we conducted experiments involving cancer classification and survival analysis based on the pre-trained Gene-MOE. According to the survival analysis results on 14 cancer types, Gene-MOE outperformed state-of-the-art models on 12 cancer types. Through detailed feature analysis, we found that the Gene-MOE model could learn rich feature representations of high-dimensional genes. According to the classification results, the total accuracy of the classification model for 33 cancer classifications reached 95.8%, representing the best performance compared to state-of-the-art models. These results indicate that Gene-MOE holds strong potential for use in cancer classification and survival analysis.
Authors: Stefan Hegselmann, Antonio Parziale, Divya Shanmugam, Shengpu Tang, Mercy Nyamewaa Asiedu, Serina Chang, Thomas Hartvigsen, Harvineet Singh
A collection of the accepted Findings papers that were presented at the 3rd Machine Learning for Health symposium (ML4H 2023), which was held on December 10, 2023, in New Orleans, Louisiana, USA. ML4H 2023 invited high-quality submissions on relevant problems in a variety of health-related disciplines including healthcare, biomedicine, and public health. Two submission tracks were offered: the archival Proceedings track, and the non-archival Findings track. Proceedings were targeted at mature work with strong technical sophistication and a high impact to health. The Findings track looked for new ideas that could spark insightful discussion, serve as valuable resources for the community, or could enable new collaborations. Submissions to the Proceedings track, if not accepted, were automatically considered for the Findings track. All the manuscripts submitted to ML4H Symposium underwent a double-blind peer-review process.
Authors: Xingtong Yu, Yuan Fang, Zemin Liu, Xinming Zhang
Graph neural networks (GNNs) and heterogeneous graph neural networks (HGNNs) are prominent techniques for homogeneous and heterogeneous graph representation learning, yet their performance in an end-to-end supervised framework greatly depends on the availability of task-specific supervision. To reduce the labeling cost, pre-training on self-supervised pretext tasks has become a popular paradigm,but there is often a gap between the pre-trained model and downstream tasks, stemming from the divergence in their objectives. To bridge the gap, prompt learning has risen as a promising direction especially in few-shot settings, without the need to fully fine-tune the pre-trained model. While there has been some early exploration of prompt-based learning on graphs, they primarily deal with homogeneous graphs, ignoring the heterogeneous graphs that are prevalent in downstream applications. In this paper, we propose HGPROMPT, a novel pre-training and prompting framework to unify not only pre-training and downstream tasks but also homogeneous and heterogeneous graphs via a dual-template design. Moreover, we propose dual-prompt in HGPROMPT to assist a downstream task in locating the most relevant prior to bridge the gaps caused by not only feature variations but also heterogeneity differences across tasks. Finally, we thoroughly evaluate and analyze HGPROMPT through extensive experiments on three public datasets.
Authors: Sehmimul Hoque (1, 2), Hao Jia (3), Abhishek Abhishek (4), Mojde Fadaie (1), J. Quetzalcoatl Toledo-Marín (4), Tiago Vale (5, 4), Roger G. Melko (1, 6), Maximilian Swiatlowski (4), Wojciech T. Fedorko (4) ((1) Perimeter Institute for Theoretical Physics, (2) Faculty of Mathematics, University of Waterloo, (3) Department of Physics and Astronomy, University of British Columbia, (4) TRIUMF, (5) Department of Physics, Simon Fraser University, (6) Department of Physics and Astronomy, University of Waterloo)
The Large Hadron Collider's high luminosity era presents major computational challenges in the analysis of collision events. Large amounts of Monte Carlo (MC) simulation will be required to constrain the statistical uncertainties of the simulated datasets below these of the experimental data. Modelling of high-energy particles propagating through the calorimeter section of the detector is the most computationally intensive MC simulation task. We introduce a technique combining recent advancements in generative models and quantum annealing for fast and efficient simulation of high-energy particle-calorimeter interactions.
