Authors: Matthias Karlbauer, Nathaniel Cresswell-Clay, Raul A. Moreno, Dale R. Durran, Thorsten Kurth, Martin V. Butz
We present a parsimonious deep learning weather prediction model on the Hierarchical Equal Area isoLatitude Pixelization (HEALPix) to forecast seven atmospheric variables for arbitrarily long lead times on a global approximately 110 km mesh at 3h time resolution. In comparison to state-of-the-art machine learning weather forecast models, such as Pangu-Weather and GraphCast, our DLWP-HPX model uses coarser resolution and far fewer prognostic variables. Yet, at one-week lead times its skill is only about one day behind the state-of-the-art numerical weather prediction model from the European Centre for Medium-Range Weather Forecasts. We report successive forecast improvements resulting from model design and data-related decisions, such as switching from the cubed sphere to the HEALPix mesh, inverting the channel depth of the U-Net, and introducing gated recurrent units (GRU) on each level of the U-Net hierarchy. The consistent east-west orientation of all cells on the HEALPix mesh facilitates the development of location-invariant convolution kernels that are successfully applied to propagate global weather patterns across our planet. Without any loss of spectral power after two days, the model can be unrolled autoregressively for hundreds of steps into the future to generate stable and realistic states of the atmosphere that respect seasonal trends, as showcased in one-year simulations. Our parsimonious DLWP-HPX model is research-friendly and potentially well-suited for sub-seasonal and seasonal forecasting.
Authors: Parham Gohari, Matthew Hale, Ufuk Topcu
In cooperative multi-agent reinforcement learning (Co-MARL), a team of agents must jointly optimize the team's long-term rewards to learn a designated task. Optimizing rewards as a team often requires inter-agent communication and data sharing, leading to potential privacy implications. We assume privacy considerations prohibit the agents from sharing their environment interaction data. Accordingly, we propose Privacy-Engineered Value Decomposition Networks (PE-VDN), a Co-MARL algorithm that models multi-agent coordination while provably safeguarding the confidentiality of the agents' environment interaction data. We integrate three privacy-engineering techniques to redesign the data flows of the VDN algorithm, an existing Co-MARL algorithm that consolidates the agents' environment interaction data to train a central controller that models multi-agent coordination, and develop PE-VDN. In the first technique, we design a distributed computation scheme that eliminates Vanilla VDN's dependency on sharing environment interaction data. Then, we utilize a privacy-preserving multi-party computation protocol to guarantee that the data flows of the distributed computation scheme do not pose new privacy risks. Finally, we enforce differential privacy to preempt inference threats against the agents' training data, past environment interactions, when they take actions based on their neural network predictions. We implement PE-VDN in StarCraft Multi-Agent Competition (SMAC) and show that it achieves 80% of Vanilla VDN's win rate while maintaining differential privacy levels that provide meaningful privacy guarantees. The results demonstrate that PE-VDN can safeguard the confidentiality of agents' environment interaction data without sacrificing multi-agent coordination.
Authors: David Jensen, Brian LaMacchia, Ufuk Topcu, Pamela Wisniewski
Algorithmic robustness refers to the sustained performance of a computational system in the face of change in the nature of the environment in which that system operates or in the task that the system is meant to perform. Below, we motivate the importance of algorithmic robustness, present a conceptual framework, and highlight the relevant areas of research for which algorithmic robustness is relevant. Why robustness? Robustness is an important enabler of other goals that are frequently cited in the context of public policy decisions about computational systems, including trustworthiness, accountability, fairness, and safety. Despite this dependence, it tends to be under-recognized compared to these other concepts. This is unfortunate, because robustness is often more immediately achievable than these other ultimate goals, which can be more subjective and exacting. Thus, we highlight robustness as an important goal for researchers, engineers, regulators, and policymakers when considering the design, implementation, and deployment of computational systems. We urge researchers and practitioners to elevate the attention paid to robustness when designing and evaluating computational systems. For many key systems, the immediate question after any demonstration of high performance should be: "How robust is that performance to realistic changes in the task or environment?" Greater robustness will set the stage for systems that are more trustworthy, accountable, fair, and safe. Toward that end, this document provides a brief roadmap to some of the concepts and existing research around the idea of algorithmic robustness.
Authors: Md Sabbirul Haque, Md Shahedul Amin, Jonayet Miah, Duc Minh Cao, Ashiqul Haque Ahmed
Prediction of stock prices plays a significant role in aiding the decision-making of investors. Considering its importance, a growing literature has emerged trying to forecast stock prices with improved accuracy. In this study, we introduce an innovative approach for forecasting stock prices with greater accuracy. We incorporate external economic environment-related information along with stock prices. In our novel approach, we improve the performance of stock price prediction by taking into account variations due to future expected macroeconomic policy changes as investors adjust their current behavior ahead of time based on expected future macroeconomic policy changes. Furthermore, we incorporate macroeconomic variables along with historical stock prices to make predictions. Results from this strongly support the inclusion of future economic policy changes along with current macroeconomic information. We confirm the supremacy of our method over the conventional approach using several tree-based machine-learning algorithms. Results are strongly conclusive across various machine learning models. Our preferred model outperforms the conventional approach with an RMSE value of 1.61 compared to an RMSE value of 1.75 from the conventional approach.
Authors: Parth Daxesh Modi, Kamyar Arshi, Pertami J. Kunz, Abdelhak M. Zoubir
Bitcoin as a cryptocurrency has been one of the most important digital coins and the first decentralized digital currency. Deep neural networks, on the other hand, has shown promising results recently; however, we require huge amount of high-quality data to leverage their power. There are some techniques such as augmentation that can help us with increasing the dataset size, but we cannot exploit them on historical bitcoin data. As a result, we propose a shallow Bidirectional-LSTM (Bi-LSTM) model, fed with feature engineered data using our proposed method to forecast bitcoin closing prices in a daily time frame. We compare the performance with that of other forecasting methods, and show that with the help of the proposed feature engineering method, a shallow deep neural network outperforms other popular price forecasting models.
Authors: Franz A. Heinsen
We show how to compute the elements of a sequence $x_t = a_t x_{t-1} + b_t$ in parallel, given $t = (1, 2, \dots, n)$, $a_t \in \mathbb{R}^n$, $b_t \in \mathbb{R}^n$, and initial value $x_0 \in \mathbb{R}$. On $n$ parallel processors, the computation of $n$ elements incurs $\mathcal{O}(\log n)$ time and $\mathcal{O}(n)$ space. Sequences of this form are ubiquitous in science and engineering, making their parallelization useful for a vast number of applications. We implement parallelization in software, test it on parallel hardware, and verify that it executes faster than sequential computation by a factor of $\frac{n}{\log n}$.
Authors: Xudong Xu, Dejan Markovic, Jacob Sandakly, Todd Keebler, Steven Krenn, Alexander Richard
While 3D human body modeling has received much attention in computer vision, modeling the acoustic equivalent, i.e. modeling 3D spatial audio produced by body motion and speech, has fallen short in the community. To close this gap, we present a model that can generate accurate 3D spatial audio for full human bodies. The system consumes, as input, audio signals from headset microphones and body pose, and produces, as output, a 3D sound field surrounding the transmitter's body, from which spatial audio can be rendered at any arbitrary position in the 3D space. We collect a first-of-its-kind multimodal dataset of human bodies, recorded with multiple cameras and a spherical array of 345 microphones. In an empirical evaluation, we demonstrate that our model can produce accurate body-induced sound fields when trained with a suitable loss. Dataset and code are available online.
Authors: Abel Sancarlos, Edgar Bahilo, Pablo Mozo, Lukas Norman, Obaid Ur Rehma, Mihails Anufrijevs
The European debt purchase market as measured by the total book value of purchased debt approached 25bn euros in 2020 and it was growing at double-digit rates. This is an example of how big the debt collection and debt purchase industry has grown and the important impact it has in the financial sector. However, in order to ensure an adequate return during the debt collection process, a good estimation of the propensity to pay and/or the expected cashflow is crucial. These estimations can be employed, for instance, to create different strategies during the amicable collection to maximize quality standards and revenues. And not only that, but also to prioritize the cases in which a legal process is necessary when debtors are unreachable for an amicable negotiation. This work offers a solution for these estimations. Specifically, a new machine learning modelling pipeline is presented showing how outperforms current strategies employed in the sector. The solution contains a pre-processing pipeline and a model selector based on the best model calibration. Performance is validated with real historical data of the debt industry.
Authors: Zeynab Kaseb, Matthias Moller, Giorgio Tosti Balducci, Peter Palensky, Pedro P. Vergara
This paper explores the potential application of quantum and hybrid quantum-classical neural networks in power flow analysis. Experiments are conducted using two small-size datasets based on the IEEE 4-bus and 33-bus test systems. A systematic performance comparison is also conducted among quantum, hybrid quantum-classical, and classical neural networks. The comparison is based on (i) generalization ability, (ii) robustness, (iii) training dataset size needed, (iv) training error. (v) training computational time, and (vi) training process stability. The results show that the developed quantum-classical neural network outperforms both quantum and classical neural networks, and hence can improve deep learning-based power flow analysis in the noisy-intermediate-scale quantum (NISQ) era.
Authors: Artem Tsypin, Leonid Ugadiarov, Kuzma Khrabrov, Manvel Avetisian, Alexander Telepov, Egor Rumiantsev, Alexey Skrynnik, Aleksandr I. Panov, Dmitry Vetrov, Elena Tutubalina, Artur Kadurin
Molecular conformation optimization is crucial to computer-aided drug discovery and materials design. Traditional energy minimization techniques rely on iterative optimization methods that use molecular forces calculated by a physical simulator (oracle) as anti-gradients. However, this is a computationally expensive approach that requires many interactions with a physical simulator. One way to accelerate this procedure is to replace the physical simulator with a neural network. Despite recent progress in neural networks for molecular conformation energy prediction, such models are prone to distribution shift, leading to inaccurate energy minimization. We find that the quality of energy minimization with neural networks can be improved by providing optimization trajectories as additional training data. Still, it takes around $5 \times 10^5$ additional conformations to match the physical simulator's optimization quality. In this work, we present the Gradual Optimization Learning Framework (GOLF) for energy minimization with neural networks that significantly reduces the required additional data. The framework consists of an efficient data-collecting scheme and an external optimizer. The external optimizer utilizes gradients from the energy prediction model to generate optimization trajectories, and the data-collecting scheme selects additional training data to be processed by the physical simulator. Our results demonstrate that the neural network trained with GOLF performs on par with the oracle on a benchmark of diverse drug-like molecules using $50$x less additional data.
Authors: Shehtab Zaman, Denis Akhiyarov, Mauricio Araya-Polo, Kenneth Chiu
Machine learning and especially deep learning has had an increasing impact on molecule and materials design. In particular, given the growing access to an abundance of high-quality small molecule data for generative modeling for drug design, results for drug discovery have been promising. However, for many important classes of materials such as catalysts, antioxidants, and metal-organic frameworks, such large datasets are not available. Such families of molecules with limited samples and structural similarities are especially prevalent for industrial applications. As is well-known, retraining and even fine-tuning are challenging on such small datasets. Novel, practically applicable molecules are most often derivatives of well-known molecules, suggesting approaches to addressing data scarcity. To address this problem, we introduce $\textbf{STRIDE}$, a generative molecule workflow that generates novel molecules with an unconditional generative model guided by known molecules without any retraining. We generate molecules outside of the training data from a highly specialized set of antioxidant molecules. Our generated molecules have on average 21.7% lower synthetic accessibility scores and also reduce ionization potential by 5.9% of generated molecules via guiding.
Authors: Junren Li, Lei Fang, Jian-Guang Lou
Computer-assisted methods have emerged as valuable tools for retrosynthesis analysis. However, quantifying the plausibility of generated retrosynthesis routes remains a challenging task. We introduce Retro-BLEU, a statistical metric adapted from the well-established BLEU score in machine translation, to evaluate the plausibility of retrosynthesis routes based on reaction template sequences analysis. We demonstrate the effectiveness of Retro-BLEU by applying it to a diverse set of retrosynthesis routes generated by state-of-the-art algorithms and compare the performance with other evaluation metrics. The results show that Retro-BLEU is capable of differentiating between plausible and implausible routes. Furthermore, we provide insights into the strengths and weaknesses of Retro-BLEU, paving the way for future developments and improvements in this field.
Authors: Mohammad Hossein Shayesteh, Behrooz Sharokhzadeh, Behrooz Masoumi
The Human Activity Recognition (HAR) tasks automatically identify human activities using the sensor data, which has numerous applications in healthcare, sports, security, and human-computer interaction. Despite significant advances in HAR, critical challenges still exist. Game theory has emerged as a promising solution to address these challenges in machine learning problems including HAR. However, there is a lack of research work on applying game theory solutions to the HAR problems. This review paper explores the potential of game theory as a solution for HAR tasks, and bridges the gap between game theory and HAR research work by suggesting novel game-theoretic approaches for HAR problems. The contributions of this work include exploring how game theory can improve the accuracy and robustness of HAR models, investigating how game-theoretic concepts can optimize recognition algorithms, and discussing the game-theoretic approaches against the existing HAR methods. The objective is to provide insights into the potential of game theory as a solution for sensor-based HAR, and contribute to develop a more accurate and efficient recognition system in the future research directions.
Authors: Noah J. Bagazinski, Faez Ahmed
Ship design is a years-long process that requires balancing complex design trade-offs to create a ship that is efficient and effective. Finding new ways to improve the ship design process can lead to significant cost savings for ship building and operation. One promising technology is generative artificial intelligence, which has been shown to reduce design cycle time and create novel, high-performing designs. In literature review, generative artificial intelligence has been shown to generate ship hulls; however, ship design is particularly difficult as the hull of a ship requires the consideration of many objectives. This paper presents a study on the generation of parametric ship hull designs using a parametric diffusion model that considers multiple objectives and constraints for the hulls. This denoising diffusion probabilistic model (DDPM) generates the tabular parametric design vectors of a ship hull for evaluation. In addition to a tabular DDPM, this paper details adding guidance to improve the quality of generated ship hull designs. By leveraging classifier guidance, the DDPM produced feasible parametric ship hulls that maintain the coverage of the initial training dataset of ship hulls with a 99.5% rate, a 149x improvement over random sampling of the design vector parameters across the design space. Parametric ship hulls produced with performance guidance saw an average of 91.4% reduction in wave drag coefficients and an average of a 47.9x relative increase in the total displaced volume of the hulls compared to the mean performance of the hulls in the training dataset. The use of a DDPM to generate parametric ship hulls can reduce design time by generating high-performing hull designs for future analysis. These generated hulls have low drag and high volume, which can reduce the cost of operating a ship and increase its potential to generate revenue.
Authors: Jinheon Baek, Nirupama Chandrasekaran, Silviu Cucerzan, Allen herring, Sujay Kumar Jauhar
Large Language Models (LLMs) excel at tackling various natural language tasks. However, due to the significant costs involved in re-training or fine-tuning them, they remain largely static and difficult to personalize. Nevertheless, a variety of applications could benefit from generations that are tailored to users' preferences, goals, and knowledge. Among them is web search, where knowing what a user is trying to accomplish, what they care about, and what they know can lead to improved search experiences. In this work, we propose a novel and general approach that augments an LLM with relevant context from users' interaction histories with a search engine in order to personalize its outputs. Specifically, we construct an entity-centric knowledge store for each user based on their search and browsing activities on the web, which is then leveraged to provide contextually relevant LLM prompt augmentations. This knowledge store is light-weight, since it only produces user-specific aggregate projections of interests and knowledge onto public knowledge graphs, and leverages existing search log infrastructure, thereby mitigating the privacy, compliance, and scalability concerns associated with building deep user profiles for personalization. We then validate our approach on the task of contextual query suggestion, which requires understanding not only the user's current search context but also what they historically know and care about. Through a number of experiments based on human evaluation, we show that our approach is significantly better than several other LLM-powered baselines, generating query suggestions that are contextually more relevant, personalized, and useful.
Authors: Zixun Huang, Hao Zheng
In this paper, we propose a machine learning-based approach to address the lack of ability for designers to optimize urban land use planning from the perspective of vehicle travel demand. Research shows that our computational model can help designers quickly obtain feedback on the vehicle travel demand, which includes its total amount and temporal distribution based on the urban function distribution designed by the designers. It also assists in design optimization and evaluation of the urban function distribution from the perspective of vehicle travel. We obtain the city function distribution information and vehicle hours traveled (VHT) information by collecting the city point-of-interest (POI) data and online vehicle data. The artificial neural networks (ANNs) with the best performance in prediction are selected. By using data sets collected in different regions for mutual prediction and remapping the predictions onto a map for visualization, we evaluate the extent to which the computational model sees use across regions in an attempt to reduce the workload of future urban researchers. Finally, we demonstrate the application of the computational model to help designers obtain feedback on vehicle travel demand in the built environment and combine it with genetic algorithms to optimize the current state of the urban environment to provide recommendations to designers.
Authors: Siao Tang, Xin Wang, Hong Chen, Chaoyu Guan, Zewen Wu, Yansong Tang, Wenwu Zhu
Diffusion models have achieved great success due to their remarkable generation ability. However, their high computational overhead is still a troublesome problem. Recent studies have leveraged post-training quantization (PTQ) to compress diffusion models. However, most of them only focus on unconditional models, leaving the quantization of widely used large pretrained text-to-image models, e.g., Stable Diffusion, largely unexplored. In this paper, we propose a novel post-training quantization method PCR (Progressive Calibration and Relaxing) for text-to-image diffusion models, which consists of a progressive calibration strategy that considers the accumulated quantization error across timesteps, and an activation relaxing strategy that improves the performance with negligible cost. Additionally, we demonstrate the previous metrics for text-to-image diffusion model quantization are not accurate due to the distribution gap. To tackle the problem, we propose a novel QDiffBench benchmark, which utilizes data in the same domain for more accurate evaluation. Besides, QDiffBench also considers the generalization performance of the quantized model outside the calibration dataset. Extensive experiments on Stable Diffusion and Stable Diffusion XL demonstrate the superiority of our method and benchmark. Moreover, we are the first to achieve quantization for Stable Diffusion XL while maintaining the performance.
Authors: Haojun Zhu, Vikram Kapoor, Priya Sharma
The Recommender system is a vital information service on today's Internet. Recently, graph neural networks have emerged as the leading approach for recommender systems. We try to review recent literature on graph neural network-based recommender systems, covering the background and development of both recommender systems and graph neural networks. Then categorizing recommender systems by their settings and graph neural networks by spectral and spatial models, we explore the motivation behind incorporating graph neural networks into recommender systems. We also analyze challenges and open problems in graph construction, embedding propagation and aggregation, and computation efficiency. This guides us to better explore the future directions and developments in this domain.
Authors: Aditi Singh
Text-to-Image and Text-to-Video AI generation models are revolutionary technologies that use deep learning and natural language processing (NLP) techniques to create images and videos from textual descriptions. This paper investigates cutting-edge approaches in the discipline of Text-to-Image and Text-to-Video AI generations. The survey provides an overview of the existing literature as well as an analysis of the approaches used in various studies. It covers data preprocessing techniques, neural network types, and evaluation metrics used in the field. In addition, the paper discusses the challenges and limitations of Text-to-Image and Text-to-Video AI generations, as well as future research directions. Overall, these models have promising potential for a wide range of applications such as video production, content creation, and digital marketing.
Authors: Edward Pearce-Crump
We derive the existence of a new type of neural network, called a compact matrix quantum group equivariant neural network, that learns from data that has an underlying quantum symmetry. We apply the Woronowicz formulation of Tannaka-Krein duality to characterise the weight matrices that appear in these neural networks for any easy compact matrix quantum group. We show that compact matrix quantum group equivariant neural networks contain, as a subclass, all compact matrix group equivariant neural networks. Moreover, we obtain characterisations of the weight matrices for many compact matrix group equivariant neural networks that have not previously appeared in the machine learning literature.
Authors: Danish Gufran, Sudeep Pasricha
Indoor localization has become increasingly vital for many applications from tracking assets to delivering personalized services. Yet, achieving pinpoint accuracy remains a challenge due to variations across indoor environments and devices used to assist with localization. Another emerging challenge is adversarial attacks on indoor localization systems that not only threaten service integrity but also reduce localization accuracy. To combat these challenges, we introduce CALLOC, a novel framework designed to resist adversarial attacks and variations across indoor environments and devices that reduce system accuracy and reliability. CALLOC employs a novel adaptive curriculum learning approach with a domain specific lightweight scaled-dot product attention neural network, tailored for adversarial and variation resilience in practical use cases with resource constrained mobile devices. Experimental evaluations demonstrate that CALLOC can achieve improvements of up to 6.03x in mean error and 4.6x in worst-case error against state-of-the-art indoor localization frameworks, across diverse building floorplans, mobile devices, and adversarial attacks scenarios.
Authors: Blake Downward, Jon Nordby
The time and expense required to collect and label audio data has been a prohibitive factor in the availability of domain specific audio datasets. As the predictive specificity of a classifier depends on the specificity of the labels it is trained on, it follows that finely-labelled datasets are crucial for advances in machine learning. Aiming to stimulate progress in the field of machine listening, this paper introduces AeroSonicDB (YPAD-0523), a dataset of low-flying aircraft sounds for training acoustic detection and classification systems. This paper describes the method of exploiting ADS-B radio transmissions to passively collect and label audio samples. Provides a summary of the collated dataset. Presents baseline results from three binary classification models, then discusses the limitations of the current dataset and its future potential. The dataset contains 625 aircraft recordings ranging in event duration from 18 to 60 seconds, for a total of 8.87 hours of aircraft audio. These 625 samples feature 301 unique aircraft, each of which are supplied with 14 supplementary (non-acoustic) labels to describe the aircraft. The dataset also contains 3.52 hours of ambient background audio ("silence"), as a means to distinguish aircraft noise from other local environmental noises. Additionally, 6 hours of urban soundscape recordings (with aircraft annotations) are included as an ancillary method for evaluating model performance, and to provide a testing ground for real-time applications.
Authors: Shirin Sultana, Jahin Hossain, Maruf Billah, Hasibul Hossain Shajeeb, Saifur Rahman, Keyvan Ansari, Khondokar Fida Hasan
Data from interconnected vehicles may contain sensitive information such as location, driving behavior, personal identifiers, etc. Without adequate safeguards, sharing this data jeopardizes data privacy and system security. The current centralized data-sharing paradigm in these systems raises particular concerns about data privacy. Recognizing these challenges, the shift towards decentralized interactions in technology, as echoed by the principles of Industry 5.0, becomes paramount. This work is closely aligned with these principles, emphasizing decentralized, human-centric, and secure technological interactions in an interconnected vehicular ecosystem. To embody this, we propose a practical approach that merges two emerging technologies: Federated Learning (FL) and Blockchain. The integration of these technologies enables the creation of a decentralized vehicular network. In this setting, vehicles can learn from each other without compromising privacy while also ensuring data integrity and accountability. Initial experiments show that compared to conventional decentralized federated learning techniques, our proposed approach significantly enhances the performance and security of vehicular networks. The system's accuracy stands at 91.92\%. While this may appear to be low in comparison to state-of-the-art federated learning models, our work is noteworthy because, unlike others, it was achieved in a malicious vehicle setting. Despite the challenging environment, our method maintains high accuracy, making it a competent solution for preserving data privacy in vehicular networks.
Authors: Amir Ali Ahmadi, Abraar Chaudhry, Jeffrey Zhang
We present generalizations of Newton's method that incorporate derivatives of an arbitrary order $d$ but maintain a polynomial dependence on dimension in their cost per iteration. At each step, our $d^{\text{th}}$-order method uses semidefinite programming to construct and minimize a sum of squares-convex approximation to the $d^{\text{th}}$-order Taylor expansion of the function we wish to minimize. We prove that our $d^{\text{th}}$-order method has local convergence of order $d$. This results in lower oracle complexity compared to the classical Newton method. We show on numerical examples that basins of attraction around local minima can get larger as $d$ increases. Under additional assumptions, we present a modified algorithm, again with polynomial cost per iteration, which is globally convergent and has local convergence of order $d$.
Authors: Mariana Dória Prata Lima, Gilson Antonio Giraldi, Gastão Florêncio Miranda Junior
In this work we use the persistent homology method, a technique in topological data analysis (TDA), to extract essential topological features from the data space and combine them with deep learning features for classification tasks. In TDA, the concepts of complexes and filtration are building blocks. Firstly, a filtration is constructed from some complex. Then, persistent homology classes are computed, and their evolution along the filtration is visualized through the persistence diagram. Additionally, we applied vectorization techniques to the persistence diagram to make this topological information compatible with machine learning algorithms. This was carried out with the aim of classifying images from multiple classes in the MNIST dataset. Our approach inserts topological features into deep learning approaches composed by single and two-streams neural networks architectures based on a multi-layer perceptron (MLP) and a convolutional neral network (CNN) taylored for multi-class classification in the MNIST dataset. In our analysis, we evaluated the obtained results and compared them with the outcomes achieved through the baselines that are available in the TensorFlow library. The main conclusion is that topological information may increase neural network accuracy in multi-class classification tasks with the price of computational complexity of persistent homology calculation. Up to the best of our knowledge, it is the first work that combines deep learning features and the combination of topological features for multi-class classification tasks.