Authors: Wei Liu, Haozhao Wang, Jun Wang, Zhiying Deng, YuanKai Zhang, Cheng Wang, Ruixuan Li
Rationalization empowers deep learning models with self-explaining capabilities through a cooperative game, where a generator selects a semantically consistent subset of the input as a rationale, and a subsequent predictor makes predictions based on the selected rationale. In this paper, we discover that rationalization is prone to a problem named \emph{rationale shift}, which arises from the algorithmic bias of the cooperative game. Rationale shift refers to a situation where the semantics of the selected rationale may deviate from the original input, but the predictor still produces accurate predictions based on the deviation, resulting in a compromised generator with misleading feedback.
To address this issue, we first demonstrate the importance of the alignment between the rationale and the full input through both empirical observations and theoretical analysis. Subsequently, we introduce a novel approach called DAR (\textbf{D}iscriminatively \textbf{A}ligned \textbf{R}ationalization), which utilizes an auxiliary module pretrained on the full input to discriminatively align the selected rationale and the original input. We theoretically illustrate how DAR accomplishes the desired alignment, thereby overcoming the rationale shift problem. The experiments on two widely used real-world benchmarks show that the proposed method significantly improves the explanation quality (measured by the overlap between the model-selected explanation and the human-annotated rationale) as compared to state-of-the-art techniques. Additionally, results on two synthetic settings further validate the effectiveness of DAR in addressing the rationale shift problem.
Authors: Easton K. Huch, Jieru Shi, Madeline R. Abbott, Jessica R. Golbus, Alexander Moreno, Walter H. Dempsey
A common approach to learning mobile health (mHealth) intervention policies is linear Thompson sampling. Two desirable mHealth policy features are (1) pooling information across individuals and time and (2) incorporating a time-varying baseline reward. Previous approaches pooled information across individuals but not time, failing to capture trends in treatment effects over time. In addition, these approaches did not explicitly model the baseline reward, which limited the ability to precisely estimate the parameters in the differential reward model. In this paper, we propose a novel Thompson sampling algorithm, termed ''DML-TS-NNR'' that leverages (1) nearest-neighbors to efficiently pool information on the differential reward function across users and time and (2) the Double Machine Learning (DML) framework to explicitly model baseline rewards and stay agnostic to the supervised learning algorithms used. By explicitly modeling baseline rewards, we obtain smaller confidence sets for the differential reward parameters. We offer theoretical guarantees on the pseudo-regret, which are supported by empirical results. Importantly, the DML-TS-NNR algorithm demonstrates robustness to potential misspecifications in the baseline reward model.
Authors: Feiping Nie, Zhezheng Hao, Rong Wang
Support Vector Machine (SVM) stands out as a prominent machine learning technique widely applied in practical pattern recognition tasks. It achieves binary classification by maximizing the "margin", which represents the minimum distance between instances and the decision boundary. Although many efforts have been dedicated to expanding SVM for multi-class case through strategies such as one versus one and one versus the rest, satisfactory solutions remain to be developed. In this paper, we propose a novel method for multi-class SVM that incorporates pairwise class loss considerations and maximizes the minimum margin. Adhering to this concept, we embrace a new formulation that imparts heightened flexibility to multi-class SVM. Furthermore, the correlations between the proposed method and multiple forms of multi-class SVM are analyzed. The proposed regularizer, akin to the concept of "margin", can serve as a seamless enhancement over the softmax in deep learning, providing guidance for network parameter learning. Empirical evaluations demonstrate the effectiveness and superiority of our proposed method over existing multi-classification methods.Code is available at https://github.com/zz-haooo/M3SVM.
Authors: Ryan Greenblatt, Buck Shlegeris, Kshitij Sachan, Fabien Roger
As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes. Researchers have investigated a variety of safety techniques for this purpose, e.g. using models to review the outputs of other models, or red-teaming techniques to surface subtle failure modes. However, researchers have not evaluated whether such techniques still ensure safety if the model is itself intentionally trying to subvert them. In this paper, we develop and evaluate pipelines of safety techniques ("protocols") that are robust to intentional subversion.
We investigate a scenario in which we want to solve a sequence of programming problems, using access to a powerful but untrusted model (in our case, GPT-4), access to a less powerful trusted model (in our case, GPT-3.5), and limited access to human contractors who provide high-quality trusted labor. We investigate protocols that aim to never submit solutions containing backdoors, which we operationalize here as logical errors that are not caught by test cases.
We investigate a range of protocols and test each against strategies that the untrusted model could use to subvert them. One protocol is what we call trusted editing. This protocol first asks GPT-4 to write code, and then asks GPT-3.5 to rate the suspiciousness of that code. If the code is below some suspiciousness threshold, it is submitted. Otherwise, GPT-3.5 edits the solution to remove parts that seem suspicious and then submits the edited code. Another protocol is untrusted monitoring. This protocol asks GPT-4 to write code, and then asks another instance of GPT-4 whether the code is backdoored, using various techniques to prevent the GPT-4 instances from colluding. These protocols improve substantially on simple baselines.
Authors: Qing-xin Meng, Jian-wei Liu
Centered around solving the Online Saddle Point problem, this paper introduces the Online Convex-Concave Optimization (OCCO) framework, which involves a sequence of two-player time-varying convex-concave games. We propose the generalized duality gap (Dual-Gap) as the performance metric and establish the parallel relationship between OCCO with Dual-Gap and Online Convex Optimization (OCO) with regret. To demonstrate the natural extension of OCCO from OCO, we develop two algorithms, the implicit online mirror descent-ascent and its optimistic variant. Analysis reveals that their duality gaps share similar expression forms with the corresponding dynamic regrets arising from implicit updates in OCO. Empirical results further substantiate the effectiveness of our algorithms. Simultaneously, we unveil that the dynamic Nash equilibrium regret, which was initially introduced in a recent paper, has inherent defects.
Authors: Jakub Lála, Odhran O'Donoghue, Aleksandar Shtedritski, Sam Cox, Samuel G. Rodriques, Andrew D. White
Large Language Models (LLMs) generalize well across language tasks, but suffer from hallucinations and uninterpretability, making it difficult to assess their accuracy without ground-truth. Retrieval-Augmented Generation (RAG) models have been proposed to reduce hallucinations and provide provenance for how an answer was generated. Applying such models to the scientific literature may enable large-scale, systematic processing of scientific knowledge. We present PaperQA, a RAG agent for answering questions over the scientific literature. PaperQA is an agent that performs information retrieval across full-text scientific articles, assesses the relevance of sources and passages, and uses RAG to provide answers. Viewing this agent as a question answering model, we find it exceeds performance of existing LLMs and LLM agents on current science QA benchmarks. To push the field closer to how humans perform research on scientific literature, we also introduce LitQA, a more complex benchmark that requires retrieval and synthesis of information from full-text scientific papers across the literature. Finally, we demonstrate PaperQA's matches expert human researchers on LitQA.
Authors: Josh Gardner, Zoran Popovic, Ludwig Schmidt
Robustness to distribution shift has become a growing concern for text and image models as they transition from research subjects to deployment in the real world. However, high-quality benchmarks for distribution shift in tabular machine learning tasks are still lacking despite the widespread real-world use of tabular data and differences in the models used for tabular data in comparison to text and images. As a consequence, the robustness of tabular models to distribution shift is poorly understood. To address this issue, we introduce TableShift, a distribution shift benchmark for tabular data. TableShift contains 15 binary classification tasks in total, each with an associated shift, and includes a diverse set of data sources, prediction targets, and distribution shifts. The benchmark covers domains including finance, education, public policy, healthcare, and civic participation, and is accessible using only a few lines of Python code via the TableShift API. We conduct a large-scale study comparing several state-of-the-art tabular data models alongside robust learning and domain generalization methods on the benchmark tasks. Our study demonstrates (1) a linear trend between in-distribution (ID) and out-of-distribution (OOD) accuracy; (2) domain robustness methods can reduce shift gaps but at the cost of reduced ID accuracy; (3) a strong relationship between shift gap (difference between ID and OOD performance) and shifts in the label distribution.