Authors: Hagen Holthusen, Lukas Lamm, Tim Brepols, Stefanie Reese, Ellen Kuhl
Nature has always been our inspiration in the research, design and development of materials and has driven us to gain a deep understanding of the mechanisms that characterize anisotropy and inelastic behavior. All this knowledge has been accumulated in the principles of thermodynamics. Deduced from these principles, the multiplicative decomposition combined with pseudo potentials are powerful and universal concepts. Simultaneously, the tremendous increase in computational performance enabled us to investigate and rethink our history-dependent material models to make the most of our predictions. Today, we have reached a point where materials and their models are becoming increasingly sophisticated. This raises the question: How do we find the best model that includes all inelastic effects to explain our complex data? Constitutive Artificial Neural Networks (CANN) may answer this question. Here, we extend the CANNs to inelastic materials (iCANN). Rigorous considerations of objectivity, rigid motion of the reference configuration, multiplicative decomposition and its inherent non-uniqueness, restrictions of energy and pseudo potential, and consistent evolution guide us towards the architecture of the iCANN satisfying thermodynamics per design. We combine feed-forward networks of the free energy and pseudo potential with a recurrent neural network approach to take time dependencies into account. We demonstrate that the iCANN is capable of autonomously discovering models for artificially generated data, the response of polymers for cyclic loading and the relaxation behavior of muscle data. As the design of the network is not limited to visco-elasticity, our vision is that the iCANN will reveal to us new ways to find the various inelastic phenomena hidden in the data and to understand their interaction. Our source code, data, and examples are available at doi.org/10.5281/zenodo.10066805
Authors: Lucio Dery, David Grangier, Awni Hannun
Large, pre-trained models are problematic to use in resource constrained applications. Fortunately, task-aware structured pruning methods offer a solution. These approaches reduce model size by dropping structural units like layers and attention heads in a manner that takes into account the end-task. However, these pruning algorithms require more task-specific data than is typically available. We propose a framework which combines structured pruning with transfer learning to reduce the need for task-specific data. Our empirical results answer questions such as: How should the two tasks be coupled? What parameters should be transferred? And, when during training should transfer learning be introduced? Leveraging these insights, we demonstrate that our framework results in pruned models with improved generalization over strong baselines.
Authors: Pouya Pezeshkpour, Hayate Iso, Thom Lake, Nikita Bhutani, Estevam Hruschka
Numerous HR applications are centered around resumes and job descriptions. While they can benefit from advancements in NLP, particularly large language models, their real-world adoption faces challenges due to absence of comprehensive benchmarks for various HR tasks, and lack of smaller models with competitive capabilities. In this paper, we aim to bridge this gap by introducing the Resume-Job Description Benchmark (RJDB). We meticulously craft this benchmark to cater to a wide array of HR tasks, including matching and explaining resumes to job descriptions, extracting skills and experiences from resumes, and editing resumes. To create this benchmark, we propose to distill domain-specific knowledge from a large language model (LLM). We rely on a curated skill-occupation graph to ensure diversity and provide context for LLMs generation. Our benchmark includes over 50 thousand triples of job descriptions, matched resumes and unmatched resumes. Using RJDB, we train multiple smaller student models. Our experiments reveal that the student models achieve near/better performance than the teacher model (GPT-4), affirming the effectiveness of the benchmark. Additionally, we explore the utility of RJDB on out-of-distribution data for skill extraction and resume-job description matching, in zero-shot and weak supervision manner. We release our datasets and code to foster further research and industry applications.
Authors: Calvin Luo, Boqing Gong, Ting Chen, Chen Sun
Recognition and reasoning are two pillars of visual understanding. However, these tasks have an imbalance in focus; whereas recent advances in neural networks have shown strong empirical performance in visual recognition, there has been comparably much less success in solving visual reasoning. Intuitively, unifying these two tasks under a singular framework is desirable, as they are mutually dependent and beneficial. Motivated by the recent success of multi-task transformers for visual recognition and language understanding, we propose a unified neural architecture for visual recognition and reasoning with a generic interface (e.g., tokens) for both. Our framework enables the principled investigation of how different visual recognition tasks, datasets, and inductive biases can help enable spatiotemporal reasoning capabilities. Noticeably, we find that object detection, which requires spatial localization of individual objects, is the most beneficial recognition task for reasoning. We further demonstrate via probing that implicit object-centric representations emerge automatically inside our framework. Intriguingly, we discover that certain architectural choices such as the backbone model of the visual encoder have a significant impact on visual reasoning, but little on object detection. Given the results of our experiments, we believe that visual reasoning should be considered as a first-class citizen alongside visual recognition, as they are strongly correlated but benefit from potentially different design choices.
Authors: Yves Atchade, Xinru Liu, Qiuyun Zhu
We consider inverse problems where the conditional distribution of the observation ${\bf y}$ given the latent variable of interest ${\bf x}$ (also known as the forward model) is known, and we have access to a data set in which multiple instances of ${\bf x}$ and ${\bf y}$ are both observed. In this context, algorithm unrolling has become a very popular approach for designing state-of-the-art deep neural network architectures that effectively exploit the forward model. We analyze the statistical complexity of the gradient descent network (GDN), an algorithm unrolling architecture driven by proximal gradient descent. We show that the unrolling depth needed for the optimal statistical performance of GDNs is of order $\log(n)/\log(\varrho_n^{-1})$, where $n$ is the sample size, and $\varrho_n$ is the convergence rate of the corresponding gradient descent algorithm. We also show that when the negative log-density of the latent variable ${\bf x}$ has a simple proximal operator, then a GDN unrolled at depth $D'$ can solve the inverse problem at the parametric rate $O(D'/\sqrt{n})$. Our results thus also suggest that algorithm unrolling models are prone to overfitting as the unrolling depth $D'$ increases. We provide several examples to illustrate these results.
Authors: Gabriel J. Aguiar, Alberto Cano
Adapting to drifting data streams is a significant challenge in online learning. Concept drift must be detected for effective model adaptation to evolving data properties. Concept drift can impact the data distribution entirely or partially, which makes it difficult for drift detectors to accurately identify the concept drift. Despite the numerous concept drift detectors in the literature, standardized procedures and benchmarks for comprehensive evaluation considering the locality of the drift are lacking. We present a novel categorization of concept drift based on its locality and scale. A systematic approach leads to a set of 2,760 benchmark problems, reflecting various difficulty levels following our proposed categorization. We conduct a comparative assessment of 9 state-of-the-art drift detectors across diverse difficulties, highlighting their strengths and weaknesses for future research. We examine how drift locality influences the classifier performance and propose strategies for different drift categories to minimize the recovery time. Lastly, we provide lessons learned and recommendations for future concept drift research. Our benchmark data streams and experiments are publicly available at https://github.com/gabrieljaguiar/locality-concept-drift.
Authors: Kaustav Bhattacharjee, Soumya Kundu, Indrasis Chakraborty, Aritra Dasgupta
Accurate net load forecasting is vital for energy planning, aiding decisions on trade and load distribution. However, assessing the performance of forecasting models across diverse input variables, like temperature and humidity, remains challenging, particularly for eliciting a high degree of trust in the model outcomes. In this context, there is a growing need for data-driven technological interventions to aid scientists in comprehending how models react to both noisy and clean input variables, thus shedding light on complex behaviors and fostering confidence in the outcomes. In this paper, we present Forte, a visual analytics-based application to explore deep probabilistic net load forecasting models across various input variables and understand the error rates for different scenarios. With carefully designed visual interventions, this web-based interface empowers scientists to derive insights about model performance by simulating diverse scenarios, facilitating an informed decision-making process. We discuss observations made using Forte and demonstrate the effectiveness of visualization techniques to provide valuable insights into the correlation between weather inputs and net load forecasts, ultimately advancing grid capabilities by improving trust in forecasting models.
Authors: Nedelina Teneva, Estevam Hruschka
Despite the recent popularity of knowledge graph (KG) related tasks and benchmarks such as KG embeddings, link prediction, entity alignment and evaluation of the reasoning abilities of pretrained language models as KGs, the structure and properties of real KGs are not well studied. In this paper, we perform a large scale comparative study of 29 real KG datasets from diverse domains such as the natural sciences, medicine, and NLP to analyze their properties and structural patterns. Based on our findings, we make several recommendations regarding KG-based model development and evaluation. We believe that the rich structural information contained in KGs can benefit the development of better KG models across fields and we hope this study will contribute to breaking the existing data silos between different areas of research (e.g., ML, NLP, AI for sciences).
Authors: Mingyuan Fan, Xiaodan Li, Cen Chen, Yinggui Wang
The transferability of adversarial examples can be exploited to launch black-box attacks. However, adversarial examples often present poor transferability. To alleviate this issue, by observing that the diversity of inputs can boost transferability, input regularization based methods are proposed, which craft adversarial examples by combining several transformed inputs. We reveal that input regularization based methods make resultant adversarial examples biased towards flat extreme regions. Inspired by this, we propose an attack called flatness-aware adversarial attack (FAA) which explicitly adds a flatness-aware regularization term in the optimization target to promote the resultant adversarial examples towards flat extreme regions. The flatness-aware regularization term involves gradients of samples around the resultant adversarial examples but optimizing gradients requires the evaluation of Hessian matrix in high-dimension spaces which generally is intractable. To address the problem, we derive an approximate solution to circumvent the construction of Hessian matrix, thereby making FAA practical and cheap. Extensive experiments show the transferability of adversarial examples crafted by FAA can be considerably boosted compared with state-of-the-art baselines.
Authors: Martino Pelucchi, Matias Valdenegro-Toro
ChatGPT took the world by storm for its impressive abilities. Due to its release without documentation, scientists immediately attempted to identify its limits, mainly through its performance in natural language processing (NLP) tasks. This paper aims to join the growing literature regarding ChatGPT's abilities by focusing on its performance in high-resource languages and on its capacity to predict its answers' accuracy by giving a confidence level. The analysis of high-resource languages is of interest as studies have shown that low-resource languages perform worse than English in NLP tasks, but no study so far has analysed whether high-resource languages perform as well as English. The analysis of ChatGPT's confidence calibration has not been carried out before either and is critical to learn about ChatGPT's trustworthiness. In order to study these two aspects, five high-resource languages and two NLP tasks were chosen. ChatGPT was asked to perform both tasks in the five languages and to give a numerical confidence value for each answer. The results show that all the selected high-resource languages perform similarly and that ChatGPT does not have a good confidence calibration, often being overconfident and never giving low confidence values.
Authors: Steve Hanneke, Shay Moran, Jonathan Shafer
We present new upper and lower bounds on the number of learner mistakes in the `transductive' online learning setting of Ben-David, Kushilevitz and Mansour (1997). This setting is similar to standard online learning, except that the adversary fixes a sequence of instances $x_1,\dots,x_n$ to be labeled at the start of the game, and this sequence is known to the learner. Qualitatively, we prove a trichotomy, stating that the minimal number of mistakes made by the learner as $n$ grows can take only one of precisely three possible values: $n$, $\Theta\left(\log (n)\right)$, or $\Theta(1)$. Furthermore, this behavior is determined by a combination of the VC dimension and the Littlestone dimension. Quantitatively, we show a variety of bounds relating the number of mistakes to well-known combinatorial dimensions. In particular, we improve the known lower bound on the constant in the $\Theta(1)$ case from $\Omega\left(\sqrt{\log(d)}\right)$ to $\Omega(\log(d))$ where $d$ is the Littlestone dimension. Finally, we extend our results to cover multiclass classification and the agnostic setting.
Authors: Isaac Caswell, Lisa Wang, Isabel Papadimitriou
Data quality is a problem that perpetually resurfaces throughout the field of NLP, regardless of task, domain, or architecture, and remains especially severe for lower-resource languages. A typical and insidious issue, affecting both training data and model output, is data that is repetitive and dominated by linguistically uninteresting boilerplate, such as price catalogs or computer-generated log files. Though this problem permeates many web-scraped corpora, there has yet to be a benchmark to test against, or a systematic study to find simple metrics that generalize across languages and agree with human judgements of data quality. In the present work, we create and release BREAD, a human-labeled benchmark on repetitive boilerplate vs. plausible linguistic content, spanning 360 languages. We release several baseline CRED (Character REDundancy) scores along with it, and evaluate their effectiveness on BREAD. We hope that the community will use this resource to develop better filtering methods, and that our reference implementations of CRED scores can become standard corpus evaluation tools, driving the development of cleaner language modeling corpora, especially in low-resource languages.
Authors: Xiaochen Wang, Xiao Xiao, Ruhan Zhang, Xuan Zhang, Taesik Na, Tejaswi Tenneti, Haixun Wang, Fenglong Ma
Efficient and accurate product relevance assessment is critical for user experiences and business success. Training a proficient relevance assessment model requires high-quality query-product pairs, often obtained through negative sampling strategies. Unfortunately, current methods introduce pooling bias by mistakenly sampling false negatives, diminishing performance and business impact. To address this, we present Bias-mitigating Hard Negative Sampling (BHNS), a novel negative sampling strategy tailored to identify and adjust for false negatives, building upon our original False Negative Estimation algorithm. Our experiments in the Instacart search setting confirm BHNS as effective for practical e-commerce use. Furthermore, comparative analyses on public dataset showcase its domain-agnostic potential for diverse applications.
Authors: Aina Tersol Montserrat, Alexander R. Loftus, Yael Daihes
In machine learning, classification tasks serve as the cornerstone of a wide range of real-world applications. Reliable, trustworthy classification is particularly intricate in biomedical settings, where the ground truth is often inherently uncertain and relies on high degrees of human expertise for labeling. Traditional metrics such as precision and recall, while valuable, are insufficient for capturing the nuances of these ambiguous scenarios. Here we introduce the concept of aberrant predictions, emphasizing that the nature of classification errors is as critical as their frequency. We propose a novel, efficient training methodology aimed at both reducing the misclassification rate and discerning aberrant predictions. Our framework demonstrates a substantial improvement in model performance, achieving a 20\% increase in precision. We apply this methodology to the less-explored domain of veterinary radiology, where the stakes are high but have not been as extensively studied compared to human medicine. By focusing on the identification and mitigation of aberrant predictions, we enhance the utility and trustworthiness of machine learning classifiers in high-stakes, real-world scenarios, including new applications in the veterinary world.
Authors: Hao Xu, Yifei Wang, Yunrui Li, Pengyu Hong
The versatility of multimodal deep learning holds tremendous promise for advancing scientific research and practical applications. As this field continues to evolve, the collective power of cross-modal analysis promises to drive transformative innovations, leading us to new frontiers in chemical understanding and discovery. Hence, we introduce Asymmetric Contrastive M}ultimodal Learning (ACML) as a novel approach tailored for molecules, showcasing its potential to advance the field of chemistry. ACML harnesses the power of effective asymmetric contrastive learning to seamlessly transfer information from various chemical modalities to molecular graph representations. By combining pre-trained chemical unimodal encoders and a shallow-designed graph encoder, ACML facilitates the assimilation of coordinated chemical semantics from different modalities, leading to comprehensive representation learning with efficient training. This innovative framework enhances the interpretability of learned representations and bolsters the expressive power of graph neural networks. Through practical tasks such as isomer discrimination and uncovering crucial chemical properties for drug discovery, ACML exhibits its capability to revolutionize chemical research and applications, providing a deeper understanding of chemical semantics of different modalities.
Authors: Zhehao Huang, Tao Li, Chenhe Yuan, Yingwen Wu, Xiaolin Huang
Online continual learning is a challenging problem where models must learn from a non-stationary data stream while avoiding catastrophic forgetting. Inter-class imbalance during training has been identified as a major cause of forgetting, leading to model prediction bias towards recently learned classes. In this paper, we theoretically analyze that inter-class imbalance is entirely attributed to imbalanced class-priors, and the function learned from intra-class intrinsic distributions is the Bayes-optimal classifier. To that end, we present that a simple adjustment of model logits during training can effectively resist prior class bias and pursue the corresponding Bayes-optimum. Our proposed method, Logit Adjusted Softmax, can mitigate the impact of inter-class imbalance not only in class-incremental but also in realistic general setups, with little additional computational cost. We evaluate our approach on various benchmarks and demonstrate significant performance improvements compared to prior arts. For example, our approach improves the best baseline by 4.6% on CIFAR10.
Authors: June-Woo Kim, Chihyeon Yoon, Miika Toikkanen, Sangmin Bae, Ho-Young Jung
Deep generative models have emerged as a promising approach in the medical image domain to address data scarcity. However, their use for sequential data like respiratory sounds is less explored. In this work, we propose a straightforward approach to augment imbalanced respiratory sound data using an audio diffusion model as a conditional neural vocoder. We also demonstrate a simple yet effective adversarial fine-tuning method to align features between the synthetic and real respiratory sound samples to improve respiratory sound classification performance. Our experimental results on the ICBHI dataset demonstrate that the proposed adversarial fine-tuning is effective, while only using the conventional augmentation method shows performance degradation. Moreover, our method outperforms the baseline by 2.24% on the ICBHI Score and improves the accuracy of the minority classes up to 26.58%. For the supplementary material, we provide the code at https://github.com/kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound.
Authors: Jianxiang Feng, Jongseok Lee, Simon Geisler, Stephan Gunnemann, Rudolph Triebel
To facilitate reliable deployments of autonomous robots in the real world, Out-of-Distribution (OOD) detection capabilities are often required. A powerful approach for OOD detection is based on density estimation with Normalizing Flows (NFs). However, we find that prior work with NFs attempts to match the complex target distribution topologically with naive base distributions leading to adverse implications. In this work, we circumvent this topological mismatch using an expressive class-conditional base distribution trained with an information-theoretic objective to match the required topology. The proposed method enjoys the merits of wide compatibility with existing learned models without any performance degradation and minimum computation overhead while enhancing OOD detection capabilities. We demonstrate superior results in density estimation and 2D object detection benchmarks in comparison with extensive baselines. Moreover, we showcase the applicability of the method with a real-robot deployment.
Authors: Amanda A Howard, Sarah H Murphy, Shady E Ahmed, Panos Stinis
Physics-informed neural networks and operator networks have shown promise for effectively solving equations modeling physical systems. However, these networks can be difficult or impossible to train accurately for some systems of equations. We present a novel multifidelity framework for stacking physics-informed neural networks and operator networks that facilitates training. We successively build a chain of networks, where the output at one step can act as a low-fidelity input for training the next step, gradually increasing the expressivity of the learned model. The equations imposed at each step of the iterative process can be the same or different (akin to simulated annealing). The iterative (stacking) nature of the proposed method allows us to progressively learn features of a solution that are hard to learn directly. Through benchmark problems including a nonlinear pendulum, the wave equation, and the viscous Burgers equation, we show how stacking can be used to improve the accuracy and reduce the required size of physics-informed neural networks and operator networks.
Authors: Le Chen, Arijit Bhattacharjee, Nesreen K. Ahmed, Niranjan Hasabnis, Gal Oren, Bin Lei, Ali Jannesari
Large language models (LLMs) have become increasingly prominent in academia and industry due to their remarkable performance in diverse applications. As these models evolve with increasing parameters, they excel in tasks like sentiment analysis and machine translation. However, even models with billions of parameters face challenges in tasks demanding multi-step reasoning. Code generation and comprehension, especially in C and C++, emerge as significant challenges. While LLMs trained on code datasets demonstrate competence in many tasks, they struggle with rectifying non-compilable C and C++ code. Our investigation attributes this subpar performance to two primary factors: the quality of the training dataset and the inherent complexity of the problem which demands intricate reasoning. Existing "Chain of Thought" (CoT) prompting techniques aim to enhance multi-step reasoning. This approach, however, retains the limitations associated with the latent drawbacks of LLMs. In this work, we propose CompCodeVet, a compiler-guided CoT approach to produce compilable code from non-compilable ones. Diverging from the conventional approach of utilizing larger LLMs, we employ compilers as a teacher to establish a more robust zero-shot thought process. The evaluation of CompCodeVet on two open-source code datasets shows that CompCodeVet has the ability to improve the training dataset quality for LLMs.
Authors: Jianbin Qin, Sifan Huang, Yaoshu Wang, Jing Zhu, Yifan Zhang, Yukai Miao, Rui Mao, Makoto Onizuka, Chuan Xiao
There is a considerable body of work on data cleaning which employs various principles to rectify erroneous data and transform a dirty dataset into a cleaner one. One of prevalent approaches is probabilistic methods, including Bayesian methods. However, existing probabilistic methods often assume a simplistic distribution (e.g., Gaussian distribution), which is frequently underfitted in practice, or they necessitate experts to provide a complex prior distribution (e.g., via a programming language). This requirement is both labor-intensive and costly, rendering these methods less suitable for real-world applications. In this paper, we propose BClean, a Bayesian Cleaning system that features automatic Bayesian network construction and user interaction. We recast the data cleaning problem as a Bayesian inference that fully exploits the relationships between attributes in the observed dataset and any prior information provided by users. To this end, we present an automatic Bayesian network construction method that extends a structure learning-based functional dependency discovery method with similarity functions to capture the relationships between attributes. Furthermore, our system allows users to modify the generated Bayesian network in order to specify prior information or correct inaccuracies identified by the automatic generation process. We also design an effective scoring model (called the compensative scoring model) necessary for the Bayesian inference. To enhance the efficiency of data cleaning, we propose several approximation strategies for the Bayesian inference, including graph partitioning, domain pruning, and pre-detection. By evaluating on both real-world and synthetic datasets, we demonstrate that BClean is capable of achieving an F-measure of up to 0.9 in data cleaning, outperforming existing Bayesian methods by 2% and other data cleaning methods by 15%.
Authors: Matan Abudy, Nur Lan, Emmanuel Chemla, Roni Katzir
Associative memory architectures are designed for memorization but also offer, through their retrieval method, a form of generalization to unseen inputs: stored memories can be seen as prototypes from this point of view. Focusing on Modern Hopfield Networks (MHN), we show that a large memorization capacity undermines the generalization opportunity. We offer a solution to better optimize this tradeoff. It relies on Minimum Description Length (MDL) to determine during training which memories to store, as well as how many of them.
Authors: Guillaume Quétant, Yury Belousov, Vitaliy Kinakh, Slava Voloshynovskiy
We present a novel information-theoretic framework, termed as TURBO, designed to systematically analyse and generalise auto-encoding methods. We start by examining the principles of information bottleneck and bottleneck-based networks in the auto-encoding setting and identifying their inherent limitations, which become more prominent for data with multiple relevant, physics-related representations. The TURBO framework is then introduced, providing a comprehensive derivation of its core concept consisting of the maximisation of mutual information between various data representations expressed in two directions reflecting the information flows. We illustrate that numerous prevalent neural network models are encompassed within this framework. The paper underscores the insufficiency of the information bottleneck concept in elucidating all such models, thereby establishing TURBO as a preferable theoretical reference. The introduction of TURBO contributes to a richer understanding of data representation and the structure of neural network models, enabling more efficient and versatile applications.
Authors: Shiqi Liu
Generalization is at the core of machine learning models. However, the definition of generalization is not entirely clear. We employ set theory to introduce the concepts of algorithms, hypotheses, and dataset generalization. We analyze the properties of dataset generalization and prove a theorem on surrogate generalization procedures. This theorem leads to our generalization method. Through a generalization experiment on the MNIST dataset, we obtain 13,541 sample bases. When we use the entire training set to evaluate the model's performance, the models achieve an accuracy of 99.945%. However, if we shift the sample bases or modify the neural network structure, the performance experiences a significant decline. We also identify consistently mispredicted samples and find that they are all challenging examples. The experiments substantiated the accuracy of the generalization definition and the effectiveness of the proposed methods. Both the set-theoretic deduction and the experiments help us better understand generalization.
Authors: Donato Crisostomi, Irene Cannistraci, Luca Moschella, Pietro Barbiero, Marco Ciccone, Pietro Liò, Emanuele Rodolà
Models trained on semantically related datasets and tasks exhibit comparable inter-sample relations within their latent spaces. We investigate in this study the aggregation of such latent spaces to create a unified space encompassing the combined information. To this end, we introduce Relative Latent Space Aggregation, a two-step approach that first renders the spaces comparable using relative representations, and then aggregates them via a simple mean. We carefully divide a classification problem into a series of learning tasks under three different settings: sharing samples, classes, or neither. We then train a model on each task and aggregate the resulting latent spaces. We compare the aggregated space with that derived from an end-to-end model trained over all tasks and show that the two spaces are similar. We then observe that the aggregated space is better suited for classification, and empirically demonstrate that it is due to the unique imprints left by task-specific embedders within the representations. We finally test our framework in scenarios where no shared region exists and show that it can still be used to merge the spaces, albeit with diminished benefits over naive merging.
Authors: Michael Yeung, Todd Watts, Sean YW Tan, Pedro F. Ferreira, Andrew D. Scott, Sonia Nielles-Vallespin, Guang Yang
Stain variation is a unique challenge associated with automated analysis of digital pathology. Numerous methods have been developed to improve the robustness of machine learning methods to stain variation, but comparative studies have demonstrated limited benefits to performance. Moreover, methods to handle stain variation were largely developed for H&E stained data, with evaluation generally limited to classification tasks. Here we propose Stain Consistency Learning, a novel framework combining stain-specific augmentation with a stain consistency loss function to learn stain colour invariant features. We perform the first, extensive comparison of methods to handle stain variation for segmentation tasks, comparing ten methods on Masson's trichrome and H&E stained cell and nuclei datasets, respectively. We observed that stain normalisation methods resulted in equivalent or worse performance, while stain augmentation or stain adversarial methods demonstrated improved performance, with the best performance consistently achieved by our proposed approach. The code is available at: https://github.com/mlyg/stain_consistency_learning
Authors: Xiao Luo, Yiyang Gu, Huiyu Jiang, Jinsheng Huang, Wei Ju, Ming Zhang, Yizhou Sun
This paper studies the problem of modeling interacting dynamical systems, which is critical for understanding physical dynamics and biological processes. Recent research predominantly uses geometric graphs to represent these interactions, which are then captured by powerful graph neural networks (GNNs). However, predicting interacting dynamics in challenging scenarios such as out-of-distribution shift and complicated underlying rules remains unsolved. In this paper, we propose a new approach named Graph ODE with factorized prototypes (GOAT) to address the problem. The core of GOAT is to incorporate factorized prototypes from contextual knowledge into a continuous graph ODE framework. Specifically, GOAT employs representation disentanglement and system parameters to extract both object-level and system-level contexts from historical trajectories, which allows us to explicitly model their independent influence and thus enhances the generalization capability under system changes. Then, we integrate these disentangled latent representations into a graph ODE model, which determines a combination of various interacting prototypes for enhanced model expressivity. The entire model is optimized using an end-to-end variational inference framework to maximize the likelihood. Extensive experiments in both in-distribution and out-of-distribution settings validate the superiority of GOAT.
Authors: Deborah Pelacani Cruz, George Strong, Oscar Bates, Carlos Cueto, Jiashun Yao, Lluis Guasch
Quantitative evaluations of differences and/or similarities between data samples define and shape optimisation problems associated with learning data distributions. Current methods to compare data often suffer from limitations in capturing such distributions or lack desirable mathematical properties for optimisation (e.g. smoothness, differentiability, or convexity). In this paper, we introduce a new method to measure (dis)similarities between paired samples inspired by Wiener-filter theory. The convolutional nature of Wiener filters allows us to comprehensively compare data samples in a globally correlated way. We validate our approach in four machine learning applications: data compression, medical imaging imputation, translated classification, and non-parametric generative modelling. Our results demonstrate increased resolution in reconstructed images with better perceptual quality and higher data fidelity, as well as robustness against translations, compared to conventional mean-squared-error analogue implementations.
Authors: Heejeong Nam
Causal disentanglement has great potential for capturing complex situations. However, there is a lack of practical and efficient approaches. It is already known that most unsupervised disentangling methods are unable to produce identifiable results without additional information, often leading to randomly disentangled output. Therefore, most existing models for disentangling are weakly supervised, providing information about intrinsic factors, which incurs excessive costs. Therefore, we propose a novel model, SCADI(SElf-supervised CAusal DIsentanglement), that enables the model to discover semantic factors and learn their causal relationships without any supervision. This model combines a masked structural causal model (SCM) with a pseudo-label generator for causal disentanglement, aiming to provide a new direction for self-supervised causal disentanglement models.
Authors: Ziyang Xiang, Zaixi Zhang, Qi Liu
Categorizing source codes accurately and efficiently is a challenging problem in real-world programming education platform management. In recent years, model-based approaches utilizing abstract syntax trees (ASTs) have been widely applied to code classification tasks. We introduce an approach named the Sparse Attention-based neural network for Code Classification (SACC) in this paper. The approach involves two main steps: In the first step, source code undergoes syntax parsing and preprocessing. The generated abstract syntax tree is split into sequences of subtrees and then encoded using a recursive neural network to obtain a high-dimensional representation. This step simultaneously considers both the logical structure and lexical level information contained within the code. In the second step, the encoded sequences of subtrees are fed into a Transformer model that incorporates sparse attention mechanisms for the purpose of classification. This method efficiently reduces the computational cost of the self-attention mechanisms, thus improving the training speed while preserving effectiveness. Our work introduces a carefully designed sparse attention pattern that is specifically designed to meet the unique needs of code classification tasks. This design helps reduce the influence of redundant information and enhances the overall performance of the model. Finally, we also deal with problems in previous related research, which include issues like incomplete classification labels and a small dataset size. We annotated the CodeNet dataset with algorithm-related labeling categories, which contains a significantly large amount of data. Extensive comparative experimental results demonstrate the effectiveness and efficiency of SACC for the code classification tasks.
Authors: Zhiquan Tan, Weiran Huang
Recently, an unusual phenomenon called grokking has gained much attention, where sometimes a neural network generalizes long after it perfectly fits the training data. We try to understand this seemingly strange phenomenon using the robustness of the neural network. Using a robustness viewpoint, we show that the popular $l_2$ weight norm (metric) of the neural network is actually a sufficient condition for grokking. As we also empirically find that $l_2$ norm correlates with grokking on the test data not in a timely way, we propose new metrics based on robustness and information theory and find that our new metrics correlate well with the grokking phenomenon. Based on the previous observations, we propose methods to speed up the generalization process. In addition, we examine the standard training process on modulo addition dataset and find that it hardly learns other basic group operations before grokking, including the commutative law. Interestingly, the speed up of generalization when using our proposed method can be partially explained by learning the commutative law, a necessary condition when the model groks on test dataset.
Authors: Sompote Youwai, Parchya Makam
Particle size analysis (PSA) is a fundamental technique for evaluating the physical characteristics of soils. However, traditional methods like sieving can be time-consuming and labor-intensive. In this study, we present a novel approach that utilizes computer vision (CV) and the Python programming language for PSA of coarse-grained soils, employing a standard mobile phone camera. By eliminating the need for a high-performance camera, our method offers convenience and cost savings. Our methodology involves using the OPENCV library to detect and measure soil particles in digital photographs taken under ordinary lighting conditions. For accurate particle size determination, a calibration target with known dimensions is placed on a plain paper alongside 20 different sand samples. The proposed method is compared with traditional sieve analysis and exhibits satisfactory performance for soil particles larger than 2 mm, with a mean absolute percent error (MAPE) of approximately 6%. However, particles smaller than 2 mm result in higher MAPE, reaching up to 60%. To address this limitation, we recommend using a higher-resolution camera to capture images of the smaller soil particles. Furthermore, we discuss the advantages, limitations, and potential future improvements of our method. Remarkably, the program can be executed on a mobile phone, providing immediate results without the need to send soil samples to a laboratory. This field-friendly feature makes our approach highly convenient for on-site usage, outside of a traditional laboratory setting. Ultimately, this novel method represents an initial disruption to the industry, enabling efficient particle size analysis of soil without the reliance on laboratory-based sieve analysis. KEYWORDS: Computer vision, Grain size, ARUCO
Authors: Florian Joseph Baader, Stefano Moret, Wolfram Wiesemann, Iain Staffell, André Bardow
Uncertainties surrounding the energy transition often lead modelers to present large sets of scenarios that are challenging for policymakers to interpret and act upon. An alternative approach is to define a few qualitative storylines from stakeholder discussions, which can be affected by biases and infeasibilities. Leveraging decision trees, a popular machine-learning technique, we derive interpretable storylines from many quantitative scenarios and show how the key decisions in the energy transition are interlinked. Specifically, our results demonstrate that choosing a high deployment of renewables and sector coupling makes global decarbonization scenarios robust against uncertainties in climate sensitivity and demand. Also, the energy transition to a fossil-free Europe is primarily determined by choices on the roles of bioenergy, storage, and heat electrification. Our transferrable approach translates vast energy model results into a small set of critical decisions, guiding decision-makers in prioritizing the key factors that will shape the energy transition.
Authors: Seunghoi Kim, Henry F. J. Tregidgo, Ahmed K. Eldaly, Matteo Figini, Daniel C. Alexander
Low-field (LF) MRI scanners (<1T) are still prevalent in settings with limited resources or unreliable power supply. However, they often yield images with lower spatial resolution and contrast than high-field (HF) scanners. This quality disparity can result in inaccurate clinician interpretations. Image Quality Transfer (IQT) has been developed to enhance the quality of images by learning a mapping function between low and high-quality images. Existing IQT models often fail to restore high-frequency features, leading to blurry output. In this paper, we propose a 3D conditional diffusion model to improve 3D volumetric data, specifically LF MR images. Additionally, we incorporate a cross-batch mechanism into the self-attention and padding of our network, ensuring broader contextual awareness even under small 3D patches. Experiments on the publicly available Human Connectome Project (HCP) dataset for IQT and brain parcellation demonstrate that our model outperforms existing methods both quantitatively and qualitatively. The code is publicly available at \url{https://github.com/edshkim98/DiffusionIQT}.
Authors: Mehdi Molkaraie
For a specific class of sparse Gaussian graphical models, we provide a closed-form solution for the determinant of the covariance matrix. In our framework, the graphical interaction model (i.e., the covariance selection model) is equal to replacement product of $\mathcal{K}_{n}$ and $\mathcal{K}_{n-1}$, where $\mathcal{K}_n$ is the complete graph with $n$ vertices. Our analysis is based on taking the Fourier transform of the local factors of the model, which can be viewed as an application of the Normal Factor Graph Duality Theorem and holographic algorithms. The closed-form expression is obtained by applying the Matrix Determinant Lemma on the transformed graphical model. In this context, we will also define a notion of equivalence between two Gaussian graphical models.
Authors: Hossein Simchi, Samira Tajik
The COVID-19 pandemic has forced many people to limit their social activities, which has resulted in a rise in mental illnesses, particularly depression. To diagnose these illnesses with accuracy and speed, and prevent severe outcomes such as suicide, the use of machine learning has become increasingly important. Additionally, to provide precise and understandable diagnoses for better treatment, AI scientists and researchers must develop interpretable AI-based solutions. This article provides an overview of relevant articles in the field of machine learning and interpretable AI, which helps to understand the advantages and disadvantages of using AI in psychiatry disorder detection applications.
Authors: Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu
Federated learning (FL) is gaining increasing popularity in the medical domain for analyzing medical images, which is considered an effective technique to safeguard sensitive patient data and comply with privacy regulations. However, several recent studies have revealed that the default settings of FL may leak private training data under privacy attacks. Thus, it is still unclear whether and to what extent such privacy risks of FL exist in the medical domain, and if so, ``how to mitigate such risks?''. In this paper, first, we propose a holistic framework for Medical data Privacy risk analysis and mitigation in Federated Learning (MedPFL) to analyze privacy risks and develop effective mitigation strategies in FL for protecting private medical data. Second, we demonstrate the substantial privacy risks of using FL to process medical images, where adversaries can easily perform privacy attacks to reconstruct private medical images accurately. Third, we show that the defense approach of adding random noises may not always work effectively to protect medical images against privacy attacks in FL, which poses unique and pressing challenges associated with medical data for privacy protection.
Authors: Paschalis Bizopoulos, Dimitrios Koutsouris
The medical field is creating large amount of data that physicians are unable to decipher and use efficiently. Moreover, rule-based expert systems are inefficient in solving complicated medical tasks or for creating insights using big data. Deep learning has emerged as a more accurate and effective technology in a wide range of medical problems such as diagnosis, prediction and intervention. Deep learning is a representation learning method that consists of layers that transform the data non-linearly, thus, revealing hierarchical relationships and structures. In this review we survey deep learning application papers that use structured data, signal and imaging modalities from cardiology. We discuss the advantages and limitations of applying deep learning in cardiology that also apply in medicine in general, while proposing certain directions as the most viable for clinical use.
Authors: Paschalis Bizopoulos, Dimitrios Koutsouris
Previous literature on unsupervised learning focused on designing structural priors with the aim of learning meaningful features. However, this was done without considering the description length of the learned representations which is a direct and unbiased measure of the model complexity. In this paper, first we introduce the $\varphi$ metric that evaluates unsupervised models based on their reconstruction accuracy and the degree of compression of their internal representations. We then present and define two activation functions (Identity, ReLU) as base of reference and three sparse activation functions (top-k absolutes, Extrema-Pool indices, Extrema) as candidate structures that minimize the previously defined $\varphi$. We lastly present Sparsely Activated Networks (SANs) that consist of kernels with shared weights that, during encoding, are convolved with the input and then passed through a sparse activation function. During decoding, the same weights are convolved with the sparse activation map and subsequently the partial reconstructions from each weight are summed to reconstruct the input. We compare SANs using the five previously defined activation functions on a variety of datasets (Physionet, UCI-epilepsy, MNIST, FMNIST) and show that models that are selected using $\varphi$ have small description representation length and consist of interpretable kernels.
Authors: Christina Winkler, Daniel Worrall, Emiel Hoogeboom, Max Welling
Normalizing Flows (NFs) are able to model complicated distributions p(y) with strong inter-dimensional correlations and high multimodality by transforming a simple base density p(z) through an invertible neural network under the change of variables formula. Such behavior is desirable in multivariate structured prediction tasks, where handcrafted per-pixel loss-based methods inadequately capture strong correlations between output dimensions. We present a study of conditional normalizing flows (CNFs), a class of NFs where the base density to output space mapping is conditioned on an input x, to model conditional densities p(y|x). CNFs are efficient in sampling and inference, they can be trained with a likelihood-based objective, and CNFs, being generative flows, do not suffer from mode collapse or training instabilities. We provide an effective method to train continuous CNFs for binary problems and in particular, we apply these CNFs to super-resolution and vessel segmentation tasks demonstrating competitive performance on standard benchmark datasets in terms of likelihood and conventional metrics.
Authors: Yu Guan, Shuyu Dong, Bin Gao, P.-A. Absil, François Glineur
We consider a Canonical Polyadic (CP) decomposition approach to low-rank tensor completion (LRTC) by incorporating external pairwise similarity relations through graph Laplacian regularization on the CP factor matrices. The usage of graph regularization entails benefits in the learning accuracy of LRTC, but at the same time, induces coupling graph Laplacian terms that hinder the optimization of the tensor completion model. In order to solve graph-regularized LRTC, we propose efficient alternating minimization algorithms by leveraging the block structure of the underlying CP decomposition-based model. For the subproblems of alternating minimization, a linear conjugate gradient subroutine is specifically adapted to graph-regularized LRTC. Alternatively, we circumvent the complicating coupling effects of graph Laplacian terms by using an alternating directions method of multipliers. Based on the Kurdyka-{\L}ojasiewicz property, we show that the sequence generated by the proposed algorithms globally converges to a critical point of the objective function. Moreover, the complexity and convergence rate are also derived. In addition, numerical experiments including synthetic data and real data show that the graph regularized tensor completion model has improved recovery results compared to those without graph regularization, and that the proposed algorithms achieve gains in time efficiency over existing algorithms.
Authors: Paschalis Bizopoulos, Nicholas Vretos, Petros Daras
Recently there has been an explosion in the use of Deep Learning (DL) methods for medical image segmentation. However the field's reliability is hindered by the lack of a common base of reference for accuracy/performance evaluation and the fact that previous research uses different datasets for evaluation. In this paper, an extensive comparison of DL models for lung and COVID-19 lesion segmentation in Computerized Tomography (CT) scans is presented, which can also be used as a benchmark for testing medical image segmentation models. Four DL architectures (Unet, Linknet, FPN, PSPNet) are combined with 25 randomly initialized and pretrained encoders (variations of VGG, DenseNet, ResNet, ResNext, DPN, MobileNet, Xception, Inception-v4, EfficientNet), to construct 200 tested models. Three experimental setups are conducted for lung segmentation, lesion segmentation and lesion segmentation using the original lung masks. A public COVID-19 dataset with 100 CT scan images (80 for train, 20 for validation) is used for training/validation and a different public dataset consisting of 829 images from 9 CT scan volumes for testing. Multiple findings are provided including the best architecture-encoder models for each experiment as well as mean Dice results for each experiment, architecture and encoder independently. Finally, the upper bounds improvements when using lung masks as a preprocessing step or when using pretrained models are quantified. The source code and 600 pretrained models for the three experiments are provided, suitable for fine-tuning in experimental setups without GPU capabilities.
Authors: Xiangqian Sun, Xing Yan, Qi Wu
We propose a multivariate generative model to capture the complex dependence structure often encountered in business and financial data. Our model features heterogeneous and asymmetric tail dependence between all pairs of individual dimensions while also allowing heterogeneity and asymmetry in the tails of the marginals. A significant merit of our model structure is that it is not prone to error propagation in the parameter estimation process, hence very scalable, as the dimensions of datasets grow large. However, the likelihood methods are infeasible for parameter estimation in our case due to the lack of a closed-form density function. Instead, we devise a novel moment learning algorithm to learn the parameters. To demonstrate the effectiveness of the model and its estimator, we test them on simulated as well as real-world datasets. Results show that this framework gives better finite-sample performance compared to the copula-based benchmarks as well as recent similar models.
Authors: Dimitris Bertsimas, Vassilis Digalakis Jr, Michael Linghzi Li, Omar Skali Lami
We present the framework of slowly varying regression under sparsity, allowing sparse regression models to exhibit slow and sparse variations. The problem of parameter estimation is formulated as a mixed-integer optimization problem. We demonstrate that it can be precisely reformulated as a binary convex optimization problem through a novel relaxation technique. This relaxation involves a new equality on Moore-Penrose inverses, convexifying the non-convex objective function while matching the original objective on all feasible binary points. This enables us to efficiently solve the problem to provable optimality using a cutting plane-type algorithm. We develop a highly optimized implementation of this algorithm, substantially improving upon the asymptotic computational complexity of a straightforward implementation. Additionally, we propose a fast heuristic method that guarantees a feasible solution and, as empirically illustrated, produces high-quality warm-start solutions for the binary optimization problem. To tune the framework's hyperparameters, we suggest a practical procedure relying on binary search that, under certain assumptions, is guaranteed to recover the true model parameters. On both synthetic and real-world datasets, we demonstrate that the resulting algorithm outperforms competing formulations in comparable times across various metrics, including estimation accuracy, predictive power, and computational time. The algorithm is highly scalable, allowing us to train models with thousands of parameters. Our implementation is available open-source at https://github.com/vvdigalakis/SSVRegression.git.
Authors: Zhou Shangnan
The emerging field of quantum machine learning has the potential of revolutionizing our perspectives of quantum computing and artificial intelligence. In the predominantly empirical realm of quantum machine learning, a theoretical void persists. This paper addresses the gap by highlighting the quantum cross entropy, a pivotal counterpart to the classical cross entropy. We establish quantum cross entropy's role in quantum data compression, a fundamental machine learning task, by demonstrating that it acts as the compression rate for sub-optimal quantum source coding. Our approach involves a novel, universal quantum data compression protocol based on the quantum generalization of variable-length coding and the principle of quantum strong typicality. This reveals that quantum cross entropy can effectively serve as a loss function in quantum machine learning algorithms. Furthermore, we illustrate that the minimum of quantum cross entropy aligns with the von Neumann entropy, reinforcing its role as the optimal compression rate and underscoring its significance in advancing our understanding of quantum machine learning's theoretical framework.
Authors: Hanzhao Wang, Kalyan Talluri, Xiaocheng Li
We consider dynamic pricing with covariates under a generalized linear demand model: a seller can dynamically adjust the price of a product over a horizon of $T$ time periods, and at each time period $t$, the demand of the product is jointly determined by the price and an observable covariate vector $x_t\in\mathbb{R}^d$ through a generalized linear model with unknown co-efficients. Most of the existing literature assumes the covariate vectors $x_t$'s are independently and identically distributed (i.i.d.); the few papers that relax this assumption either sacrifice model generality or yield sub-optimal regret bounds. In this paper, we show that UCB and Thompson sampling-based pricing algorithms can achieve an $O(d\sqrt{T}\log T)$ regret upper bound without assuming any statistical structure on the covariates $x_t$. Our upper bound on the regret matches the lower bound up to logarithmic factors. We thus show that (i) the i.i.d. assumption is not necessary for obtaining low regret, and (ii) the regret bound can be independent of the (inverse) minimum eigenvalue of the covariance matrix of the $x_t$'s, a quantity present in previous bounds. Moreover, we consider a constrained setting of the dynamic pricing problem where there is a limited and unreplenishable inventory and we develop theoretical results that relate the best achievable algorithm performance to a variation measure with respect to the temporal distribution shift of the covariates. We also discuss conditions under which a better regret is achievable and demonstrate the proposed algorithms' performance with numerical experiments.
Authors: Hamdy Abdelkhalik, Shamminuj Aktar, Yehia Arafa, Atanu Barai, Gopinath Chennupati, Nandakishore Santhi, Nishant Panda, Nirmal Prajapati, Nazmul Haque Turja, Stephan Eidenbenz, Abdel-Hameed Badawy
Recent years have seen the adoption of Machine Learning (ML) techniques to predict the performance of large-scale applications, mostly at a coarse level. In contrast, we propose to use ML techniques for performance prediction at a much finer granularity, namely at the Basic Block (BB) level, which are single entry, single exit code blocks that are used for analysis by the compilers to break down a large code into manageable pieces. We extrapolate the basic block execution counts of GPU applications and use them for predicting the performance for large input sizes from the counts of smaller input sizes. We train a Poisson Neural Network (PNN) model using random input values as well as the lowest input values of the application to learn the relationship between inputs and basic block counts. Experimental results show that the model can accurately predict the basic block execution counts of 16 GPU benchmarks. We achieve an accuracy of 93.5% in extrapolating the basic block counts for large input sets when trained on smaller input sets and an accuracy of 97.7% in predicting basic block counts on random instances. In a case study, we apply the ML model to CUDA GPU benchmarks for performance prediction across a spectrum of applications. We use a variety of metrics for evaluation, including global memory requests and the active cycles of tensor cores, ALU, and FMA units. Results demonstrate the model's capability of predicting the performance of large datasets with an average error rate of 0.85% and 0.17% for global and shared memory requests, respectively. Additionally, to address the utilization of the main functional units in Ampere architecture GPUs, we calculate the active cycles for tensor cores, ALU, FMA, and FP64 units and achieve an average error of 2.3% and 10.66% for ALU and FMA units while the maximum observed error across all tested applications and units reaches 18.5%.
Authors: Florian Mai, Arnaud Pannatier, Fabio Fehr, Haolin Chen, Francois Marelli, Francois Fleuret, James Henderson
Transformer-based architectures are the model of choice for natural language understanding, but they come at a significant cost, as they have quadratic complexity in the input length, require a lot of training data, and can be difficult to tune. In the pursuit of lower costs, we investigate simple MLP-based architectures. We find that existing architectures such as MLPMixer, which achieves token mixing through a static MLP applied to each feature independently, are too detached from the inductive biases required for natural language understanding. In this paper, we propose a simple variant, HyperMixer, which forms the token mixing MLP dynamically using hypernetworks. Empirically, we demonstrate that our model performs better than alternative MLP-based models, and on par with Transformers. In contrast to Transformers, HyperMixer achieves these results at substantially lower costs in terms of processing time, training data, and hyperparameter tuning.
Authors: Yao Yao, Bin Liu, Haoxun He, Dakui Sheng, Ke Wang, Li Xiao, Huanhuan Cao
Input features play a crucial role in DNN-based recommender systems with thousands of categorical and continuous fields from users, items, contexts, and interactions. Noisy features and inappropriate embedding dimension assignments can deteriorate the performance of recommender systems and introduce unnecessary complexity in model training and online serving. Optimizing the input configuration of DNN models, including feature selection and embedding dimension assignment, has become one of the essential topics in feature engineering. However, in existing industrial practices, feature selection and dimension search are optimized sequentially, i.e., feature selection is performed first, followed by dimension search to determine the optimal dimension size for each selected feature. Such a sequential optimization mechanism increases training costs and risks generating suboptimal input configurations. To address this problem, we propose a differentiable neural input razor (i-Razor) that enables joint optimization of feature selection and dimension search. Concretely, we introduce an end-to-end differentiable model to learn the relative importance of different embedding regions of each feature. Furthermore, a flexible pruning algorithm is proposed to achieve feature filtering and dimension derivation simultaneously. Extensive experiments on two large-scale public datasets in the Click-Through-Rate (CTR) prediction task demonstrate the efficacy and superiority of i-Razor in balancing model complexity and performance.
Authors: Luca Masserano, Tommaso Dorigo, Rafael Izbicki, Mikael Kuusela, Ann B. Lee
Prediction algorithms, such as deep neural networks (DNNs), are used in many domain sciences to directly estimate internal parameters of interest in simulator-based models, especially in settings where the observations include images or complex high-dimensional data. In parallel, modern neural density estimators, such as normalizing flows, are becoming increasingly popular for uncertainty quantification, especially when both parameters and observations are high-dimensional. However, parameter inference is an inverse problem and not a prediction task; thus, an open challenge is to construct conditionally valid and precise confidence regions, with a guaranteed probability of covering the true parameters of the data-generating process, no matter what the (unknown) parameter values are, and without relying on large-sample theory. Many simulator-based inference (SBI) methods are indeed known to produce biased or overly confident parameter regions, yielding misleading uncertainty estimates. This paper presents WALDO, a novel method to construct confidence regions with finite-sample conditional validity by leveraging prediction algorithms or posterior estimators that are currently widely adopted in SBI. WALDO reframes the well-known Wald test statistic, and uses a computationally efficient regression-based machinery for classical Neyman inversion of hypothesis tests. We apply our method to a recent high-energy physics problem, where prediction with DNNs has previously led to estimates with prediction bias. We also illustrate how our approach can correct overly confident posterior regions computed with normalizing flows.