The benchmark data, Python package, model implementations, and more information about TableShift are available at https://github.com/mlfoundations/tableshift and https://tableshift.org .
Authors: Silu He, Qinyao Luo, Xinsha Fu, Ling Zhao, Ronghua Du, Haifeng Li
Local Attention-guided Message Passing Mechanism (LAMP) adopted in Graph Attention Networks (GATs) is designed to adaptively learn the importance of neighboring nodes for better local aggregation on the graph, which can bring the representations of similar neighbors closer effectively, thus showing stronger discrimination ability. However, existing GATs suffer from a significant discrimination ability decline in heterophilic graphs because the high proportion of dissimilar neighbors can weaken the self-attention of the central node, jointly resulting in the deviation of the central node from similar nodes in the representation space. This kind of effect generated by neighboring nodes is called the Distraction Effect (DE) in this paper. To estimate and weaken the DE of neighboring nodes, we propose a Causally graph Attention network for Trimming heterophilic graph (CAT). To estimate the DE, since the DE are generated through two paths (grab the attention assigned to neighbors and reduce the self-attention of the central node), we use Total Effect to model DE, which is a kind of causal estimand and can be estimated from intervened data; To weaken the DE, we identify the neighbors with the highest DE (we call them Distraction Neighbors) and remove them. We adopt three representative GATs as the base model within the proposed CAT framework and conduct experiments on seven heterophilic datasets in three different sizes. Comparative experiments show that CAT can improve the node classification accuracy of all base GAT models. Ablation experiments and visualization further validate the enhancement of discrimination ability brought by CAT. The source code is available at https://github.com/GeoX-Lab/CAT.
Authors: Yafei Hu, Quanting Xie, Vidhi Jain, Jonathan Francis, Jay Patrikar, Nikhil Keetha, Seungchan Kim, Yaqi Xie, Tianyi Zhang, Shibo Zhao, Yu Quan Chong, Chen Wang, Katia Sycara, Matthew Johnson-Roberson, Dhruv Batra, Xiaolong Wang, Sebastian Scherer, Zsolt Kira, Fei Xia, Yonatan Bisk
Building general-purpose robots that can operate seamlessly, in any environment, with any object, and utilizing various skills to complete diverse tasks has been a long-standing goal in Artificial Intelligence. Unfortunately, however, most existing robotic systems have been constrained - having been designed for specific tasks, trained on specific datasets, and deployed within specific environments. These systems usually require extensively-labeled data, rely on task-specific models, have numerous generalization issues when deployed in real-world scenarios, and struggle to remain robust to distribution shifts. Motivated by the impressive open-set performance and content generation capabilities of web-scale, large-capacity pre-trained models (i.e., foundation models) in research fields such as Natural Language Processing (NLP) and Computer Vision (CV), we devote this survey to exploring (i) how these existing foundation models from NLP and CV can be applied to the field of robotics, and also exploring (ii) what a robotics-specific foundation model would look like. We begin by providing an overview of what constitutes a conventional robotic system and the fundamental barriers to making it universally applicable. Next, we establish a taxonomy to discuss current work exploring ways to leverage existing foundation models for robotics and develop ones catered to robotics. Finally, we discuss key challenges and promising future directions in using foundation models for enabling general-purpose robotic systems. We encourage readers to view our living GitHub repository of resources, including papers reviewed in this survey as well as related projects and repositories for developing foundation models for robotics.