Authors: Stefano Sarao Mannelli, Federica Gerace, Negar Rostamzadeh, Luca Saglietti
Machine learning (ML) may be oblivious to human bias but it is not immune to its perpetuation. Marginalisation and iniquitous group representation are often traceable in the very data used for training, and may be reflected or even enhanced by the learning models. In the present work, we aim at clarifying the role played by data geometry in the emergence of ML bias. We introduce an exactly solvable high-dimensional model of data imbalance, where parametric control over the many bias-inducing factors allows for an extensive exploration of the bias inheritance mechanism. Through the tools of statistical physics, we analytically characterise the typical properties of learning models trained in this synthetic framework and obtain exact predictions for the observables that are commonly employed for fairness assessment. Despite the simplicity of the data model, we retrace and unpack typical unfairness behaviour observed on real-world datasets. We also obtain a detailed analytical characterisation of a class of bias mitigation strategies. We first consider a basic loss-reweighing scheme, which allows for an implicit minimisation of different unfairness metrics, and quantify the incompatibilities between some existing fairness criteria. Then, we consider a novel mitigation strategy based on a matched inference approach, consisting in the introduction of coupled learning models. Our theoretical analysis of this approach shows that the coupled strategy can strike superior fairness-accuracy trade-offs.
Authors: Justin Whitehouse, Zhiwei Steven Wu, Aaditya Ramdas, Ryan Rogers
There is a disconnect between how researchers and practitioners handle privacy-utility tradeoffs. Researchers primarily operate from a privacy first perspective, setting strict privacy requirements and minimizing risk subject to these constraints. Practitioners often desire an accuracy first perspective, possibly satisfied with the greatest privacy they can get subject to obtaining sufficiently small error. Ligett et al. have introduced a "noise reduction" algorithm to address the latter perspective. The authors show that by adding correlated Laplace noise and progressively reducing it on demand, it is possible to produce a sequence of increasingly accurate estimates of a private parameter while only paying a privacy cost for the least noisy iterate released. In this work, we generalize noise reduction to the setting of Gaussian noise, introducing the Brownian mechanism. The Brownian mechanism works by first adding Gaussian noise of high variance corresponding to the final point of a simulated Brownian motion. Then, at the practitioner's discretion, noise is gradually decreased by tracing back along the Brownian path to an earlier time. Our mechanism is more naturally applicable to the common setting of bounded $\ell_2$-sensitivity, empirically outperforms existing work on common statistical tasks, and provides customizable control of privacy loss over the entire interaction with the practitioner. We complement our Brownian mechanism with ReducedAboveThreshold, a generalization of the classical AboveThreshold algorithm that provides adaptive privacy guarantees. Overall, our results demonstrate that one can meet utility constraints while still maintaining strong levels of privacy.
Authors: Sainyam Galhotra, Arya Mazumdar, Soumyabrata Pal, Barna Saha
To capture inherent geometric features of many community detection problems, we propose to use a new random graph model of communities that we call a \textit{Geometric Block Model}. The geometric block model builds on the \emph{random geometric graphs} (Gilbert, 1961), one of the basic models of random graphs for spatial networks, in the same way that the well-studied stochastic block model builds on the Erd\H{o}s-R\'{en}yi random graphs. It is also a natural extension of random community models inspired by the recent theoretical and practical advancements in community detection. To analyze the geometric block model, we first provide new connectivity results for \emph{random annulus graphs} which are generalizations of random geometric graphs. The connectivity properties of geometric graphs have been studied since their introduction, and analyzing them has been difficult due to correlated edge formation.
We then use the connectivity results of random annulus graphs to provide necessary and sufficient conditions for efficient recovery of communities for the geometric block model. We show that a simple triangle-counting algorithm to detect communities in the geometric block model is near-optimal. For this we consider two regimes of graph density.
In the regime where the average degree of the graph grows logarithmically with number of vertices, we show that our algorithm performs extremely well, both theoretically and practically. In contrast, the triangle-counting algorithm is far from being optimum for the stochastic block model in the logarithmic degree regime. We also look at the regime where the average degree of the graph grows linearly with the number of vertices $n$, and hence to store the graph one needs $\Theta(n^2)$ memory. We show that our algorithm needs to store only $O(n \log n)$ edges in this regime to recover the latent communities.
Authors: Ben Dai, Chunlin Li
Segmentation has emerged as a fundamental field of computer vision and natural language processing, which assigns a label to every pixel/feature to extract regions of interest from an image/text. To evaluate the performance of segmentation, the Dice and IoU metrics are used to measure the degree of overlap between the ground truth and the predicted segmentation. In this paper, we establish a theoretical foundation of segmentation with respect to the Dice/IoU metrics, including the Bayes rule and Dice-/IoU-calibration, analogous to classification-calibration or Fisher consistency in classification. We prove that the existing thresholding-based framework with most operating losses are not consistent with respect to the Dice/IoU metrics, and thus may lead to a suboptimal solution. To address this pitfall, we propose a novel consistent ranking-based framework, namely RankDice/RankIoU, inspired by plug-in rules of the Bayes segmentation rule. Three numerical algorithms with GPU parallel execution are developed to implement the proposed framework in large-scale and high-dimensional segmentation. We study statistical properties of the proposed framework. We show it is Dice-/IoU-calibrated, and its excess risk bounds and the rate of convergence are also provided. The numerical effectiveness of RankDice/mRankDice is demonstrated in various simulated examples and Fine-annotated CityScapes, Pascal VOC and Kvasir-SEG datasets with state-of-the-art deep learning architectures.
Authors: Kamel Lahouel, Michael Wells, Victor Rielly, Ethan Lew, David Lovitz, Bruno M. Jedynak
Learning nonparametric systems of Ordinary Differential Equations (ODEs) dot x = f(t,x) from noisy data is an emerging machine learning topic. We use the well-developed theory of Reproducing Kernel Hilbert Spaces (RKHS) to define candidates for f for which the solution of the ODE exists and is unique. Learning f consists of solving a constrained optimization problem in an RKHS. We propose a penalty method that iteratively uses the Representer theorem and Euler approximations to provide a numerical solution. We prove a generalization bound for the L2 distance between x and its estimator and provide experimental comparisons with the state-of-the-art.
Authors: Chien-Ming Chi, Yingying Fan, Jinchi Lv
Quantifying the usefulness of individual features in random forests learning can greatly enhance its interpretability. Existing studies have shown that some popularly used feature importance measures for random forests suffer from the bias issue. In addition, there lack comprehensive size and power analyses for most of these existing methods. In this paper, we approach the problem via hypothesis testing, and suggest a framework of the self-normalized feature-residual correlation test (FACT) for evaluating the significance of a given feature in the random forests model with bias-resistance property, where our null hypothesis concerns whether the feature is conditionally independent of the response given all other features. Such an endeavor on random forests inference is empowered by some recent developments on high-dimensional random forests consistency. Under a fairly general high-dimensional nonparametric model setting with dependent features, we formally establish that FACT can provide theoretically justified feature importance test with controlled type I error and enjoy appealing power property. The theoretical results and finite-sample advantages of the newly suggested method are illustrated with several simulation examples and an economic forecasting application.
Authors: Matthew Dicks, Andrew Paskaramoorthy, Tim Gebbie
We consider the learning dynamics of a single reinforcement learning optimal execution trading agent when it interacts with an event driven agent-based financial market model. Trading takes place asynchronously through a matching engine in event time. The optimal execution agent is considered at different levels of initial order-sizes and differently sized state spaces. The resulting impact on the agent-based model and market are considered using a calibration approach that explores changes in the empirical stylised facts and price impact curves. Convergence, volume trajectory and action trace plots are used to visualise the learning dynamics. Here the smaller state space agents had the number of states they visited converge much faster than the larger state space agents, and they were able to start learning to trade intuitively using the spread and volume states. We find that the moments of the model are robust to the impact of the learning agents except for the Hurst exponent, which was lowered by the introduction of strategic order-splitting. The introduction of the learning agent preserves the shape of the price impact curves but can reduce the trade-sign auto-correlations when their trading volumes increase.
Authors: Raphaël Berthier
Diagonal linear networks (DLNs) are a toy simplification of artificial neural networks; they consist in a quadratic reparametrization of linear regression inducing a sparse implicit regularization. In this paper, we describe the trajectory of the gradient flow of DLNs in the limit of small initialization. We show that incremental learning is effectively performed in the limit: coordinates are successively activated, while the iterate is the minimizer of the loss constrained to have support on the active coordinates only. This shows that the sparse implicit regularization of DLNs decreases with time. This work is restricted to the underparametrized regime with anti-correlated features for technical reasons.
Authors: Alexander Marusov, Alexey Zaytsev
The representation learning problem in the oil & gas industry aims to construct a model that provides a representation based on logging data for a well interval. Previous attempts are mainly supervised and focus on similarity task, which estimates closeness between intervals. We desire to build informative representations without using supervised (labelled) data. One of the possible approaches is self-supervised learning (SSL). In contrast to the supervised paradigm, this one requires little or no labels for the data. Nowadays, most SSL approaches are either contrastive or non-contrastive. Contrastive methods make representations of similar (positive) objects closer and distancing different (negative) ones. Due to possible wrong marking of positive and negative pairs, these methods can provide an inferior performance. Non-contrastive methods don't rely on such labelling and are widespread in computer vision. They learn using only pairs of similar objects that are easier to identify in logging data.
We are the first to introduce non-contrastive SSL for well-logging data. In particular, we exploit Bootstrap Your Own Latent (BYOL) and Barlow Twins methods that avoid using negative pairs and focus only on matching positive pairs. The crucial part of these methods is an augmentation strategy. Our augmentation strategies and adaption of BYOL and Barlow Twins together allow us to achieve superior quality on clusterization and mostly the best performance on different classification tasks. Our results prove the usefulness of the proposed non-contrastive self-supervised approaches for representation learning and interval similarity in particular.
Authors: Ananda Padhmanabhan Suresh, Sanjana Jain, Pavit Noinongyao, Ankush Ganguly
In recent years, language-driven artistic style transfer has emerged as a new type of style transfer technique, eliminating the need for a reference style image by using natural language descriptions of the style. The first model to achieve this, called CLIPstyler, has demonstrated impressive stylisation results. However, its lengthy optimisation procedure at runtime for each query limits its suitability for many practical applications. In this work, we present FastCLIPstyler, a generalised text-based image style transfer model capable of stylising images in a single forward pass for arbitrary text inputs. Furthermore, we introduce EdgeCLIPstyler, a lightweight model designed for compatibility with resource-constrained devices. Through quantitative and qualitative comparisons with state-of-the-art approaches, we demonstrate that our models achieve superior stylisation quality based on measurable metrics while offering significantly improved runtime efficiency, particularly on edge devices.
Authors: Tsun-Hsuan Wang, Wei Xiao, Tim Seyde, Ramin Hasani, Daniela Rus
The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning. Understanding how learning-based controllers make decisions is crucial since robots are often safety-critical systems. This urges a formal and quantitative understanding of the explanatory factors in the interpretability of robot learning. In this paper, we aim to study interpretability of compact neural policies through the lens of disentangled representation. We leverage decision trees to obtain factors of variation [1] for disentanglement in robot learning; these encapsulate skills, behaviors, or strategies toward solving tasks. To assess how well networks uncover the underlying task dynamics, we introduce interpretability metrics that measure disentanglement of learned neural dynamics from a concentration of decisions, mutual information and modularity perspective. We showcase the effectiveness of the connection between interpretability and disentanglement consistently across extensive experimental analysis.
Authors: Satesh Ramdhani
The separation of performance metrics from gradient based loss functions may not always give optimal results and may miss vital aggregate information. This paper investigates incorporating a performance metric alongside differentiable loss functions to inform training outcomes. The goal is to guide model performance and interpretation by assuming statistical distributions on this performance metric for dynamic weighting. The focus is on van Rijsbergens $F_{\beta}$ metric -- a popular choice for gauging classification performance. Through distributional assumptions on the $F_{\beta}$, an intermediary link can be established to the standard binary cross-entropy via dynamic penalty weights. First, the $F_{\beta}$ metric is reformulated to facilitate assuming statistical distributions with accompanying proofs for the cumulative density function. These probabilities are used within a knee curve algorithm to find an optimal $\beta$ or $\beta_{opt}$. This $\beta_{opt}$ is used as a weight or penalty in the proposed weighted binary cross-entropy. Experimentation on publicly available data along with benchmark analysis mostly yields better and interpretable results as compared to the baseline for both imbalanced and balanced classes. For example, for the IMDB text data with known labeling errors, a 14% boost in $F_1$ score is shown. The results also reveal commonalities between the penalty model families derived in this paper and the suitability of recall-centric or precision-centric parameters used in the optimization. The flexibility of this methodology can enhance interpretation.
Authors: Songyan Hou, Parnian Kassraie, Anastasis Kratsios, Andreas Krause, Jonas Rothfuss
Existing generalization bounds fail to explain crucial factors that drive the generalization of modern neural networks. Since such bounds often hold uniformly over all parameters, they suffer from over-parametrization and fail to account for the strong inductive bias of initialization and stochastic gradient descent. As an alternative, we propose a novel optimal transport interpretation of the generalization problem. This allows us to derive instance-dependent generalization bounds that depend on the local Lipschitz regularity of the learned prediction function in the data space. Therefore, our bounds are agnostic to the parametrization of the model and work well when the number of training samples is much smaller than the number of parameters. With small modifications, our approach yields accelerated rates for data on low-dimensional manifolds and guarantees under distribution shifts. We empirically analyze our generalization bounds for neural networks, showing that the bound values are meaningful and capture the effect of popular regularization methods during training.
Authors: Amanpreet Singh, Mike D'Arcy, Arman Cohan, Doug Downey, Sergey Feldman
Learned representations of scientific documents can serve as valuable input features for downstream tasks without further fine-tuning. However, existing benchmarks for evaluating these representations fail to capture the diversity of relevant tasks. In response, we introduce SciRepEval, the first comprehensive benchmark for training and evaluating scientific document representations. It includes 24 challenging and realistic tasks, 8 of which are new, across four formats: classification, regression, ranking and search. We then use this benchmark to study and improve the generalization ability of scientific document representation models. We show how state-of-the-art models like SPECTER and SciNCL struggle to generalize across the task formats, and that simple multi-task training fails to improve them. However, a new approach that learns multiple embeddings per document, each tailored to a different format, can improve performance. We experiment with task-format-specific control codes and adapters and find they outperform the existing single-embedding state-of-the-art by over 2 points absolute. We release the resulting family of multi-format models, called SPECTER2, for the community to use and build on.
Authors: Caspar Oesterheld, Johannes Treutlein, Roger Grosse, Vincent Conitzer, Jakob Foerster
As machine learning agents act more autonomously in the world, they will increasingly interact with each other. Unfortunately, in many social dilemmas like the one-shot Prisoner's Dilemma, standard game theory predicts that ML agents will fail to cooperate with each other. Prior work has shown that one way to enable cooperative outcomes in the one-shot Prisoner's Dilemma is to make the agents mutually transparent to each other, i.e., to allow them to access one another's source code (Rubinstein 1998, Tennenholtz 2004) -- or weights in the case of ML agents. However, full transparency is often unrealistic, whereas partial transparency is commonplace. Moreover, it is challenging for agents to learn their way to cooperation in the full transparency setting. In this paper, we introduce a more realistic setting in which agents only observe a single number indicating how similar they are to each other. We prove that this allows for the same set of cooperative outcomes as the full transparency setting. We also demonstrate experimentally that cooperation can be learned using simple ML methods.
Authors: Moritz Kappel, Vladislav Golyanik, Susana Castillo, Christian Theobalt, Marcus Magnor
The reconstruction and novel view synthesis of dynamic scenes recently gained increased attention. As reconstruction from large-scale multi-view data involves immense memory and computational requirements, recent benchmark datasets provide collections of single monocular views per timestamp sampled from multiple (virtual) cameras. We refer to this form of inputs as "monocularized" data. Existing work shows impressive results for synthetic setups and forward-facing real-world data, but is often limited in the training speed and angular range for generating novel views. This paper addresses these limitations and proposes a new method for full 360{\deg} inward-facing novel view synthesis of non-rigidly deforming scenes. At the core of our method are: 1) An efficient deformation module that decouples the processing of spatial and temporal information for accelerated training and inference; and 2) A static module representing the canonical scene as a fast hash-encoded neural radiance field. In addition to existing synthetic monocularized data, we systematically analyze the performance on real-world inward-facing scenes using a newly recorded challenging dataset sampled from a synchronized large-scale multi-view rig. In both cases, our method is significantly faster than previous methods, converging in less than 7 minutes and achieving real-time framerates at 1K resolution, while obtaining a higher visual accuracy for generated novel views. Our source code and data is available at our project page https://graphics.tu-bs.de/publications/kappel2022fast.
Authors: Zimeng Fan, Nianli Peng, Muhang Tian, Brandon Fain
We study fair multi-objective reinforcement learning in which an agent must learn a policy that simultaneously achieves high reward on multiple dimensions of a vector-valued reward. Motivated by the fair resource allocation literature, we model this as an expected welfare maximization problem, for some nonlinear fair welfare function of the vector of long-term cumulative rewards. One canonical example of such a function is the Nash Social Welfare, or geometric mean, the log transform of which is also known as the Proportional Fairness objective. We show that even approximately optimal optimization of the expected Nash Social Welfare is computationally intractable even in the tabular case. Nevertheless, we provide a novel adaptation of Q-learning that combines nonlinear scalarized learning updates and non-stationary action selection to learn effective policies for optimizing nonlinear welfare functions. We show that our algorithm is provably convergent, and we demonstrate experimentally that our approach outperforms techniques based on linear scalarization, mixtures of optimal linear scalarizations, or stationary action selection for the Nash Social Welfare Objective.
Authors: Mohammad Pasande, Reshad Hosseini, Babak Nadjar Araabi
Gaussian Mixture Models (GMMs) are one of the most potent parametric density models used extensively in many applications. Flexibly-tied factorization of the covariance matrices in GMMs is a powerful approach for coping with the challenges of common GMMs when faced with high-dimensional data and complex densities which often demand a large number of Gaussian components. However, the expectation-maximization algorithm for fitting flexibly-tied GMMs still encounters difficulties with streaming and very large dimensional data. To overcome these challenges, this paper suggests the use of first-order stochastic optimization algorithms. Specifically, we propose a new stochastic optimization algorithm on the manifold of orthogonal matrices. Through numerous empirical results on both synthetic and real datasets, we observe that stochastic optimization methods can outperform the expectation-maximization algorithm in terms of attaining better likelihood, needing fewer epochs for convergence, and consuming less time per each epoch.
Authors: Soumen Pachal, Shalabh Bhatnagar, L.A. Prashanth
We present in this paper a family of generalized simultaneous perturbation-based gradient search (GSPGS) estimators that use noisy function measurements. The number of function measurements required by each estimator is guided by the desired level of accuracy. We first present in detail unbalanced generalized simultaneous perturbation stochastic approximation (GSPSA) estimators and later present the balanced versions (B-GSPSA) of these. We extend this idea further and present the generalized smoothed functional (GSF) and generalized random directions stochastic approximation (GRDSA) estimators, respectively, as well as their balanced variants. We show that estimators within any specified class requiring more number of function measurements result in lower estimator bias. We present a detailed analysis of both the asymptotic and non-asymptotic convergence of the resulting stochastic approximation schemes. We further present a series of experimental results with the various GSPGS estimators on the Rastrigin and quadratic function objectives. Our experiments are seen to validate our theoretical findings.
Authors: Beatrice Couture (Université de Montréal), Farah Verret (Université de Montréal), Maxime Gohier (Université du Québec à Rimouski), Dominique Deslandres (Université de Montréal)
The arrival of handwriting recognition technologies offers new possibilities for research in heritage studies. However, it is now necessary to reflect on the experiences and the practices developed by research teams. Our use of the Transkribus platform since 2018 has led us to search for the most significant ways to improve the performance of our handwritten text recognition (HTR) models which are made to transcribe French handwriting dating from the 17th century. This article therefore reports on the impacts of creating transcribing protocols, using the language model at full scale and determining the best way to use base models in order to help increase the performance of HTR models. Combining all of these elements can indeed increase the performance of a single model by more than 20% (reaching a Character Error Rate below 5%). This article also discusses some challenges regarding the collaborative nature of HTR platforms such as Transkribus and the way researchers can share their data generated in the process of creating or training handwritten text recognition models.
Authors: David Chiang, Peter Cholak, Anand Pillay
Characterizing neural networks in terms of better-understood formal systems has the potential to yield new insights into the power and limitations of these networks. Doing so for transformers remains an active area of research. Bhattamishra and others have shown that transformer encoders are at least as expressive as a certain kind of counter machine, while Merrill and Sabharwal have shown that fixed-precision transformer encoders recognize only languages in uniform $TC^0$. We connect and strengthen these results by identifying a variant of first-order logic with counting quantifiers that is simultaneously an upper bound for fixed-precision transformer encoders and a lower bound for transformer encoders. This brings us much closer than before to an exact characterization of the languages that transformer encoders recognize.
Authors: Nathan Fradet, Nicolas Gutowski, Fabien Chhel, Jean-Pierre Briot
When used with deep learning, the symbolic music modality is often coupled with language model architectures. To do so, the music needs to be tokenized, i.e. converted into a sequence of discrete tokens. This can be achieved by different approaches, as music can be composed of simultaneous tracks, of simultaneous notes with several attributes. Until now, the proposed tokenizations rely on small vocabularies of tokens describing the note attributes and time events, resulting in fairly long token sequences, and a sub-optimal use of the embedding space of language models. Recent research has put efforts on reducing the overall sequence length by merging embeddings or combining tokens. In this paper, we show that Byte Pair Encoding, a compression technique widely used for natural language, significantly decreases the sequence length while increasing the vocabulary size. By doing so, we leverage the embedding capabilities of such models with more expressive tokens, resulting in both better results and faster inference in generation and classification tasks. The source code is shared on Github, along with a companion website. Finally, BPE is directly implemented in MidiTok, allowing the reader to easily benefit from this method.
Authors: Ashkan Parsi, David O'Callaghan, Joseph Lemley
Driver stress is a major cause of car accidents and death worldwide. Furthermore, persistent stress is a health problem, contributing to hypertension and other diseases of the cardiovascular system. Stress has a measurable impact on heart and breathing rates and stress levels can be inferred from such measurements. Galvanic skin response is a common test to measure the perspiration caused by both physiological and psychological stress, as well as extreme emotions. In this paper, galvanic skin response is used to estimate the ground truth stress levels. A feature selection technique based on the minimal redundancy-maximal relevance method is then applied to multiple heart rate variability and breathing rate metrics to identify a novel and optimal combination for use in detecting stress. The support vector machine algorithm with a radial basis function kernel was used along with these features to reliably predict stress. The proposed method has achieved a high level of accuracy on the target dataset.
Authors: Masatoshi Uehara, Nathan Kallus, Jason D. Lee, Wen Sun
In offline reinforcement learning (RL) we have no opportunity to explore so we must make assumptions that the data is sufficient to guide picking a good policy, taking the form of assuming some coverage, realizability, Bellman completeness, and/or hard margin (gap). In this work we propose value-based algorithms for offline RL with PAC guarantees under just partial coverage, specifically, coverage of just a single comparator policy, and realizability of soft (entropy-regularized) Q-function of the single policy and a related function defined as a saddle point of certain minimax optimization problem. This offers refined and generally more lax conditions for offline RL. We further show an analogous result for vanilla Q-functions under a soft margin condition. To attain these guarantees, we leverage novel minimax learning algorithms to accurately estimate soft or vanilla Q-functions with $L^2$-convergence guarantees. Our algorithms' loss functions arise from casting the estimation problems as nonlinear convex optimization problems and Lagrangifying.
Authors: Kevin Scaria, Himanshu Gupta, Siddharth Goyal, Saurabh Arjun Sawant, Swaroop Mishra, Chitta Baral
We introduce InstructABSA, an instruction learning paradigm for Aspect-Based Sentiment Analysis (ABSA) subtasks. Our method introduces positive, negative, and neutral examples to each training sample, and instruction tune the model (Tk-Instruct) for ABSA subtasks, yielding significant performance improvements. Experimental results on the Sem Eval 2014, 15, and 16 datasets demonstrate that InstructABSA outperforms the previous state-of-the-art (SOTA) approaches on Term Extraction (ATE), Sentiment Classification(ATSC) and Sentiment Pair Extraction (ASPE) subtasks. In particular, InstructABSA outperforms the previous state-of-the-art (SOTA) on the Rest14 ATE subtask by 5.69% points, the Rest15 ATSC subtask by 9.59% points, and the Lapt14 AOPE subtask by 3.37% points, surpassing 7x larger models. We also get competitive results on AOOE, AOPE, and AOSTE subtasks indicating strong generalization ability to all subtasks. Exploring sample efficiency reveals that just 50% train data is required to get competitive results with other instruction tuning approaches. Lastly, we assess the quality of instructions and observe that InstructABSA's performance experiences a decline of ~10% when adding misleading examples.
Authors: Oren Yuval, Saharon Rosset
We present a methodology for using unlabeled data to design semi supervised learning (SSL) methods that improve the prediction performance of supervised learning for regression tasks. The main idea is to design different mechanisms for integrating the unlabeled data, and include in each of them a mixing parameter $\alpha$, controlling the weight given to the unlabeled data. Focusing on Generalized Linear Models (GLM) and linear interpolators classes of models, we analyze the characteristics of different mixing mechanisms, and prove that in all cases, it is invariably beneficial to integrate the unlabeled data with some nonzero mixing ratio $\alpha>0$, in terms of predictive performance. Moreover, we provide a rigorous framework to estimate the best mixing ratio $\alpha^*$ where mixed SSL delivers the best predictive performance, while using the labeled and unlabeled data on hand.
The effectiveness of our methodology in delivering substantial improvement compared to the standard supervised models, in a variety of settings, is demonstrated empirically through extensive simulation, in a manner that supports the theoretical analysis. We also demonstrate the applicability of our methodology (with some intuitive modifications) to improve more complex models, such as deep neural networks, in real-world regression tasks.
Authors: Sagar Patel, Junyang Zhang, Sangeetha Abdu Jyothi, Nina Narodytska
Deep Reinforcement Learning (DRL) has shown promise in various networking environments. However, these environments present several fundamental challenges for standard DRL techniques. They are difficult to explore and exhibit high levels of noise and uncertainty. Although these challenges complicate the training process, we find that in practice we can substantially mitigate their effects and even achieve state-of-the-art real-world performance by addressing a factor that has been previously overlooked: the skewed input trace distribution in DRL training datasets.
We introduce a generalized framework, Plume, to automatically identify and balance the skew using a three-stage process. First, we identify the critical features that determine the behavior of the traces. Second, we classify the traces into clusters. Finally, we prioritize the salient clusters to improve the overall performance of the controller. Plume seamlessly works across DRL algorithms, without requiring any changes to the DRL workflow. We evaluated Plume on three networking environments, including Adaptive Bitrate Streaming, Congestion Control, and Load Balancing. Plume offers superior performance in both simulation and real-world settings, across different controllers and DRL algorithms. For example, our novel ABR controller, Gelato trained with Plume consistently outperforms prior state-of-the-art controllers on the live streaming platform Puffer for over a year. It is the first controller on the platform to deliver statistically significant improvements in both video quality and stalling, decreasing stalls by as much as 75%.
Authors: Ilze Amanda Auzina, Çağatay Yıldız, Sara Magliacane, Matthias Bethge, Efstratios Gavves
Neural ordinary differential equations (NODEs) have been proven useful for learning non-linear dynamics of arbitrary trajectories. However, current NODE methods capture variations across trajectories only via the initial state value or by auto-regressive encoder updates. In this work, we introduce Modulated Neural ODEs (MoNODEs), a novel framework that sets apart dynamics states from underlying static factors of variation and improves the existing NODE methods. In particular, we introduce $\textit{time-invariant modulator variables}$ that are learned from the data. We incorporate our proposed framework into four existing NODE variants. We test MoNODE on oscillating systems, videos and human walking trajectories, where each trajectory has trajectory-specific modulation. Our framework consistently improves the existing model ability to generalize to new dynamic parameterizations and to perform far-horizon forecasting. In addition, we verify that the proposed modulator variables are informative of the true unknown factors of variation as measured by $R^2$ scores.
Authors: Sadaf Khan, Zhengyuan Shi, Min Li, Qiang Xu
Circuit representation learning is a promising research direction in the electronic design automation (EDA) field. With sufficient data for pre-training, the learned general yet effective representation can help to solve multiple downstream EDA tasks by fine-tuning it on a small set of task-related data. However, existing solutions only target combinational circuits, significantly limiting their applications. In this work, we propose DeepSeq, a novel representation learning framework for sequential netlists. Specifically, we introduce a dedicated graph neural network (GNN) with a customized propagation scheme to exploit the temporal correlations between gates in sequential circuits. To ensure effective learning, we propose to use a multi-task training objective with two sets of strongly related supervision: logic probability and transition probability at each node. A novel dual attention aggregation mechanism is introduced to facilitate learning both tasks efficiently. Experimental results on various benchmark circuits show that DeepSeq outperforms other GNN models for sequential circuit learning. We evaluate the generalization capability of DeepSeq on a downstream power estimation task. After fine-tuning, DeepSeq can accurately estimate power across various circuits under different workloads.
Authors: Sayantan Choudhury, Eduard Gorbunov, Nicolas Loizou
Single-call stochastic extragradient methods, like stochastic past extragradient (SPEG) and stochastic optimistic gradient (SOG), have gained a lot of interest in recent years and are one of the most efficient algorithms for solving large-scale min-max optimization and variational inequalities problems (VIP) appearing in various machine learning tasks. However, despite their undoubted popularity, current convergence analyses of SPEG and SOG require a bounded variance assumption. In addition, several important questions regarding the convergence properties of these methods are still open, including mini-batching, efficient step-size selection, and convergence guarantees under different sampling strategies. In this work, we address these questions and provide convergence guarantees for two large classes of structured non-monotone VIPs: (i) quasi-strongly monotone problems (a generalization of strongly monotone problems) and (ii) weak Minty variational inequalities (a generalization of monotone and Minty VIPs). We introduce the expected residual condition, explain its benefits, and show how it can be used to obtain a strictly weaker bound than previously used growth conditions, expected co-coercivity, or bounded variance assumptions. Equipped with this condition, we provide theoretical guarantees for the convergence of single-call extragradient methods for different step-size selections, including constant, decreasing, and step-size-switching rules. Furthermore, our convergence analysis holds under the arbitrary sampling paradigm, which includes importance sampling and various mini-batching strategies as special cases.
Authors: Zohreh Aghababaeyan, Manel Abdellatif, Mahboubeh Dadkhah, Lionel Briand
Deep neural networks (DNNs) are widely used in various application domains such as image processing, speech recognition, and natural language processing. However, testing DNN models may be challenging due to the complexity and size of their input domain. Particularly, testing DNN models often requires generating or exploring large unlabeled datasets. In practice, DNN test oracles, which identify the correct outputs for inputs, often require expensive manual effort to label test data, possibly involving multiple experts to ensure labeling correctness. In this paper, we propose DeepGD, a black-box multi-objective test selection approach for DNN models. It reduces the cost of labeling by prioritizing the selection of test inputs with high fault revealing power from large unlabeled datasets. DeepGD not only selects test inputs with high uncertainty scores to trigger as many mispredicted inputs as possible but also maximizes the probability of revealing distinct faults in the DNN model by selecting diverse mispredicted inputs. The experimental results conducted on four widely used datasets and five DNN models show that in terms of fault-revealing ability: (1) White-box, coverage-based approaches fare poorly, (2) DeepGD outperforms existing black-box test selection approaches in terms of fault detection, and (3) DeepGD also leads to better guidance for DNN model retraining when using selected inputs to augment the training set.
Authors: Duc Nguyen, Anderson Y. Zhang
Item response theory (IRT) is the study of how people make probabilistic decisions, with diverse applications in education testing, recommendation systems, among others. The Rasch model of binary response data, one of the most fundamental models in IRT, remains an active area of research with important practical significance. Recently, Nguyen and Zhang (2022) proposed a new spectral estimation algorithm that is efficient and accurate. In this work, we extend their results in two important ways. Firstly, we obtain a refined entrywise error bound for the spectral algorithm, complementing the `average error' $\ell_2$ bound in their work. Notably, under mild sampling conditions, the spectral algorithm achieves the minimax optimal error bound (modulo a log factor). Building on the refined analysis, we also show that the spectral algorithm enjoys optimal sample complexity for top-$K$ recovery (e.g., identifying the best $K$ items from approval/disapproval response data), explaining the empirical findings in the previous work. Our second contribution addresses an important but understudied topic in IRT: privacy. Despite the human-centric applications of IRT, there has not been any proposed privacy-preserving mechanism in the literature. We develop a private extension of the spectral algorithm, leveraging its unique Markov chain formulation and the discrete Gaussian mechanism (Canonne et al., 2020). Experiments show that our approach is significantly more accurate than the baselines in the low-to-moderate privacy regime.
Authors: Qi Zhao, Qiqi Duan, Bai Yan, Shi Cheng, Yuhui Shi
Metaheuristics have gained great success in academia and practice because their search logic can be applied to any problem with available solution representation, solution quality evaluation, and certain notions of locality. Manually designing metaheuristic algorithms for solving a target problem is criticized for being laborious, error-prone, and requiring intensive specialized knowledge. This gives rise to increasing interest in automated design of metaheuristic algorithms. With computing power to fully explore potential design choices, the automated design could reach and even surpass human-level design and could make high-performance algorithms accessible to a much wider range of researchers and practitioners. This paper presents a broad picture of automated design of metaheuristic algorithms, by conducting a survey on the common grounds and representative techniques in terms of design space, design strategies, performance evaluation strategies, and target problems in this field.
Authors: Hong Ye Tan, Subhadip Mukherjee, Junqi Tang, Carola-Bibiane Schönlieb
Plug-and-Play (PnP) methods are a class of efficient iterative methods that aim to combine data fidelity terms and deep denoisers using classical optimization algorithms, such as ISTA or ADMM, with applications in inverse problems and imaging. Provable PnP methods are a subclass of PnP methods with convergence guarantees, such as fixed point convergence or convergence to critical points of some energy function. Many existing provable PnP methods impose heavy restrictions on the denoiser or fidelity function, such as non-expansiveness or strict convexity, respectively. In this work, we propose a novel algorithmic approach incorporating quasi-Newton steps into a provable PnP framework based on proximal denoisers, resulting in greatly accelerated convergence while retaining light assumptions on the denoiser. By characterizing the denoiser as the proximal operator of a weakly convex function, we show that the fixed points of the proposed quasi-Newton PnP algorithm are critical points of a weakly convex function. Numerical experiments on image deblurring and super-resolution demonstrate 2--8x faster convergence as compared to other provable PnP methods with similar reconstruction quality.
Authors: Zhuowei Li, Long Zhao, Zizhao Zhang, Han Zhang, Di Liu, Ting Liu, Dimitris N. Metaxas
In the context of continual learning, prototypes-as representative class embeddings-offer advantages in memory conservation and the mitigation of catastrophic forgetting. However, challenges related to semantic drift and prototype interference persist. In this study, we introduce the Contrastive Prototypical Prompt (CPP) approach. Through task-specific prompt-tuning, underpinned by a contrastive learning objective, we effectively address both aforementioned challenges. Our evaluations on four challenging class-incremental benchmarks reveal that CPP achieves a significant 4% to 6% improvement over state-of-the-art methods. Importantly, CPP operates without a rehearsal buffer and narrows the performance divergence between continual and offline joint-learning, suggesting an innovative scheme for Transformer-based continual learning systems.
Authors: Xiuding Cai, Jiao Chen, Yaoyao Zhu, Beimin Wang, Yu Yao
Automated anesthesia promises to enable more precise and personalized anesthetic administration and free anesthesiologists from repetitive tasks, allowing them to focus on the most critical aspects of a patient's surgical care. Current research has typically focused on creating simulated environments from which agents can learn. These approaches have demonstrated good experimental results, but are still far from clinical application. In this paper, Policy Constraint Q-Learning (PCQL), a data-driven reinforcement learning algorithm for solving the problem of learning anesthesia strategies on real clinical datasets, is proposed. Conservative Q-Learning was first introduced to alleviate the problem of Q function overestimation in an offline context. A policy constraint term is added to agent training to keep the policy distribution of the agent and the anesthesiologist consistent to ensure safer decisions made by the agent in anesthesia scenarios. The effectiveness of PCQL was validated by extensive experiments on a real clinical anesthesia dataset. Experimental results show that PCQL is predicted to achieve higher gains than the baseline approach while maintaining good agreement with the reference dose given by the anesthesiologist, using less total dose, and being more responsive to the patient's vital signs. In addition, the confidence intervals of the agent were investigated, which were able to cover most of the clinical decisions of the anesthesiologist. Finally, an interpretable method, SHAP, was used to analyze the contributing components of the model predictions to increase the transparency of the model.
Authors: Borui Cai, Yong Xiang, Longxiang Gao, Di Wu, He Zhang, Jiong Jin, Tom Luan
Knowledge graph embedding (KGE) that maps entities and relations into vector representations is essential for downstream applications. Conventional KGE methods require high-dimensional representations to learn the complex structure of knowledge graph, but lead to oversized model parameters. Recent advances reduce parameters by low-dimensional entity representations, while developing techniques (e.g., knowledge distillation or reinvented representation forms) to compensate for reduced dimension. However, such operations introduce complicated computations and model designs that may not benefit large knowledge graphs. To seek a simple strategy to improve the parameter efficiency of conventional KGE models, we take inspiration from that deeper neural networks require exponentially fewer parameters to achieve expressiveness comparable to wider networks for compositional structures. We view all entity representations as a single-layer embedding network, and conventional KGE methods that adopt high-dimensional entity representations equal widening the embedding network to gain expressiveness. To achieve parameter efficiency, we instead propose a deeper embedding network for entity representations, i.e., a narrow entity embedding layer plus a multi-layer dimension lifting network (LiftNet). Experiments on three public datasets show that by integrating LiftNet, four conventional KGE methods with 16-dimensional representations achieve comparable link prediction accuracy as original models that adopt 512-dimensional representations, saving 68.4% to 96.9% parameters.
Authors: Andrea Rossi, Andrea Visentin, Diego Carraro, Steven Prestwich, Kenneth N. Brown
Predicting future resource demand in Cloud Computing is essential for optimizing the trade-off between serving customers' requests efficiently and minimizing the provisioning cost. Modelling prediction uncertainty is also desirable to better inform the resource decision-making process, but research in this field is under-investigated. In this paper, we propose univariate and bivariate Bayesian deep learning models that provide predictions of future workload demand and its uncertainty. We run extensive experiments on Google and Alibaba clusters, where we first train our models with datasets from different cloud providers and compare them with LSTM-based baselines. Results show that modelling the uncertainty of predictions has a positive impact on performance, especially on service level metrics, because uncertainty quantification can be tailored to desired target service levels that are critical in cloud applications. Moreover, we investigate whether our models benefit transfer learning capabilities across different domains, i.e. dataset distributions. Experiments on the same workload datasets reveal that acceptable transfer learning performance can be achieved within the same provider (because distributions are more similar). Also, domain knowledge does not transfer when the source and target domains are very different (e.g. from different providers), but this performance degradation can be mitigated by increasing the training set size of the source domain.
Authors: Tongzhou Wang, Antonio Torralba, Phillip Isola, Amy Zhang
In goal-reaching reinforcement learning (RL), the optimal value function has a particular geometry, called quasimetric structure. This paper introduces Quasimetric Reinforcement Learning (QRL), a new RL method that utilizes quasimetric models to learn optimal value functions. Distinct from prior approaches, the QRL objective is specifically designed for quasimetrics, and provides strong theoretical recovery guarantees. Empirically, we conduct thorough analyses on a discretized MountainCar environment, identifying properties of QRL and its advantages over alternatives. On offline and online goal-reaching benchmarks, QRL also demonstrates improved sample efficiency and performance, across both state-based and image-based observations.
Authors: Adrian Celaya, Beatrice Riviere, David Fuentes
Accurate medical imaging segmentation is critical for precise and effective medical interventions. However, despite the success of convolutional neural networks (CNNs) in medical image segmentation, they still face challenges in handling fine-scale features and variations in image scales. These challenges are particularly evident in complex and challenging segmentation tasks, such as the BraTS multi-label brain tumor segmentation challenge. In this task, accurately segmenting the various tumor sub-components, which vary significantly in size and shape, remains a significant challenge, with even state-of-the-art methods producing substantial errors. Therefore, we propose two architectures, FMG-Net and W-Net, that incorporate the principles of geometric multigrid methods for solving linear systems of equations into CNNs to address these challenges. Our experiments on the BraTS 2020 dataset demonstrate that both FMG-Net and W-Net outperform the widely used U-Net architecture regarding tumor subcomponent segmentation accuracy and training efficiency. These findings highlight the potential of incorporating the principles of multigrid methods into CNNs to improve the accuracy and efficiency of medical imaging segmentation.
Authors: Bohan Li, Longxu Dou, Yutai Hou, Yunlong Feng, Honglin Mu, Qingfu Zhu, Qinghua Sun, Wanxiang Che
Prompt-based learning has shown considerable promise in reformulating various downstream tasks as cloze problems by combining original input with a predetermined template. This approach demonstrates its effectiveness, especially in few-shot learning scenarios, where the model is trained on a scarce amount of data. Despite its successes, the limited templates and text in few-shot prompt-based learning scenarios leave significant room for performance improvement. Moreover, existing methods sometimes resort to model ensembles, which, while effective, could potentially hamper model efficiency due to increased computational demands. To address these issues, we introduce MixPro, an augmentation method designed to augment both the vanilla input text and the templates. We implement this through the token-level, the sentence-level, and the template-level Mixup strategies. The experimental results on five few-shot datasets show that MixPro outperforms other augmentation baselines, improving model performance by an average of 5.08% compared to before augmentation.
Authors: Stefano Calzavara, Lorenzo Cazzaro, Giulio Ermanno Pibiri, Nicola Prezza
Verifying the robustness of machine learning models against evasion attacks at test time is an important research problem. Unfortunately, prior work established that this problem is NP-hard for decision tree ensembles, hence bound to be intractable for specific inputs. In this paper, we identify a restricted class of decision tree ensembles, called large-spread ensembles, which admit a security verification algorithm running in polynomial time. We then propose a new approach called verifiable learning, which advocates the training of such restricted model classes which are amenable for efficient verification. We show the benefits of this idea by designing a new training algorithm that automatically learns a large-spread decision tree ensemble from labelled data, thus enabling its security verification in polynomial time. Experimental results on public datasets confirm that large-spread ensembles trained using our algorithm can be verified in a matter of seconds, using standard commercial hardware. Moreover, large-spread ensembles are more robust than traditional ensembles against evasion attacks, at the cost of an acceptable loss of accuracy in the non-adversarial setting.
Authors: Mingtian Zhang, Alex Hawkins-Hooker, Brooks Paige, David Barber
Energy-Based Models (EBMs) offer a versatile framework for modeling complex data distributions. However, training and sampling from EBMs continue to pose significant challenges. The widely-used Denoising Score Matching (DSM) method for scalable EBM training suffers from inconsistency issues, causing the energy model to learn a `noisy' data distribution. In this work, we propose an efficient sampling framework: (pseudo)-Gibbs sampling with moment matching, which enables effective sampling from the underlying clean model when given a `noisy' model that has been well-trained via DSM. We explore the benefits of our approach compared to related methods and demonstrate how to scale the method to high-dimensional datasets.
Authors: Yuchen Yang, Bo Hui, Haolin Yuan, Neil Gong, Yinzhi Cao
Text-to-image generative models such as Stable Diffusion and DALL$\cdot$E raise many ethical concerns due to the generation of harmful images such as Not-Safe-for-Work (NSFW) ones. To address these ethical concerns, safety filters are often adopted to prevent the generation of NSFW images. In this work, we propose SneakyPrompt, the first automated attack framework, to jailbreak text-to-image generative models such that they generate NSFW images even if safety filters are adopted. Given a prompt that is blocked by a safety filter, SneakyPrompt repeatedly queries the text-to-image generative model and strategically perturbs tokens in the prompt based on the query results to bypass the safety filter. Specifically, SneakyPrompt utilizes reinforcement learning to guide the perturbation of tokens. Our evaluation shows that SneakyPrompt successfully jailbreaks DALL$\cdot$E 2 with closed-box safety filters to generate NSFW images. Moreover, we also deploy several state-of-the-art, open-source safety filters on a Stable Diffusion model. Our evaluation shows that SneakyPrompt not only successfully generates NSFW images, but also outperforms existing text adversarial attacks when extended to jailbreak text-to-image generative models, in terms of both the number of queries and qualities of the generated NSFW images. SneakyPrompt is open-source and available at this repository: \url{https://github.com/Yuchen413/text2image_safety}.
Authors: Yaohua Zang, Gang Bao
Deep neural networks (DNNs) have been widely used to solve partial differential equations (PDEs) in recent years. In this work, a novel deep learning-based framework named Particle Weak-form based Neural Networks (ParticleWNN) is developed for solving PDEs in the weak form. In this framework, the trial space is defined as the space of DNNs, while the test space consists of functions compactly supported in extremely small regions, centered around particles. To facilitate the training of neural networks, an R-adaptive strategy is designed to adaptively modify the radius of regions during training. The ParticleWNN inherits the benefits of weak/variational formulation, requiring less regularity of the solution and a small number of quadrature points for computing integrals. Additionally, due to the special construction of the test functions, ParticleWNN enables parallel implementation and integral calculations only in extremely small regions. This framework is particularly desirable for solving problems with high-dimensional and complex domains. The efficiency and accuracy of ParticleWNN are demonstrated through several numerical examples, showcasing its superiority over state-of-the-art methods. The source code for the numerical examples presented in this paper is available at https://github.com/yaohua32/ParticleWNN.
Authors: Matteo Biagiola, Paolo Tonella
Deep Reinforcement Learning (DRL) has received a lot of attention from the research community in recent years. As the technology moves away from game playing to practical contexts, such as autonomous vehicles and robotics, it is crucial to evaluate the quality of DRL agents. In this paper, we propose a search-based approach to test such agents. Our approach, implemented in a tool called Indago, trains a classifier on failure and non-failure environment (i.e., pass) configurations resulting from the DRL training process. The classifier is used at testing time as a surrogate model for the DRL agent execution in the environment, predicting the extent to which a given environment configuration induces a failure of the DRL agent under test. The failure prediction acts as a fitness function, guiding the generation towards failure environment configurations, while saving computation time by deferring the execution of the DRL agent in the environment to those configurations that are more likely to expose failures. Experimental results show that our search-based approach finds 50% more failures of the DRL agent than state-of-the-art techniques. Moreover, such failures are, on average, 78% more diverse; similarly, the behaviors of the DRL agent induced by failure configurations are 74% more diverse.
Authors: Shayne Longpre, Gregory Yauney, Emily Reif, Katherine Lee, Adam Roberts, Barret Zoph, Denny Zhou, Jason Wei, Kevin Robinson, David Mimno, Daphne Ippolito
Pretraining is the preliminary and fundamental step in developing capable language models (LM). Despite this, pretraining data design is critically under-documented and often guided by empirically unsupported intuitions. To address this, we pretrain 28 1.5B parameter decoder-only models, training on data curated (1) at different times, (2) with varying toxicity and quality filters, and (3) with different domain compositions. First, we quantify the effect of pretraining data age. A temporal shift between evaluation data and pretraining data leads to performance degradation, which is not overcome by finetuning. Second, we explore the effect of quality and toxicity filters, showing a trade-off between performance on standard benchmarks and risk of toxic generations. Our findings indicate there does not exist a one-size-fits-all solution to filtering training data. We also find that the effects of different types of filtering are not predictable from text domain characteristics. Lastly, we empirically validate that the inclusion of heterogeneous data sources, like books and web, is broadly beneficial and warrants greater prioritization. These findings constitute the largest set of experiments to validate, quantify, and expose many undocumented intuitions about text pretraining, which we hope will help support more informed data-centric decisions in LM development.
Authors: James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Ioannis Patras
Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks. However, their utility is limited by their entanglement with respect to different visual attributes. For instance, recent work has shown that CLIP image representations are often biased toward specific visual properties (such as objects or actions) in an unpredictable manner. In this paper, we propose to separate representations of the different visual modalities in CLIP's joint vision-language space by leveraging the association between parts of speech and specific visual modes of variation (e.g. nouns relate to objects, adjectives describe appearance). This is achieved by formulating an appropriate component analysis model that learns subspaces capturing variability corresponding to a specific part of speech, while jointly minimising variability to the rest. Such a subspace yields disentangled representations of the different visual properties of an image or text in closed form while respecting the underlying geometry of the manifold on which the representations lie. What's more, we show the proposed model additionally facilitates learning subspaces corresponding to specific visual appearances (e.g. artists' painting styles), which enables the selective removal of entire visual themes from CLIP-based text-to-image synthesis. We validate the model both qualitatively, by visualising the subspace projections with a text-to-image model and by preventing the imitation of artists' styles, and quantitatively, through class invariance metrics and improvements to baseline zero-shot classification.
Authors: Anthony Gruber, Kookjin Lee, Nathaniel Trask
Recent works have shown that physics-inspired architectures allow the training of deep graph neural networks (GNNs) without oversmoothing. The role of these physics is unclear, however, with successful examples of both reversible (e.g., Hamiltonian) and irreversible (e.g., diffusion) phenomena producing comparable results despite diametrically opposed mechanisms, and further complications arising due to empirical departures from mathematical theory. This work presents a series of novel GNN architectures based upon structure-preserving bracket-based dynamical systems, which are provably guaranteed to either conserve energy or generate positive dissipation with increasing depth. It is shown that the theoretically principled framework employed here allows for inherently explainable constructions, which contextualize departures from theory in current architectures and better elucidate the roles of reversibility and irreversibility in network performance.