Authors: Niklas Hemken, Florian Jacob, Fabian Peller-Konrad, Rainer Kartmann, Tamim Asfour, Hannes Hartenstein
Humanoid robots will be able to assist humans in their daily life, in particular due to their versatile action capabilities. However, while these robots need a certain degree of autonomy to learn and explore, they also should respect various constraints, for access control and beyond. We explore the novel field of incorporating privacy, security, and access control constraints with robot task planning approaches. We report preliminary results on the classical symbolic approach, deep-learned neural networks, and modern ideas using large language models as knowledge base. From analyzing their trade-offs, we conclude that a hybrid approach is necessary, and thereby present a new use case for the emerging field of neuro-symbolic artificial intelligence.
Authors: Weilong Chai, DanDan Zheng, Jiajiong Cao, Zhiquan Chen, Changbao Wang, Chenguang Ma
Text-to-image diffusion models (SD) exhibit significant advancements while requiring extensive computational resources. Though many acceleration methods have been proposed, they suffer from generation quality degradation or extra training cost generalizing to new fine-tuned models. To address these limitations, we propose a novel and universal Stable-Diffusion (SD) acceleration module called SpeedUpNet(SUN). SUN can be directly plugged into various fine-tuned SD models without extra training. This technique utilizes cross-attention layers to learn the relative offsets in the generated image results between negative and positive prompts achieving classifier-free guidance distillation with negative prompts controllable, and introduces a Multi-Step Consistency (MSC) loss to ensure a harmonious balance between reducing inference steps and maintaining consistency in the generated output. Consequently, SUN significantly reduces the number of inference steps to just 4 steps and eliminates the need for classifier-free guidance. It leads to an overall speedup of more than 10 times for SD models compared to the state-of-the-art 25-step DPM-solver++, and offers two extra advantages: (1) classifier-free guidance distillation with controllable negative prompts and (2) seamless integration into various fine-tuned Stable-Diffusion models without training. The effectiveness of the SUN has been verified through extensive experimentation. Project Page: https://williechai.github.io/speedup-plugin-for-stable-diffusions.github.io
Authors: Zi-Yu Khoo, Delong Zhang, Stéphane Bressan
We present several methods for predicting the dynamics of Hamiltonian systems from discrete observations of their vector field. Each method is either informed or uninformed of the Hamiltonian property. We empirically and comparatively evaluate the methods and observe that information that the system is Hamiltonian can be effectively informed, and that different methods strike different trade-offs between efficiency and effectiveness for different dynamical systems.
Authors: Abiodun Finbarrs Oketunji, James Hanify, Salter Heffron-Smith
This study harnesses the predictive capabilities of Long Short-Term Memory (LSTM) networks to analyse and predict road traffic accidents in Great Britain. It addresses the challenge of traffic accident forecasting, which is paramount for devising effective preventive measures. We utilised an extensive dataset encompassing reported collisions, casualties, and vehicles involvements from 1926 to 2022, provided by the Department for Transport (DfT). The data underwent stringent processing to rectify missing values and normalise features, ensuring robust LSTM network input.
Authors: Pranava Singhal, Shashi Raj Pandey, Petar Popovski
The standard client selection algorithms for Federated Learning (FL) are often unbiased and involve uniform random sampling of clients. This has been proven sub-optimal for fast convergence under practical settings characterized by significant heterogeneity in data distribution, computing, and communication resources across clients. For applications having timing constraints due to limited communication opportunities with the parameter server (PS), the client selection strategy is critical to complete model training within the fixed budget of communication rounds. To address this, we develop a biased client selection strategy, GreedyFed, that identifies and greedily selects the most contributing clients in each communication round. This method builds on a fast approximation algorithm for the Shapley Value at the PS, making the computation tractable for real-world applications with many clients. Compared to various client selection strategies on several real-world datasets, GreedyFed demonstrates fast and stable convergence with high accuracy under timing constraints and when imposing a higher degree of heterogeneity in data distribution, systems constraints, and privacy requirements.