Authors: Yunze Tong, Junkun Yuan, Min Zhang, Didi Zhu, Keli Zhang, Fei Wu, Kun Kuang
Domain generalization (DG) is a prevalent problem in real-world applications, which aims to train well-generalized models for unseen target domains by utilizing several source domains. Since domain labels, i.e., which domain each data point is sampled from, naturally exist, most DG algorithms treat them as a kind of supervision information to improve the generalization performance. However, the original domain labels may not be the optimal supervision signal due to the lack of domain heterogeneity, i.e., the diversity among domains. For example, a sample in one domain may be closer to another domain, its original label thus can be the noise to disturb the generalization learning. Although some methods try to solve it by re-dividing domains and applying the newly generated dividing pattern, the pattern they choose may not be the most heterogeneous due to the lack of the metric for heterogeneity. In this paper, we point out that domain heterogeneity mainly lies in variant features under the invariant learning framework. With contrastive learning, we propose a learning potential-guided metric for domain heterogeneity by promoting learning variant features. Then we notice the differences between seeking variance-based heterogeneity and training invariance-based generalizable model. We thus propose a novel method called Heterogeneity-based Two-stage Contrastive Learning (HTCL) for the DG task. In the first stage, we generate the most heterogeneous dividing pattern with our contrastive metric. In the second stage, we employ an invariance-aimed contrastive learning by re-building pairs with the stable relation hinted by domains and classes, which better utilizes generated domain labels for generalization learning. Extensive experiments show HTCL better digs heterogeneity and yields great generalization performance.
Authors: Yuchen Bai, Jean-Baptiste Durand, Florence Forbes, Grégoire Vincent
LiDAR (Light Detection and Ranging) has become an essential part of the remote sensing toolbox used for biosphere monitoring. In particular, LiDAR provides the opportunity to map forest leaf area with unprecedented accuracy, while leaf area has remained an important source of uncertainty affecting models of gas exchanges between the vegetation and the atmosphere. Unmanned Aerial Vehicles (UAV) are easy to mobilize and therefore allow frequent revisits to track the response of vegetation to climate change. However, miniature sensors embarked on UAVs usually provide point clouds of limited density, which are further affected by a strong decrease in density from top to bottom of the canopy due to progressively stronger occlusion. In such a context, discriminating leaf points from wood points presents a significant challenge due in particular to strong class imbalance and spatially irregular sampling intensity. Here we introduce a neural network model based on the Pointnet ++ architecture which makes use of point geometry only (excluding any spectral information). To cope with local data sparsity, we propose an innovative sampling scheme which strives to preserve local important geometric information. We also propose a loss function adapted to the severe class imbalance. We show that our model outperforms state-of-the-art alternatives on UAV point clouds. We discuss future possible improvements, particularly regarding much denser point clouds acquired from below the canopy.
Authors: Justin Lidard, Oswin So, Yanxia Zhang, Jonathan DeCastro, Xiongyi Cui, Xin Huang, Yen-Ling Kuo, John Leonard, Avinash Balachandran, Naomi Leonard, Guy Rosman
Interactions between road agents present a significant challenge in trajectory prediction, especially in cases involving multiple agents. Because existing diversity-aware predictors do not account for the interactive nature of multi-agent predictions, they may miss these important interaction outcomes. In this paper, we propose NashFormer, a framework for trajectory prediction that leverages game-theoretic inverse reinforcement learning to improve coverage of multi-modal predictions. We use a training-time game-theoretic analysis as an auxiliary loss resulting in improved coverage and accuracy without presuming a taxonomy of actions for the agents. We demonstrate our approach on the interactive split of the Waymo Open Motion Dataset, including four subsets involving scenarios with high interaction complexity. Experiment results show that our predictor produces accurate predictions while covering $33\%$ more potential interactions versus a baseline model.
Authors: Huizong Yang, Yuxin Sun, Ganesh Sundaramoorthi, Anthony Yezzi
We present new insights and a novel paradigm (StEik) for learning implicit neural representations (INR) of shapes. In particular, we shed light on the popular eikonal loss used for imposing a signed distance function constraint in INR. We show analytically that as the representation power of the network increases, the optimization approaches a partial differential equation (PDE) in the continuum limit that is unstable. We show that this instability can manifest in existing network optimization, leading to irregularities in the reconstructed surface and/or convergence to sub-optimal local minima, and thus fails to capture fine geometric and topological structure. We show analytically how other terms added to the loss, currently used in the literature for other purposes, can actually eliminate these instabilities. However, such terms can over-regularize the surface, preventing the representation of fine shape detail. Based on a similar PDE theory for the continuum limit, we introduce a new regularization term that still counteracts the eikonal instability but without over-regularizing. Furthermore, since stability is now guaranteed in the continuum limit, this stabilization also allows for considering new network structures that are able to represent finer shape detail. We introduce such a structure based on quadratic layers. Experiments on multiple benchmark data sets show that our new regularization and network are able to capture more precise shape details and more accurate topology than existing state-of-the-art.
Authors: Yudi Zhang, Yali Du, Biwei Huang, Ziyan Wang, Jun Wang, Meng Fang, Mykola Pechenizkiy
A major challenge in reinforcement learning is to determine which state-action pairs are responsible for future rewards that are delayed. Reward redistribution serves as a solution to re-assign credits for each time step from observed sequences. While the majority of current approaches construct the reward redistribution in an uninterpretable manner, we propose to explicitly model the contributions of state and action from a causal perspective, resulting in an interpretable reward redistribution and preserving policy invariance. In this paper, we start by studying the role of causal generative models in reward redistribution by characterizing the generation of Markovian rewards and trajectory-wise long-term return and further propose a framework, called Generative Return Decomposition (GRD), for policy optimization in delayed reward scenarios. Specifically, GRD first identifies the unobservable Markovian rewards and causal relations in the generative process. Then, GRD makes use of the identified causal generative model to form a compact representation to train policy over the most favorable subspace of the state space of the agent. Theoretically, we show that the unobservable Markovian reward function is identifiable, as well as the underlying causal structure and causal models. Experimental results show that our method outperforms state-of-the-art methods and the provided visualization further demonstrates the interpretability of our method. The project page is located at https://reedzyd.github.io/GenerativeReturnDecomposition/.
Authors: Qin Xie, Qinghua Zhang, Shuyin Xia, Fan Zhao, Chengying Wu, Guoyin Wang, Weiping Ding
Granular ball computing (GBC), as an efficient, robust, and scalable learning method, has become a popular research topic of granular computing. GBC includes two stages: granular ball generation (GBG) and multi-granularity learning based on the granular ball (GB). However, the stability and efficiency of existing GBG methods need to be further improved due to their strong dependence on $k$-means or $k$-division. In addition, GB-based classifiers only unilaterally consider the GB's geometric characteristics to construct classification rules, but the GB's quality is ignored. Therefore, in this paper, based on the attention mechanism, a fast and stable GBG (GBG++) method is proposed first. Specifically, the proposed GBG++ method only needs to calculate the distances from the data-driven center to the undivided samples when splitting each GB instead of randomly selecting the center and calculating the distances between it and all samples. Moreover, an outlier detection method is introduced to identify local outliers. Consequently, the GBG++ method can significantly improve effectiveness, robustness, and efficiency while being absolutely stable. Second, considering the influence of the sample size within the GB on the GB's quality, based on the GBG++ method, an improved GB-based $k$-nearest neighbors algorithm (GB$k$NN++) is presented, which can reduce misclassification at the class boundary. Finally, the experimental results indicate that the proposed method outperforms several existing GB-based classifiers and classical machine learning classifiers on $24$ public benchmark datasets.
Authors: Théo Gnassounou, Rémi Flamary, Alexandre Gramfort
In many machine learning applications on signals and biomedical data, especially electroencephalogram (EEG), one major challenge is the variability of the data across subjects, sessions, and hardware devices. In this work, we propose a new method called Convolutional Monge Mapping Normalization (CMMN), which consists in filtering the signals in order to adapt their power spectrum density (PSD) to a Wasserstein barycenter estimated on training data. CMMN relies on novel closed-form solutions for optimal transport mappings and barycenters and provides individual test time adaptation to new data without needing to retrain a prediction model. Numerical experiments on sleep EEG data show that CMMN leads to significant and consistent performance gains independent from the neural network architecture when adapting between subjects, sessions, and even datasets collected with different hardware. Notably our performance gain is on par with much more numerically intensive Domain Adaptation (DA) methods and can be used in conjunction with those for even better performances.
Authors: Max Schwarzer, Johan Obando-Ceron, Aaron Courville, Marc Bellemare, Rishabh Agarwal, Pablo Samuel Castro
We introduce a value-based RL agent, which we call BBF, that achieves super-human performance in the Atari 100K benchmark. BBF relies on scaling the neural networks used for value estimation, as well as a number of other design choices that enable this scaling in a sample-efficient manner. We conduct extensive analyses of these design choices and provide insights for future work. We end with a discussion about updating the goalposts for sample-efficient RL research on the ALE. We make our code and data publicly available at https://github.com/google-research/google-research/tree/master/bigger_better_faster.
Authors: Nina L. Corvelo Benz, Manuel Gomez Rodriguez
Whenever a binary classifier is used to provide decision support, it typically provides both a label prediction and a confidence value. Then, the decision maker is supposed to use the confidence value to calibrate how much to trust the prediction. In this context, it has been often argued that the confidence value should correspond to a well calibrated estimate of the probability that the predicted label matches the ground truth label. However, multiple lines of empirical evidence suggest that decision makers have difficulties at developing a good sense on when to trust a prediction using these confidence values. In this paper, our goal is first to understand why and then investigate how to construct more useful confidence values. We first argue that, for a broad class of utility functions, there exist data distributions for which a rational decision maker is, in general, unlikely to discover the optimal decision policy using the above confidence values -- an optimal decision maker would need to sometimes place more (less) trust on predictions with lower (higher) confidence values. However, we then show that, if the confidence values satisfy a natural alignment property with respect to the decision maker's confidence on her own predictions, there always exists an optimal decision policy under which the level of trust the decision maker would need to place on predictions is monotone on the confidence values, facilitating its discoverability. Further, we show that multicalibration with respect to the decision maker's confidence on her own predictions is a sufficient condition for alignment. Experiments on four different AI-assisted decision making tasks where a classifier provides decision support to real human experts validate our theoretical results and suggest that alignment may lead to better decisions.
Authors: Peng Cheng, Xianyuan Zhan, Zhihao Wu, Wenjia Zhang, Shoucheng Song, Han Wang, Youfang Lin, Li Jiang
Offline reinforcement learning (RL) offers an appealing approach to real-world tasks by learning policies from pre-collected datasets without interacting with the environment. However, the performance of existing offline RL algorithms heavily depends on the scale and state-action space coverage of datasets. Real-world data collection is often expensive and uncontrollable, leading to small and narrowly covered datasets and posing significant challenges for practical deployments of offline RL. In this paper, we provide a new insight that leveraging the fundamental symmetry of system dynamics can substantially enhance offline RL performance under small datasets. Specifically, we propose a Time-reversal symmetry (T-symmetry) enforced Dynamics Model (TDM), which establishes consistency between a pair of forward and reverse latent dynamics. TDM provides both well-behaved representations for small datasets and a new reliability measure for OOD samples based on compliance with the T-symmetry. These can be readily used to construct a new offline RL algorithm (TSRL) with less conservative policy constraints and a reliable latent space data augmentation procedure. Based on extensive experiments, we find TSRL achieves great performance on small benchmark datasets with as few as 1% of the original samples, which significantly outperforms the recent offline RL algorithms in terms of data efficiency and generalizability.Code is available at: https://github.com/pcheng2/TSRL
Authors: Sheng-Yen Chou, Pin-Yu Chen, Tsung-Yi Ho
Diffusion Models (DMs) are state-of-the-art generative models that learn a reversible corruption process from iterative noise addition and denoising. They are the backbone of many generative AI applications, such as text-to-image conditional generation. However, recent studies have shown that basic unconditional DMs (e.g., DDPM and DDIM) are vulnerable to backdoor injection, a type of output manipulation attack triggered by a maliciously embedded pattern at model input. This paper presents a unified backdoor attack framework (VillanDiffusion) to expand the current scope of backdoor analysis for DMs. Our framework covers mainstream unconditional and conditional DMs (denoising-based and score-based) and various training-free samplers for holistic evaluations. Experiments show that our unified framework facilitates the backdoor analysis of different DM configurations and provides new insights into caption-based backdoor attacks on DMs. Our code is available on GitHub: \url{https://github.com/IBM/villandiffusion}
Authors: Dan Braha
Phase transitions, characterized by abrupt shifts between macroscopic patterns of organization, are ubiquitous in complex systems. Despite considerable research in the physical and natural sciences, the empirical study of this phenomenon in societal systems is relatively underdeveloped. The goal of this study is to explore whether the dynamics of collective civil unrest can be plausibly characterized as a sequence of recurrent phase shifts, with each phase having measurable and identifiable latent characteristics. Building on previous efforts to characterize civil unrest as a self-organized critical system, we introduce a macro-level statistical model of civil unrest and evaluate its plausibility using a comprehensive dataset of civil unrest events in 170 countries from 1946 to 2017. Our findings demonstrate that the macro-level phase model effectively captures the characteristics of civil unrest data from diverse countries globally and that universal mechanisms may underlie certain aspects of the dynamics of civil unrest. We also introduce a scale to quantify a country's long-term unrest per unit of time and show that civil unrest events tend to cluster geographically, with the magnitude of civil unrest concentrated in specific regions. Our approach has the potential to identify and measure phase transitions in various collective human phenomena beyond civil unrest, contributing to a better understanding of complex social systems.
Authors: Xianbiao Qi, Jianan Wang, Lei Zhang
This article provides a comprehensive understanding of optimization in deep learning, with a primary focus on the challenges of gradient vanishing and gradient exploding, which normally lead to diminished model representational ability and training instability, respectively. We analyze these two challenges through several strategic measures, including the improvement of gradient flow and the imposition of constraints on a network's Lipschitz constant. To help understand the current optimization methodologies, we categorize them into two classes: explicit optimization and implicit optimization. Explicit optimization methods involve direct manipulation of optimizer parameters, including weight, gradient, learning rate, and weight decay. Implicit optimization methods, by contrast, focus on improving the overall landscape of a network by enhancing its modules, such as residual shortcuts, normalization methods, attention mechanisms, and activations. In this article, we provide an in-depth analysis of these two optimization classes and undertake a thorough examination of the Jacobian matrices and the Lipschitz constants of many widely used deep learning modules, highlighting existing issues as well as potential improvements. Moreover, we also conduct a series of analytical experiments to substantiate our theoretical discussions. This article does not aim to propose a new optimizer or network. Rather, our intention is to present a comprehensive understanding of optimization in deep learning. We hope that this article will assist readers in gaining a deeper insight in this field and encourages the development of more robust, efficient, and high-performing models.
Authors: Jonathan D. Chang, Kiante Brantley, Rajkumar Ramamurthy, Dipendra Misra, Wen Sun
Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning Large Language Models (LLMs) for text generation. In particular, recent LLMs such as ChatGPT and GPT-4 can engage in fluent conversations with users after finetuning with RL. Capitalizing on key properties of text generation, we seek to investigate RL algorithms beyond general purpose algorithms like Proximal Policy Optimization (PPO). In particular, we extend RL algorithms to allow them to interact with a dynamic black-box guide LLM and propose RL with guided feedback (RLGF), a suite of RL algorithms for LLM fine-tuning. We provide two ways for the guide LLM to interact with the LLM to be optimized for maximizing rewards. The guide LLM can generate text which serves as additional starting states for the RL optimization procedure. The guide LLM can also be used to complete the partial sentences generated by the LLM that is being optimized, treating the guide LLM as an expert to imitate and surpass eventually. We experiment on the IMDB positive sentiment, CommonGen, and TL;DR summarization tasks. We show that our RL algorithms achieve higher performance than supervised learning (SL) and the RL baseline PPO, demonstrating the benefit of interaction with the guide LLM. On both CommonGen and TL;DR, we not only outperform our SL baselines but also improve upon PPO across a variety of metrics beyond the one we optimized for. Our code can be found at https://github.com/Cornell-RL/tril.
Authors: Amal Feriani, Di Wu, Steve Liu, Greg Dudek
Deep learning has been extensively used in wireless communication problems, including channel estimation. Although several data-driven approaches exist, a fair and realistic comparison between them is difficult due to inconsistencies in the experimental conditions and the lack of a standardized experimental design. In addition, the performance of data-driven approaches is often compared based on empirical analysis. The lack of reproducibility and availability of standardized evaluation tools (e.g., datasets, codebases) hinder the development and progress of data-driven methods for channel estimation and wireless communication in general. In this work, we introduce an initiative to build benchmarks that unify several data-driven OFDM channel estimation approaches. Specifically, we present CeBed (a testbed for channel estimation) including different datasets covering various systems models and propagation conditions along with the implementation of ten deep and traditional baselines. This benchmark considers different practical aspects such as the robustness of the data-driven models, the number and the arrangement of pilots, and the number of receive antennas. This work offers a comprehensive and unified framework to help researchers evaluate and design data-driven channel estimation algorithms.
Authors: Jingwei Zuo, Wenbin Li, Michele Baldo, Hakim Hacid
Air quality forecasting has garnered significant attention recently, with data-driven models taking center stage due to advancements in machine learning and deep learning models. However, researchers face challenges with complex data acquisition and the lack of open-sourced datasets, hindering efficient model validation. This paper introduces PurpleAirSF, a comprehensive and easily accessible dataset collected from the PurpleAir network. With its high temporal resolution, various air quality measures, and diverse geographical coverage, this dataset serves as a useful tool for researchers aiming to develop novel forecasting models, study air pollution patterns, and investigate their impacts on health and the environment. We present a detailed account of the data collection and processing methods employed to build PurpleAirSF. Furthermore, we conduct preliminary experiments using both classic and modern spatio-temporal forecasting models, thereby establishing a benchmark for future air quality forecasting tasks.
Authors: Jiaming Yu, Zihao Guan, Xinyue Chang, Shujie Liu, Zhenshan Shi, Xiumei Liu, Changcai Yang, Riqing Chen, Lanyan Xue, Lifang Wei
Since the strong comorbid similarity in NDDs, such as attention-deficit hyperactivity disorder, can interfere with the accurate diagnosis of autism spectrum disorder (ASD), identifying unknown classes is extremely crucial and challenging from NDDs. We design a novel open set recognition framework for ASD-aided diagnosis (OpenNDD), which trains a model by combining autoencoder and adversarial reciprocal points learning to distinguish in-distribution and out-of-distribution categories as well as identify ASD accurately. Considering the strong similarities between NDDs, we present a joint scaling method by Min-Max scaling combined with Standardization (MMS) to increase the differences between classes for better distinguishing unknown NDDs. We conduct the experiments in the hybrid datasets from Autism Brain Imaging Data Exchange I (ABIDE I) and THE ADHD-200 SAMPLE (ADHD-200) with 791 samples from four sites and the results demonstrate the superiority on various metrics. Our OpenNDD achieves promising performance, where the accuracy is 77.38%, AUROC is 75.53% and the open set classification rate is as high as 59.43%.
Authors: Erik Lien Bolager, Iryna Burak, Chinmay Datar, Qing Sun, Felix Dietrich
We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks. In a supervised learning context, no iterative optimization or gradient computations of internal network parameters are needed to obtain a trained network. The sampling is based on the idea of random feature models. However, instead of a data-agnostic distribution, e.g., a normal distribution, we use both the input and the output training data to sample shallow and deep networks. We prove that sampled networks are universal approximators. For Barron functions, we show that the $L^2$-approximation error of sampled shallow networks decreases with the square root of the number of neurons. Our sampling scheme is invariant to rigid body transformations and scaling of the input data, which implies many popular pre-processing techniques are not required. In numerical experiments, we demonstrate that sampled networks achieve accuracy comparable to iteratively trained ones, but can be constructed orders of magnitude faster. Our test cases involve a classification benchmark from OpenML, sampling of neural operators to represent maps in function spaces, and transfer learning using well-known architectures.
Authors: Fangqiang Ding, Zhen Luo, Peijun Zhao, Chris Xiaoxuan Lu
Approaching the era of ubiquitous computing, human motion sensing plays a crucial role in smart systems for decision making, user interaction, and personalized services. Extensive research has been conducted on human tracking, pose estimation, gesture recognition, and activity recognition, which are predominantly based on cameras in traditional methods. However, the intrusive nature of cameras limits their use in smart home applications. To address this, mmWave radars have gained popularity due to their privacy-friendly features. In this work, we propose milliFlow, a novel deep learning method for scene flow estimation as a complementary motion information for mmWave point cloud, serving as an intermediate level of features and directly benefiting downstream human motion sensing tasks. Experimental results demonstrate the superior performance of our method with an average 3D endpoint error of 4.6cm, significantly surpassing the competing approaches. Furthermore, by incorporating scene flow information, we achieve remarkable improvements in human activity recognition, human parsing, and human body part tracking. To foster further research in this area, we will provide our codebase and dataset for open access upon acceptance.
Authors: George Papadakis, Nishadi Kirielle, Peter Christen, Themis Palpanas
Entity resolution (ER) is the process of identifying records that refer to the same entities within one or across multiple databases. Numerous techniques have been developed to tackle ER challenges over the years, with recent emphasis placed on machine and deep learning methods for the matching phase. However, the quality of the benchmark datasets typically used in the experimental evaluations of learning-based matching algorithms has not been examined in the literature. To cover this gap, we propose four different approaches to assessing the difficulty and appropriateness of 13 established datasets: two theoretical approaches, which involve new measures of linearity and existing measures of complexity, and two practical approaches: the difference between the best non-linear and linear matchers, as well as the difference between the best learning-based matcher and the perfect oracle. Our analysis demonstrates that most of the popular datasets pose rather easy classification tasks. As a result, they are not suitable for properly evaluating learning-based matching algorithms. To address this issue, we propose a new methodology for yielding benchmark datasets. We put it into practice by creating four new matching tasks, and we verify that these new benchmarks are more challenging and therefore more suitable for further advancements in the field.
Authors: Jiate Liu, Yiqin Zhu, Kaiwen Xiao, Qiang Fu, Xiao Han, Wei Yang, Deheng Ye
The goal of program synthesis, or code generation, is to generate executable code based on given descriptions. Recently, there has been an increasing number of studies employing reinforcement learning (RL) to improve the performance of large language models (LLMs) for code. However, current representative works either rely solely on offline frameworks, limiting the exploration of new sample spaces, or fall short in the utilization of unit test signals, not accounting for specific error locations within the code. To address these issues, we propose RLTF, i.e., Reinforcement Learning from Unit Test Feedback, a novel online RL framework with unit test feedback of multi-granularity for refining code LLMs. Our approach generates data in real-time during training and simultaneously utilizes fine-grained feedback signals to guide the model towards producing higher-quality code. Extensive experiments show that RLTF achieves state-of-the-art performance on the APPS and the MBPP benchmarks. Our code is available at: https://github.com/Zyq-scut/RLTF.
Authors: Jean Kaddour, Oscar Key, Piotr Nawrot, Pasquale Minervini, Matt J. Kusner
The computation necessary for training Transformer-based language models has skyrocketed in recent years. This trend has motivated research on efficient training algorithms designed to improve training, validation, and downstream performance faster than standard training. In this work, we revisit three categories of such algorithms: dynamic architectures (layer stacking, layer dropping), batch selection (selective backprop, RHO loss), and efficient optimizers (Lion, Sophia). When pre-training BERT and T5 with a fixed computation budget using such methods, we find that their training, validation, and downstream gains vanish compared to a baseline with a fully-decayed learning rate. We define an evaluation protocol that enables computation to be done on arbitrary machines by mapping all computation time to a reference machine which we call reference system time. We discuss the limitations of our proposed protocol and release our code to encourage rigorous research in efficient training procedures: https://github.com/JeanKaddour/NoTrainNoGain.
Authors: Yuzhou Gu, Zhao Song, Lichen Zhang
Quadratic programming is a ubiquitous prototype in convex programming. Many combinatorial optimizations on graphs and machine learning problems can be formulated as quadratic programming; for example, Support Vector Machines (SVMs). Linear and kernel SVMs have been among the most popular models in machine learning over the past three decades, prior to the deep learning era.
Generally, a quadratic program has an input size of $\Theta(n^2)$, where $n$ is the number of variables. Assuming the Strong Exponential Time Hypothesis ($\textsf{SETH}$), it is known that no $O(n^{2-o(1)})$ algorithm exists (Backurs, Indyk, and Schmidt, NIPS'17). However, problems such as SVMs usually feature much smaller input sizes: one is given $n$ data points, each of dimension $d$, with $d \ll n$. Furthermore, SVMs are variants with only $O(1)$ linear constraints. This suggests that faster algorithms are feasible, provided the program exhibits certain underlying structures.
In this work, we design the first nearly-linear time algorithm for solving quadratic programs whenever the quadratic objective has small treewidth or admits a low-rank factorization, and the number of linear constraints is small. Consequently, we obtain a variety of results for SVMs:
* For linear SVM, where the quadratic constraint matrix has treewidth $\tau$, we can solve the corresponding program in time $\widetilde O(n\tau^{(\omega+1)/2}\log(1/\epsilon))$;
* For linear SVM, where the quadratic constraint matrix admits a low-rank factorization of rank-$k$, we can solve the corresponding program in time $\widetilde O(nk^{(\omega+1)/2}\log(1/\epsilon))$;
* For Gaussian kernel SVM, where the data dimension $d = \Theta(\log n)$ and the squared dataset radius is small, we can solve it in time $O(n^{1+o(1)}\log(1/\epsilon))$. We also prove that when the squared dataset radius is large, then $\Omega(n^{2-o(1)})$ time is required.
Authors: Zhanpeng Zhou, Yongyi Yang, Xiaojiang Yang, Junchi Yan, Wei Hu
Recent work has revealed many intriguing empirical phenomena in neural network training, despite the poorly understood and highly complex loss landscapes and training dynamics. One of these phenomena, Linear Mode Connectivity (LMC), has gained considerable attention due to the intriguing observation that different solutions can be connected by a linear path in the parameter space while maintaining near-constant training and test losses. In this work, we introduce a stronger notion of linear connectivity, Layerwise Linear Feature Connectivity (LLFC), which says that the feature maps of every layer in different trained networks are also linearly connected. We provide comprehensive empirical evidence for LLFC across a wide range of settings, demonstrating that whenever two trained networks satisfy LMC (via either spawning or permutation methods), they also satisfy LLFC in nearly all the layers. Furthermore, we delve deeper into the underlying factors contributing to LLFC, which reveal new insights into the spawning and permutation approaches. The study of LLFC transcends and advances our understanding of LMC by adopting a feature-learning perspective.
Authors: Chia-Hsiang Kao, Yu-Chiang Frank Wang
Federated Learning (FL) offers a collaborative training framework, allowing multiple clients to contribute to a shared model without compromising data privacy. Due to the heterogeneous nature of local datasets, updated client models may overfit and diverge from one another, commonly known as the problem of client drift. In this paper, we propose FedBug (Federated Learning with Bottom-Up Gradual Unfreezing), a novel FL framework designed to effectively mitigate client drift. FedBug adaptively leverages the client model parameters, distributed by the server at each global round, as the reference points for cross-client alignment. Specifically, on the client side, FedBug begins by freezing the entire model, then gradually unfreezes the layers, from the input layer to the output layer. This bottom-up approach allows models to train the newly thawed layers to project data into a latent space, wherein the separating hyperplanes remain consistent across all clients. We theoretically analyze FedBug in a novel over-parameterization FL setup, revealing its superior convergence rate compared to FedAvg. Through comprehensive experiments, spanning various datasets, training conditions, and network architectures, we validate the efficacy of FedBug. Our contributions encompass a novel FL framework, theoretical analysis, and empirical validation, demonstrating the wide potential and applicability of FedBug.
Authors: Zahra Gharaee, ZeMing Gong, Nicholas Pellegrino, Iuliia Zarubiieva, Joakim Bruslund Haurum, Scott C. Lowe, Jaclyn T.A. McKeown, Chris C.Y. Ho, Joschka McLeod, Yi-Yun C Wei, Jireh Agda, Sujeevan Ratnasingham, Dirk Steinke, Angel X. Chang, Graham W. Taylor, Paul Fieguth
In an effort to catalog insect biodiversity, we propose a new large dataset of hand-labelled insect images, the BIOSCAN-Insect Dataset. Each record is taxonomically classified by an expert, and also has associated genetic information including raw nucleotide barcode sequences and assigned barcode index numbers, which are genetically-based proxies for species classification. This paper presents a curated million-image dataset, primarily to train computer-vision models capable of providing image-based taxonomic assessment, however, the dataset also presents compelling characteristics, the study of which would be of interest to the broader machine learning community. Driven by the biological nature inherent to the dataset, a characteristic long-tailed class-imbalance distribution is exhibited. Furthermore, taxonomic labelling is a hierarchical classification scheme, presenting a highly fine-grained classification problem at lower levels. Beyond spurring interest in biodiversity research within the machine learning community, progress on creating an image-based taxonomic classifier will also further the ultimate goal of all BIOSCAN research: to lay the foundation for a comprehensive survey of global biodiversity. This paper introduces the dataset and explores the classification task through the implementation and analysis of a baseline classifier.
Authors: Shiwei Ding, Lan Zhang, Miao Pan, Xiaoyong Yuan
Collaborative inference has been a promising solution to enable resource-constrained edge devices to perform inference using state-of-the-art deep neural networks (DNNs). In collaborative inference, the edge device first feeds the input to a partial DNN locally and then uploads the intermediate result to the cloud to complete the inference. However, recent research indicates model inversion attacks (MIAs) can reconstruct input data from intermediate results, posing serious privacy concerns for collaborative inference. Existing perturbation and cryptography techniques are inefficient and unreliable in defending against MIAs while performing accurate inference. This paper provides a viable solution, named PATROL, which develops privacy-oriented pruning to balance privacy, efficiency, and utility of collaborative inference. PATROL takes advantage of the fact that later layers in a DNN can extract more task-specific features. Given limited local resources for collaborative inference, PATROL intends to deploy more layers at the edge based on pruning techniques to enforce task-specific features for inference and reduce task-irrelevant but sensitive features for privacy preservation. To achieve privacy-oriented pruning, PATROL introduces two key components: Lipschitz regularization and adversarial reconstruction training, which increase the reconstruction errors by reducing the stability of MIAs and enhance the target inference model by adversarial training, respectively. On a real-world collaborative inference task, vehicle re-identification, we demonstrate the superior performance of PATROL in terms of against MIAs.
Authors: Rui Zhang, Yixin Su, Bayu Distiawan Trisedya, Xiaoyan Zhao, Min Yang, Hong Cheng, Jianzhong Qi
The task of entity alignment between knowledge graphs (KGs) aims to identify every pair of entities from two different KGs that represent the same entity. Many machine learning-based methods have been proposed for this task. However, to our best knowledge, existing methods all require manually crafted seed alignments, which are expensive to obtain. In this paper, we propose the first fully automatic alignment method named AutoAlign, which does not require any manually crafted seed alignments. Specifically, for predicate embeddings, AutoAlign constructs a predicate-proximity-graph with the help of large language models to automatically capture the similarity between predicates across two KGs. For entity embeddings, AutoAlign first computes the entity embeddings of each KG independently using TransE, and then shifts the two KGs' entity embeddings into the same vector space by computing the similarity between entities based on their attributes. Thus, both predicate alignment and entity alignment can be done without manually crafted seed alignments. AutoAlign is not only fully automatic, but also highly effective. Experiments using real-world KGs show that AutoAlign improves the performance of entity alignment significantly compared to state-of-the-art methods.
Authors: Zheyuan Hu, Khemraj Shukla, George Em Karniadakis, Kenji Kawaguchi
The curse-of-dimensionality taxes computational resources heavily with exponentially increasing computational cost as the dimension increases. This poses great challenges in solving high-dimensional PDEs, as Richard E. Bellman first pointed out over 60 years ago. While there has been some recent success in solving numerically partial differential equations (PDEs) in high dimensions, such computations are prohibitively expensive, and true scaling of general nonlinear PDEs to high dimensions has never been achieved. We develop a new method of scaling up physics-informed neural networks (PINNs) to solve arbitrary high-dimensional PDEs. The new method, called Stochastic Dimension Gradient Descent (SDGD), decomposes a gradient of PDEs into pieces corresponding to different dimensions and randomly samples a subset of these dimensional pieces in each iteration of training PINNs. We prove theoretically the convergence and other desired properties of the proposed method. We demonstrate in various diverse tests that the proposed method can solve many notoriously hard high-dimensional PDEs, including the Hamilton-Jacobi-Bellman (HJB) and the Schr\"{o}dinger equations in tens of thousands of dimensions very fast on a single GPU using the PINNs mesh-free approach. Notably, we solve nonlinear PDEs with nontrivial, anisotropic, and inseparable solutions in 100,000 effective dimensions in 12 hours on a single GPU using SDGD with PINNs. Since SDGD is a general training methodology of PINNs, it can be applied to any current and future variants of PINNs to scale them up for arbitrary high-dimensional PDEs.
Authors: Parnian Kassraie, Nicolas Emmenegger, Andreas Krause, Aldo Pacchiano
Model selection in the context of bandit optimization is a challenging problem, as it requires balancing exploration and exploitation not only for action selection, but also for model selection. One natural approach is to rely on online learning algorithms that treat different models as experts. Existing methods, however, scale poorly ($\text{poly}M$) with the number of models $M$ in terms of their regret. Our key insight is that, for model selection in linear bandits, we can emulate full-information feedback to the online learner with a favorable bias-variance trade-off. This allows us to develop ALEXP, which has an exponentially improved ($\log M$) dependence on $M$ for its regret. ALEXP has anytime guarantees on its regret, and neither requires knowledge of the horizon $n$, nor relies on an initial purely exploratory stage. Our approach utilizes a novel time-uniform analysis of the Lasso, establishing a new connection between online learning and high-dimensional statistics.
Authors: Patrick Vossler, Sina Aghaei, Nathan Justin, Nathanael Jo, Andrés Gómez, Phebe Vayanos
ODTLearn is an open-source Python package that provides methods for learning optimal decision trees for high-stakes predictive and prescriptive tasks based on the mixed-integer optimization (MIO) framework proposed in Aghaei et al. (2019) and several of its extensions. The current version of the package provides implementations for learning optimal classification trees, optimal fair classification trees, optimal classification trees robust to distribution shifts, and optimal prescriptive trees from observational data. We have designed the package to be easy to maintain and extend as new optimal decision tree problem classes, reformulation strategies, and solution algorithms are introduced. To this end, the package follows object-oriented design principles and supports both commercial (Gurobi) and open source (COIN-OR branch and cut) solvers. The package documentation and an extensive user guide can be found at https://d3m-research-group.github.io/odtlearn/. Additionally, users can view the package source code and submit feature requests and bug reports by visiting https://github.com/D3M-Research-Group/odtlearn.
Authors: Vladimir Dvorkin, Ferdinando Fioretto
While deep learning gradually penetrates operational planning, its inherent prediction errors may significantly affect electricity prices. This letter examines how prediction errors propagate into electricity prices, revealing notable pricing errors and their spatial disparity in congested power systems. To improve fairness, we propose to embed electricity market-clearing optimization as a deep learning layer. Differentiating through this layer allows for balancing between prediction and pricing errors, as oppose to minimizing prediction errors alone. This layer implicitly optimizes fairness and controls the spatial distribution of price errors across the system. We showcase the price-aware deep learning in the nexus of wind power forecasting and short-term electricity market clearing.
Authors: Yao Lu, Shang Liu, Qijun Zhang, Zhiyao Xie
Inspired by the recent success of large language models (LLMs) like ChatGPT, researchers start to explore the adoption of LLMs for agile hardware design, such as generating design RTL based on natural-language instructions. However, in existing works, their target designs are all relatively simple and in a small scale, and proposed by the authors themselves, making a fair comparison among different LLM solutions challenging. In addition, many prior works only focus on the design correctness, without evaluating the design qualities of generated design RTL. In this work, we propose an open-source benchmark named RTLLM, for generating design RTL with natural language instructions. To systematically evaluate the auto-generated design RTL, we summarized three progressive goals, named syntax goal, functionality goal, and design quality goal. This benchmark can automatically provide a quantitative evaluation of any given LLM-based solution. Furthermore, we propose an easy-to-use yet surprisingly effective prompt engineering technique named self-planning, which proves to significantly boost the performance of GPT-3.5 in our proposed benchmark.
Authors: Terufumi Morishita, Gaku Morio, Atsuki Yamaguchi, Yasuhiro Sogawa
We study a synthetic corpus based approach for language models (LMs) to acquire logical deductive reasoning ability. The previous studies generated deduction examples using specific sets of deduction rules. However, these rules were limited or otherwise arbitrary, limiting the generalizability of acquired reasoning ability. We rethink this and adopt a well-grounded set of deduction rules based on formal logic theory, which can derive any other deduction rules when combined in a multistep way. Then, using the proposed corpora, which we name FLD (Formal Logic Deduction), we first evaluate and analyze the logical reasoning ability of the latest LLMs. Even GPT-4 can solve only half of the problems, suggesting that pure logical reasoning isolated from knowledge is still challenging for the LLMs, and additional training specialized in logical reasoning is indeed essential. We next empirically verify that LMs trained on FLD corpora acquire more generalizable reasoning ability. Furthermore, we identify the aspects of reasoning ability on which deduction corpora can enhance LMs and those on which they cannot, and discuss future directions on each aspect. The released corpora serve both as learning resources and as challenging benchmarks.
Authors: Alexander Matt Turner, Lisa Thiergart, David Udell, Gavin Leech, Ulisse Mini, Monte MacDiarmid
Reliably controlling the behavior of large language models is a pressing open problem. Existing methods include supervised finetuning, reinforcement learning from human feedback, prompt engineering and guided decoding. We instead investigate activation engineering: modifying activations at inference-time to predictably alter model behavior. We bias the forward pass with a 'steering vector' implicitly specified through natural language. Past work learned these steering vectors; our Activation Addition (ActAdd) method instead computes them by taking the activation differences which result from pairs of prompts.
We demonstrate ActAdd on GPT-2 on OpenWebText and ConceptNet, and replicate the effect on Llama-13B and GPT-J-6B. Our approach yields inference-time control over high-level properties of output & preserves performance on off-target topics. The method requires far less compute and implementation effort than finetuning and RLHF, allows for natural language specification by users, and its overhead scales naturally with model size.
Authors: Vishnu Pandi Chellapandi, Liangqi Yuan, Christopher G. Brinton, Stanislaw H Zak, Ziran Wang
Machine learning (ML) is widely used for key tasks in Connected and Automated Vehicles (CAV), including perception, planning, and control. However, its reliance on vehicular data for model training presents significant challenges related to in-vehicle user privacy and communication overhead generated by massive data volumes. Federated learning (FL) is a decentralized ML approach that enables multiple vehicles to collaboratively develop models, broadening learning from various driving environments, enhancing overall performance, and simultaneously securing local vehicle data privacy and security. This survey paper presents a review of the advancements made in the application of FL for CAV (FL4CAV). First, centralized and decentralized frameworks of FL are analyzed, highlighting their key characteristics and methodologies. Second, diverse data sources, models, and data security techniques relevant to FL in CAVs are reviewed, emphasizing their significance in ensuring privacy and confidentiality. Third, specific applications of FL are explored, providing insight into the base models and datasets employed for each application. Finally, existing challenges for FL4CAV are listed and potential directions for future investigation to further enhance the effectiveness and efficiency of FL in the context of CAV are discussed.
Authors: Ali Cem, Ognjen Jovanovic, Siqi Yan, Yunhong Ding, Darko Zibar, Francesco Da Ros
We present and experimentally evaluate using transfer learning to address experimental data scarcity when training neural network (NN) models for Mach-Zehnder interferometer mesh-based optical matrix multipliers. Our approach involves pre-training the model using synthetic data generated from a less accurate analytical model and fine-tuning with experimental data. Our investigation demonstrates that this method yields significant reductions in modeling errors compared to using an analytical model, or a standalone NN model when training data is limited. Utilizing regularization techniques and ensemble averaging, we achieve < 1 dB root-mean-square error on the matrix weights implemented by a 3x3 photonic chip while using only 25% of the available data.
Authors: Ziwei Zhang, Haoyang Li, Zeyang Zhang, Yijian Qin, Xin Wang, Wenwu Zhu
Large models have emerged as the most recent groundbreaking achievements in artificial intelligence, and particularly machine learning. However, when it comes to graphs, large models have not achieved the same level of success as in other fields, such as natural language processing and computer vision. In order to promote applying large models for graphs forward, we present a perspective paper to discuss the challenges and opportunities associated with developing large graph models. First, we discuss the desired characteristics of large graph models. Then, we present detailed discussions from three key perspectives: representation basis, graph data, and graph models. In each category, we provide a brief overview of recent advances and highlight the remaining challenges together with our visions. Finally, we discuss valuable applications of large graph models. We believe this perspective can encourage further investigations into large graph models, ultimately pushing us one step closer towards artificial general intelligence (AGI). We are the first to comprehensively study large graph models, to the best of our knowledge.
Authors: Aliasghar Khani, Saeid Asgari Taghanaki, Aditya Sanghi, Ali Mahdavi Amiri, Ghassan Hamarneh
Significant strides have been made using large vision-language models, like Stable Diffusion (SD), for a variety of downstream tasks, including image editing, image correspondence, and 3D shape generation. Inspired by these advancements, we explore leveraging these extensive vision-language models for segmenting images at any desired granularity using as few as one annotated sample by proposing SLiMe. SLiMe frames this problem as an optimization task. Specifically, given a single training image and its segmentation mask, we first extract attention maps, including our novel "weighted accumulated self-attention map" from the SD prior. Then, using the extracted attention maps, the text embeddings of Stable Diffusion are optimized such that, each of them, learn about a single segmented region from the training image. These learned embeddings then highlight the segmented region in the attention maps, which in turn can then be used to derive the segmentation map. This enables SLiMe to segment any real-world image during inference with the granularity of the segmented region in the training image, using just one example. Moreover, leveraging additional training data when available, i.e. few-shot, improves the performance of SLiMe. We carried out a knowledge-rich set of experiments examining various design factors and showed that SLiMe outperforms other existing one-shot and few-shot segmentation methods.
Authors: Tyler LaBonte, Vidya Muthukumar, Abhishek Kumar
Empirical risk minimization (ERM) of neural networks is prone to over-reliance on spurious correlations and poor generalization on minority groups. The recent deep feature reweighting (DFR) technique achieves state-of-the-art group robustness via simple last-layer retraining, but it requires held-out group and class annotations to construct a group-balanced reweighting dataset. In this work, we examine this impractical requirement and find that last-layer retraining can be surprisingly effective with no group annotations (other than for model selection) and only a handful of class annotations. We first show that last-layer retraining can greatly improve worst-group accuracy even when the reweighting dataset has only a small proportion of worst-group data. This implies a "free lunch" where holding out a subset of training data to retrain the last layer can substantially outperform ERM on the entire dataset with no additional data or annotations. To further improve group robustness, we introduce a lightweight method called selective last-layer finetuning (SELF), which constructs the reweighting dataset using misclassifications or disagreements. Our empirical and theoretical results present the first evidence that model disagreement upsamples worst-group data, enabling SELF to nearly match DFR on four well-established benchmarks across vision and language tasks with no group annotations and less than 3% of the held-out class annotations. Our code is available at https://github.com/tmlabonte/last-layer-retraining.
Authors: Yuyang Deng, Ilja Kuzborskij, Mehrdad Mahdavi
We consider the problem of learning a model from multiple heterogeneous sources with the goal of performing well on a new target distribution. The goal of learner is to mix these data sources in a target-distribution aware way and simultaneously minimize the empirical risk on the mixed source. The literature has made some tangible advancements in establishing theory of learning on mixture domain. However, there are still two unsolved problems. Firstly, how to estimate the optimal mixture of sources, given a target domain; Secondly, when there are numerous target domains, how to solve empirical risk minimization (ERM) for each target using possibly unique mixture of data sources in a computationally efficient manner. In this paper we address both problems efficiently and with guarantees. We cast the first problem, mixture weight estimation, as a convex-nonconcave compositional minimax problem, and propose an efficient stochastic algorithm with provable stationarity guarantees. Next, for the second problem, we identify that for certain regimes, solving ERM for each target domain individually can be avoided, and instead parameters for a target optimal model can be viewed as a non-linear function on a space of the mixture coefficients. Building upon this, we show that in the offline setting, a GD-trained overparameterized neural network can provably learn such function to predict the model of target domain instead of solving a designated ERM problem. Finally, we also consider an online setting and propose a label efficient online algorithm, which predicts parameters for new targets given an arbitrary sequence of mixing coefficients, while enjoying regret guarantees.
Authors: Wei Liao, Joel Voldman
Recent work in machine learning for healthcare has raised concerns about patient privacy and algorithmic fairness. For example, previous work has shown that patient self-reported race can be predicted from medical data that does not explicitly contain racial information. However, the extent of data identification is unknown, and we lack ways to develop models whose outcomes are minimally affected by such information. Here we systematically investigated the ability of time-series electronic health record data to predict patient static information. We found that not only the raw time-series data, but also learned representations from machine learning models, can be trained to predict a variety of static information with area under the receiver operating characteristic curve as high as 0.851 for biological sex, 0.869 for binarized age and 0.810 for self-reported race. Such high predictive performance can be extended to a wide range of comorbidity factors and exists even when the model was trained for different tasks, using different cohorts, using different model architectures and databases. Given the privacy and fairness concerns these findings pose, we develop a variational autoencoder-based approach that learns a structured latent space to disentangle patient-sensitive attributes from time-series data. Our work thoroughly investigates the ability of machine learning models to encode patient static information from time-series electronic health records and introduces a general approach to protect patient-sensitive attribute information for downstream tasks.
Authors: Manuel Schürch, Xiang Li, Ahmed Allam, Giulia Rathmes, Amina Mollaysa, Claudia Cavelti-Weder, Michael Krauthammer
We propose a novel framework that combines deep generative time series models with decision theory for generating personalized treatment strategies. It leverages historical patient trajectory data to jointly learn the generation of realistic personalized treatment and future outcome trajectories through deep generative time series models. In particular, our framework enables the generation of novel multivariate treatment strategies tailored to the personalized patient history and trained for optimal expected future outcomes based on conditional expected utility maximization. We demonstrate our framework by generating personalized insulin treatment strategies and blood glucose predictions for hospitalized diabetes patients, showcasing the potential of our approach for generating improved personalized treatment strategies. Keywords: deep generative model, probabilistic decision support, personalized treatment generation, insulin and blood glucose prediction
Authors: Gaurav Shinde, Rohan Mohapatra, Pooja Krishan, Saptarshi Sengupta
The usage of Lithium-ion (Li-ion) batteries has gained widespread popularity across various industries, from powering portable electronic devices to propelling electric vehicles and supporting energy storage systems. A central challenge in Li-ion battery reliability lies in accurately predicting their Remaining Useful Life (RUL), which is a critical measure for proactive maintenance and predictive analytics. This study presents a novel approach that harnesses the power of multiple denoising modules, each trained to address specific types of noise commonly encountered in battery data. Specifically, a denoising auto-encoder and a wavelet denoiser are used to generate encoded/decomposed representations, which are subsequently processed through dedicated self-attention transformer encoders. After extensive experimentation on NASA and CALCE data, a broad spectrum of health indicator values are estimated under a set of diverse noise patterns. The reported error metrics on these data are on par with or better than the state-of-the-art reported in recent literature.
Authors: Ivan Tang, Ray Zhang, Zoey Guo
The popularity of pre-trained large models has revolutionized downstream tasks across diverse fields, such as language, vision, and multi-modality. To minimize the adaption cost for downstream tasks, many Parameter-Efficient Fine-Tuning (PEFT) techniques are proposed for language and 2D image pre-trained models. However, the specialized PEFT method for 3D pre-trained models is still under-explored. To this end, we introduce Point-PEFT, a novel framework for adapting point cloud pre-trained models with minimal learnable parameters. Specifically, for a pre-trained 3D model, we freeze most of its parameters, and only tune the newly added PEFT modules on downstream tasks, which consist of a Point-prior Prompt and a Geometry-aware Adapter. The Point-prior Prompt adopts a set of learnable prompt tokens, for which we propose to construct a memory bank with domain-specific knowledge, and utilize a parameter-free attention to enhance the prompt tokens. The Geometry-aware Adapter aims to aggregate point cloud features within spatial neighborhoods to capture fine-grained geometric information through local interactions. Extensive experiments indicate that our Point-PEFT can achieve better performance than the full fine-tuning on various downstream tasks, while using only 5% of the trainable parameters, demonstrating the efficiency and effectiveness of our approach. Code will be released at https://github.com/Even-JK/PEFT-3D.
Authors: Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda
We identify hidden layers inside a deep neural network (DNN) with group actions on the data domain, and formulate a formal deep network as a dual voice transform with respect to the Koopman operator, a linear representation of the group action. Based on the group theoretic arguments, particularly by using Schur's lemma, we show a simple proof of the universality of DNNs.
Authors: Sho Sonoda, Hideyuki Ishi, Isao Ishikawa, Masahiro Ikeda
The symmetry and geometry of input data are considered to be encoded in the internal data representation inside the neural network, but the specific encoding rule has been less investigated. In this study, we present a systematic method to induce a generalized neural network and its right inverse operator, called the ridgelet transform, from a joint group invariant function on the data-parameter domain. Since the ridgelet transform is an inverse, (1) it can describe the arrangement of parameters for the network to represent a target function, which is understood as the encoding rule, and (2) it implies the universality of the network. Based on the group representation theory, we present a new simple proof of the universality by using Schur's lemma in a unified manner covering a wide class of networks, for example, the original ridgelet transform, formal deep networks, and the dual voice transform. Since traditional universality theorems were demonstrated based on functional analysis, this study sheds light on the group theoretic aspect of the approximation theory, connecting geometric deep learning to abstract harmonic analysis.
Authors: Giacomo Aldegheri, Alina Rogalska, Ahmed Youssef, Eugenia Iofinova
In this work, we propose a method to 'hack' generative models, pushing their outputs away from the original training distribution towards a new objective. We inject a small-scale trainable module between the intermediate layers of the model and train it for a low number of iterations, keeping the rest of the network frozen. The resulting output images display an uncanny quality, given by the tension between the original and new objectives that can be exploited for artistic purposes.
Authors: Qingyue Zhao, Banghua Zhu
We characterize the statistical efficiency of knowledge transfer through $n$ samples from a teacher to a probabilistic student classifier with input space $\mathcal S$ over labels $\mathcal A$. We show that privileged information at three progressive levels accelerates the transfer. At the first level, only samples with hard labels are known, via which the maximum likelihood estimator attains the minimax rate $\sqrt{{|{\mathcal S}||{\mathcal A}|}/{n}}$. The second level has the teacher probabilities of sampled labels available in addition, which turns out to boost the convergence rate lower bound to ${{|{\mathcal S}||{\mathcal A}|}/{n}}$. However, under this second data acquisition protocol, minimizing a naive adaptation of the cross-entropy loss results in an asymptotically biased student. We overcome this limitation and achieve the fundamental limit by using a novel empirical variant of the squared error logit loss. The third level further equips the student with the soft labels (complete logits) on ${\mathcal A}$ given every sampled input, thereby provably enables the student to enjoy a rate ${|{\mathcal S}|}/{n}$ free of $|{\mathcal A}|$. We find any Kullback-Leibler divergence minimizer to be optimal in the last case. Numerical simulations distinguish the four learners and corroborate our theory.
Authors: Heasung Kim, Sravan Kumar Ankireddy
In this work, we consider the problem of network parameter optimization for rate maximization. We frame this as a joint optimization problem of power control, beam forming, and interference cancellation. We consider the setting where multiple Base Stations (BSs) communicate with multiple user equipment (UEs). Because of the exponential computational complexity of brute force search, we instead solve this nonconvex optimization problem using deep reinforcement learning (RL) techniques. Modern communication systems are notorious for their difficulty in exactly modeling their behavior. This limits us in using RL-based algorithms as interaction with the environment is needed for the agent to explore and learn efficiently. Further, it is ill-advised to deploy the algorithm in the real world for exploration and learning because of the high cost of failure. In contrast to the previous RL-based solutions proposed, such as deep-Q network (DQN) based control, we suggest an offline model-based approach. We specifically consider discrete batch-constrained deep Q-learning (BCQ) and show that performance similar to DQN can be achieved with only a fraction of the data without exploring. This maximizes sample efficiency and minimizes risk in deploying a new algorithm to commercial networks. We provide the entire project resource, including code and data, at the following link: https://github.com/Heasung-Kim/ safe-rl-deployment-for-5g.
Authors: Alex Mei, Sharon Levy, William Yang Wang
As large language models are integrated into society, robustness toward a suite of prompts is increasingly important to maintain reliability in a high-variance environment.Robustness evaluations must comprehensively encapsulate the various settings in which a user may invoke an intelligent system. This paper proposes ASSERT, Automated Safety Scenario Red Teaming, consisting of three methods -- semantically aligned augmentation, target bootstrapping, and adversarial knowledge injection. For robust safety evaluation, we apply these methods in the critical domain of AI safety to algorithmically generate a test suite of prompts covering diverse robustness settings -- semantic equivalence, related scenarios, and adversarial. We partition our prompts into four safety domains for a fine-grained analysis of how the domain affects model performance. Despite dedicated safeguards in existing state-of-the-art models, we find statistically significant performance differences of up to 11% in absolute classification accuracy among semantically related scenarios and error rates of up to 19% absolute error in zero-shot adversarial settings, raising concerns for users' physical safety.
Authors: Seungju Han, Junhyeok Kim, Jack Hessel, Liwei Jiang, Jiwan Chung, Yejin Son, Yejin Choi, Youngjae Yu
Commonsense norms are defeasible by context: reading books is usually great, but not when driving a car. While contexts can be explicitly described in language, in embodied scenarios, contexts are often provided visually. This type of visually grounded reasoning about defeasible commonsense norms is generally easy for humans, but (as we show) poses a challenge for machines, as it necessitates both visual understanding and reasoning about commonsense norms. We construct a new multimodal benchmark for studying visual-grounded commonsense norms: NORMLENS. NORMLENS consists of 10K human judgments accompanied by free-form explanations covering 2K multimodal situations, and serves as a probe to address two questions: (1) to what extent can models align with average human judgment? and (2) how well can models explain their predicted judgments? We find that state-of-the-art model judgments and explanations are not well-aligned with human annotation. Additionally, we present a new approach to better align models with humans by distilling social commonsense knowledge from large language models. The data and code are released at https://seungjuhan.me/normlens.
Authors: Kamal Taha
This survey paper offers a comprehensive review of methodologies utilizing machine learning (ML) classification techniques for identifying wafer defects in semiconductor manufacturing. Despite the growing body of research demonstrating the effectiveness of ML in wafer defect identification, there is a noticeable absence of comprehensive reviews on this subject. This survey attempts to fill this void by amalgamating available literature and providing an in-depth analysis of the advantages, limitations, and potential applications of various ML classification algorithms in the realm of wafer defect detection. An innovative taxonomy of methodologies that we present provides a detailed classification of algorithms into more refined categories and techniques. This taxonomy follows a four-tier structure, starting from broad methodology categories and ending with specific sub-techniques. It aids researchers in comprehending the complex relationships between different algorithms and their techniques. We employ a rigorous empirical and experimental evaluation to rank these varying techniques. For the empirical evaluation, we assess techniques based on a set of four criteria. The experimental evaluation ranks the algorithms employing the same sub-techniques, techniques, sub-categories, and categories. This integration of a multi-layered taxonomy, empirical evaluations, and comparative experiments provides a detailed and holistic understanding of ML techniques and algorithms for identifying wafer defects. Additionally, the paper illuminates the future prospects of ML classification techniques for wafer defect identification, underscoring potential advancements and opportunities for further research in this field
Authors: Junjun Pan, Yixin Liu, Yizhen Zheng, Shirui Pan
Node-level graph anomaly detection (GAD) plays a critical role in identifying anomalous nodes from graph-structured data in various domains such as medicine, social networks, and e-commerce. However, challenges have arisen due to the diversity of anomalies and the dearth of labeled data. Existing methodologies - reconstruction-based and contrastive learning - while effective, often suffer from efficiency issues, stemming from their complex objectives and elaborate modules. To improve the efficiency of GAD, we introduce a simple method termed PREprocessing and Matching (PREM for short). Our approach streamlines GAD, reducing time and memory consumption while maintaining powerful anomaly detection capabilities. Comprising two modules - a pre-processing module and an ego-neighbor matching module - PREM eliminates the necessity for message-passing propagation during training, and employs a simple contrastive loss, leading to considerable reductions in training time and memory usage. Moreover, through rigorous evaluations of five real-world datasets, our method demonstrated robustness and effectiveness. Notably, when validated on the ACM dataset, PREM achieved a 5% improvement in AUC, a 9-fold increase in training speed, and sharply reduce memory usage compared to the most efficient baseline.
Authors: Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan O Arik, Tomas Pfister, Somesh Jha
Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes decision-making scenarios is still limited due to the potential for errors. Selective prediction is a technique that can be used to improve the reliability of the LLMs by allowing them to abstain from making predictions when they are unsure of the answer. In this work, we propose a novel framework for adaptation with self-evaluation to improve the selective prediction performance of LLMs. Our framework is based on the idea of using parameter-efficient tuning to adapt the LLM to the specific task at hand while improving its ability to perform self-evaluation. We evaluate our method on a variety of question-answering (QA) datasets and show that it outperforms state-of-the-art selective prediction methods. For example, on the CoQA benchmark, our method improves the AUACC from 91.23% to 92.63% and improves the AUROC from 74.61% to 80.25%.
Authors: Hongliang Zhong, Jingbo Zhang, Jing Liao
We propose VQ-NeRF, a two-branch neural network model that incorporates Vector Quantization (VQ) to decompose and edit reflectance fields in 3D scenes. Conventional neural reflectance fields use only continuous representations to model 3D scenes, despite the fact that objects are typically composed of discrete materials in reality. This lack of discretization can result in noisy material decomposition and complicated material editing. To address these limitations, our model consists of a continuous branch and a discrete branch. The continuous branch follows the conventional pipeline to predict decomposed materials, while the discrete branch uses the VQ mechanism to quantize continuous materials into individual ones. By discretizing the materials, our model can reduce noise in the decomposition process and generate a segmentation map of discrete materials. Specific materials can be easily selected for further editing by clicking on the corresponding area of the segmentation outcomes. Additionally, we propose a dropout-based VQ codeword ranking strategy to predict the number of materials in a scene, which reduces redundancy in the material segmentation process. To improve usability, we also develop an interactive interface to further assist material editing. We evaluate our model on both computer-generated and real-world scenes, demonstrating its superior performance. To the best of our knowledge, our model is the first to enable discrete material editing in 3D scenes.
Authors: Hans W. A. Hanley, Zakir Durumeric
Stance detection is important for understanding different attitudes and beliefs on the Internet. However, given that a passage's stance toward a given topic is often highly dependent on that topic, building a stance detection model that generalizes to unseen topics is difficult. In this work, we propose using contrastive learning as well as an unlabeled dataset of news articles that cover a variety of different topics to train topic-agnostic/TAG and topic-aware/TAW embeddings for use in downstream stance detection. Combining these embeddings in our full TATA model, we achieve state-of-the-art performance across several public stance detection datasets (0.771 $F_1$-score on the Zero-shot VAST dataset). We release our code and data at https://github.com/hanshanley/tata.
Authors: Giacomo Balloccu, Ludovico Boratto, Christian Cancedda, Gianni Fenu, Mirko Marras
Path reasoning methods over knowledge graphs have gained popularity for their potential to improve transparency in recommender systems. However, the resulting models still rely on pre-trained knowledge graph embeddings, fail to fully exploit the interdependence between entities and relations in the KG for recommendation, and may generate inaccurate explanations. In this paper, we introduce PEARLM, a novel approach that efficiently captures user behaviour and product-side knowledge through language modelling. With our approach, knowledge graph embeddings are directly learned from paths over the KG by the language model, which also unifies entities and relations in the same optimisation space. Constraints on the sequence decoding additionally guarantee path faithfulness with respect to the KG. Experiments on two datasets show the effectiveness of our approach compared to state-of-the-art baselines. Source code and datasets: AVAILABLE AFTER GETTING ACCEPTED.
Authors: Hui Lan, Vasilis Syrgkanis
Accurate estimation of conditional average treatment effects (CATE) is at the core of personalized decision making. While there is a plethora of models for CATE estimation, model selection is a nontrivial task, due to the fundamental problem of causal inference. Recent empirical work provides evidence in favor of proxy loss metrics with double robust properties and in favor of model ensembling. However, theoretical understanding is lacking. Direct application of prior theoretical work leads to suboptimal oracle model selection rates due to the non-convexity of the model selection problem. We provide regret rates for the major existing CATE ensembling approaches and propose a new CATE model ensembling approach based on Q-aggregation using the doubly robust loss. Our main result shows that causal Q-aggregation achieves statistically optimal oracle model selection regret rates of $\frac{\log(M)}{n}$ (with $M$ models and $n$ samples), with the addition of higher-order estimation error terms related to products of errors in the nuisance functions. Crucially, our regret rate does not require that any of the candidate CATE models be close to the truth. We validate our new method on many semi-synthetic datasets and also provide extensions of our work to CATE model selection with instrumental variables and unobserved confounding.
Authors: Yoshua Bengio, Geoffrey Hinton, Andrew Yao, Dawn Song, Pieter Abbeel, Yuval Noah Harari, Ya-Qin Zhang, Lan Xue, Shai Shalev-Shwartz, Gillian Hadfield, Jeff Clune, Tegan Maharaj, Frank Hutter, Atılım Güneş Baydin, Sheila McIlraith, Qiqi Gao, Ashwin Acharya, David Krueger, Anca Dragan, Philip Torr, Stuart Russell, Daniel Kahneman, Jan Brauner, Sören Mindermann
In this short consensus paper, we outline risks from upcoming, advanced AI systems. We examine large-scale social harms and malicious uses, as well as an irreversible loss of human control over autonomous AI systems. In light of rapid and continuing AI progress, we propose urgent priorities for AI R&D and governance.
Authors: Louis Yu Lu
This paper presents a novel fast machine learning method that leverages two techniques: Vector Embedding on Orthonormal Basis (VEOB) and Spectral Transform (ST). The VEOB converts the original data encoding into a vector embedding with coordinates projected onto orthonormal bases. The Singular Value Decomposition (SVD) technique is used to calculate the vector basis and projection coordinates, leading to an enhanced distance measurement in the embedding space and facilitating data compression by preserving the projection vectors associated with the largest singular values. On the other hand, ST transforms sequence of vector data into spectral space. By applying the Discrete Cosine Transform (DCT) and selecting the most significant components, it streamlines the handling of lengthy vector sequences. The paper provides examples of word embedding, text chunk embedding, and image embedding, implemented in Julia language with a vector database. It also investigates unsupervised learning and supervised learning using this method, along with strategies for handling large data volumes.
Authors: Soon-Jae Hwang, Chang-Sung Jeong
Neural Machine Translation (NMT) has become a significant technology in natural language processing through extensive research and development. However, the deficiency of high-quality bilingual language pair data still poses a major challenge to improving NMT performance. Recent studies are exploring the use of contextual information from pre-trained language model (PLM) to address this problem. Yet, the issue of incompatibility between PLM and NMT model remains unresolved. This study proposes a PLM-integrated NMT (PiNMT) model to overcome the identified problems. The PiNMT model consists of three critical components, PLM Multi Layer Converter, Embedding Fusion, and Cosine Alignment, each playing a vital role in providing effective PLM information to NMT. Furthermore, two training strategies, Separate Learning Rates and Dual Step Training, are also introduced in this paper. By implementing the proposed PiNMT model and training strategy, we achieved state-of-the-art performance on the IWSLT'14 En$\leftrightarrow$De dataset. This study's outcomes are noteworthy as they demonstrate a novel approach for efficiently integrating PLM with NMT to overcome incompatibility and enhance performance.
Authors: Dimitris Stripelis, Chrysovalantis Anastasiou, Patrick Toral, Armaghan Asghar, Jose Luis Ambite
A Federated Learning (FL) system typically consists of two core processing entities: the federation controller and the learners. The controller is responsible for managing the execution of FL workflows across learners and the learners for training and evaluating federated models over their private datasets. While executing an FL workflow, the FL system has no control over the computational resources or data of the participating learners. Still, it is responsible for other operations, such as model aggregation, task dispatching, and scheduling. These computationally heavy operations generally need to be handled by the federation controller. Even though many FL systems have been recently proposed to facilitate the development of FL workflows, most of these systems overlook the scalability of the controller. To meet this need, we designed and developed a novel FL system called MetisFL, where the federation controller is the first-class citizen. MetisFL re-engineers all the operations conducted by the federation controller to accelerate the training of large-scale FL workflows. By quantitatively comparing MetisFL against other state-of-the-art FL systems, we empirically demonstrate that MetisFL leads to a 10-fold wall-clock time execution boost across a wide range of challenging FL workflows with increasing model sizes and federation sites.
Authors: Ni Yao, Hang Hu, Kaicong Chen, Chen Zhao, Yuan Guo, Boya Li, Jiaofen Nan, Yanting Li, Chuang Han, Fubao Zhu, Weihua Zhou, Li Tian
Objectives To develop and validate a deep learning-based diagnostic model incorporating uncertainty estimation so as to facilitate radiologists in the preoperative differentiation of the pathological subtypes of renal cell carcinoma (RCC) based on CT images. Methods Data from 668 consecutive patients, pathologically proven RCC, were retrospectively collected from Center 1. By using five-fold cross-validation, a deep learning model incorporating uncertainty estimation was developed to classify RCC subtypes into clear cell RCC (ccRCC), papillary RCC (pRCC), and chromophobe RCC (chRCC). An external validation set of 78 patients from Center 2 further evaluated the model's performance. Results In the five-fold cross-validation, the model's area under the receiver operating characteristic curve (AUC) for the classification of ccRCC, pRCC, and chRCC was 0.868 (95% CI: 0.826-0.923), 0.846 (95% CI: 0.812-0.886), and 0.839 (95% CI: 0.802-0.88), respectively. In the external validation set, the AUCs were 0.856 (95% CI: 0.838-0.882), 0.787 (95% CI: 0.757-0.818), and 0.793 (95% CI: 0.758-0.831) for ccRCC, pRCC, and chRCC, respectively. Conclusions The developed deep learning model demonstrated robust performance in predicting the pathological subtypes of RCC, while the incorporated uncertainty emphasized the importance of understanding model confidence, which is crucial for assisting clinical decision-making for patients with renal tumors. Clinical relevance statement Our deep learning approach, integrated with uncertainty estimation, offers clinicians a dual advantage: accurate RCC subtype predictions complemented by diagnostic confidence references, promoting informed decision-making for patients with RCC.
Authors: Nikolaos Evangelou, Tianqi Cui, Juan M. Bello-Rivas, Alexei Makeev, Ioannis G. Kevrekidis
We study the tipping point collective dynamics of an adaptive susceptible-infected-susceptible (SIS) epidemiological network in a data-driven, machine learning-assisted manner. We identify a parameter-dependent effective stochastic differential equation (eSDE) in terms of physically meaningful coarse mean-field variables through a deep-learning ResNet architecture inspired by numerical stochastic integrators. We construct an approximate effective bifurcation diagram based on the identified drift term of the eSDE and contrast it with the mean-field SIS model bifurcation diagram. We observe a subcritical Hopf bifurcation in the evolving network's effective SIS dynamics, that causes the tipping point behavior; this takes the form of large amplitude collective oscillations that spontaneously -- yet rarely -- arise from the neighborhood of a (noisy) stationary state. We study the statistics of these rare events both through repeated brute force simulations and by using established mathematical/computational tools exploiting the right-hand-side of the identified SDE. We demonstrate that such a collective SDE can also be identified (and the rare events computations also performed) in terms of data-driven coarse observables, obtained here via manifold learning techniques, in particular Diffusion Maps. The workflow of our study is straightforwardly applicable to other complex dynamics problems exhibiting tipping point dynamics.
Authors: Baisong Li, Xingwang Wang, Haixiao Xu
Large language models(LLMs) exhibit excellent performance across a variety of tasks, but they come with significant computational and storage costs. Quantizing these models is an effective way to alleviate this issue. However, existing methods struggle to strike a balance between model accuracy and hardware efficiency. This is where we introduce AWEQ, a post-training method that requires no additional training overhead. AWEQ excels in both ultra-low-bit quantization and 8-bit weight and activation (W8A8) quantization. There is an observation that weight quantization is less challenging than activation quantization. AWEQ transfers the difficulty of activation quantization to weights using channel equalization, achieving a balance between the quantization difficulties of both, and thereby maximizing performance. We have further refined the equalization method to mitigate quantization bias error, ensuring the robustness of the model. Extensive experiments on popular models such as LLaMA and OPT demonstrate that AWEQ outperforms all existing post-training quantization methods for large models.
Authors: Yufei Wang, Zhou Xian, Feng Chen, Tsun-Hsuan Wang, Yian Wang, Zackory Erickson, David Held, Chuang Gan
We present RoboGen, a generative robotic agent that automatically learns diverse robotic skills at scale via generative simulation. RoboGen leverages the latest advancements in foundation and generative models. Instead of directly using or adapting these models to produce policies or low-level actions, we advocate for a generative scheme, which uses these models to automatically generate diversified tasks, scenes, and training supervisions, thereby scaling up robotic skill learning with minimal human supervision. Our approach equips a robotic agent with a self-guided propose-generate-learn cycle: the agent first proposes interesting tasks and skills to develop, and then generates corresponding simulation environments by populating pertinent objects and assets with proper spatial configurations. Afterwards, the agent decomposes the proposed high-level task into sub-tasks, selects the optimal learning approach (reinforcement learning, motion planning, or trajectory optimization), generates required training supervision, and then learns policies to acquire the proposed skill. Our work attempts to extract the extensive and versatile knowledge embedded in large-scale models and transfer them to the field of robotics. Our fully generative pipeline can be queried repeatedly, producing an endless stream of skill demonstrations associated with diverse tasks and environments.
Authors: Björn Deiseroth, Max Meuer, Nikolas Gritsch, Constantin Eichenberg, Patrick Schramowski, Matthias Aßenmacher, Kristian Kersting
Large Language Models (LLMs) have reshaped natural language processing with their impressive capabilities. Their ever-increasing size, however, raised concerns about their effective deployment and the need for LLM compressions. This study introduces the Divergent Token metrics (DTMs), a novel approach for assessing compressed LLMs, addressing the limitations of traditional perplexity or accuracy measures that fail to accurately reflect text generation quality. DTMs focus on token divergence, that allow deeper insights into the subtleties of model compression, i.p. when evaluating component's impacts individually. Utilizing the First Divergent Token metric (FDTM) in model sparsification reveals that a quarter of all attention components can be pruned beyond 90% on the Llama-2 model family, still keeping SOTA performance. For quantization FDTM suggests that over 80% of parameters can naively be transformed to int8 without special outlier management. These evaluations indicate the necessity of choosing appropriate compressions for parameters individually-and that FDTM can identify those-while standard metrics result in deteriorated outcomes.
Authors: Jianyi Yang, Pengfei Li, Tongxin Li, Adam Wierman, Shaolei Ren
This paper studies the problem of Anytime-Competitive Markov Decision Process (A-CMDP). Existing works on Constrained Markov Decision Processes (CMDPs) aim to optimize the expected reward while constraining the expected cost over random dynamics, but the cost in a specific episode can still be unsatisfactorily high. In contrast, the goal of A-CMDP is to optimize the expected reward while guaranteeing a bounded cost in each round of any episode against a policy prior. We propose a new algorithm, called Anytime-Competitive Reinforcement Learning (ACRL), which provably guarantees the anytime cost constraints. The regret analysis shows the policy asymptotically matches the optimal reward achievable under the anytime competitive constraints. Experiments on the application of carbon-intelligent computing verify the reward performance and cost constraint guarantee of ACRL.
Authors: Elisa Warner, Joonsang Lee, William Hsu, Tanveer Syeda-Mahmood, Charles Kahn, Olivier Gevaert, Arvind Rao
Machine learning (ML) applications in medical artificial intelligence (AI) systems have shifted from traditional and statistical methods to increasing application of deep learning models. This survey navigates the current landscape of multimodal ML, focusing on its profound impact on medical image analysis and clinical decision support systems. Emphasizing challenges and innovations in addressing multimodal representation, fusion, translation, alignment, and co-learning, the paper explores the transformative potential of multimodal models for clinical predictions. It also questions practical implementation of such models, bringing attention to the dynamics between decision support systems and healthcare providers. Despite advancements, challenges such as data biases and the scarcity of "big data" in many biomedical domains persist. We conclude with a discussion on effective innovation and collaborative efforts to further the miss
Authors: Xinyun Chen, Guiyu Hong
We investigate the long-run behavior of single-server queues with Hawkes arrivals and general service distributions and related optimization problems. In detail, utilizing novel coupling techniques, we establish finite moment bounds for the stationary distribution of the workload and busy period processes. In addition, we are able to show that, those queueing processes converge exponentially fast to their stationary distribution. Based on these theoretic results, we develop an efficient numerical algorithm to solve the optimal staffing problem for the Hawkes queues in a data-driven manner. Numerical results indicate a sharp difference in staffing for Hawkes queues, compared to the classic GI/GI/1 model, especially in the heavy-traffic regime.
Authors: Yann Hicke, Anmol Agarwal, Qianou Ma, Paul Denny
Responding to the thousands of student questions on online QA platforms each semester has a considerable human cost, particularly in computing courses with rapidly growing enrollments. To address the challenges of scalable and intelligent question-answering (QA), we introduce an innovative solution that leverages open-source Large Language Models (LLMs) from the LLaMA-2 family to ensure data privacy. Our approach combines augmentation techniques such as retrieval augmented generation (RAG), supervised fine-tuning (SFT), and learning from human preferences data using Direct Preference Optimization (DPO). Through extensive experimentation on a Piazza dataset from an introductory CS course, comprising 10,000 QA pairs and 1,500 pairs of preference data, we demonstrate a significant 30% improvement in the quality of answers, with RAG being a particularly impactful addition. Our contributions include the development of a novel architecture for educational QA, extensive evaluations of LLM performance utilizing both human assessments and LLM-based metrics, and insights into the challenges and future directions of educational data processing. This work paves the way for the development of CHATA, an intelligent QA assistant customizable for courses with an online QA platform
Authors: Zahed Rahmati, Ali Rahmati, Dariush Kazemi
Despite the success of graph neural network models in node classification, edge prediction (the task of predicting missing or potential links between nodes in a graph) remains a challenging problem for these models. A common approach for edge prediction is to first obtain the embeddings of two nodes, and then a predefined scoring function is used to predict the existence of an edge between the two nodes. In this paper, we introduce a new approach called Edge2Node (E2N) which directly obtains an embedding for each edge, without the need for a scoring function. To do this, we create a new graph H based on the graph G given for the edge prediction task, and then reduce the edge prediction task on G to a node classification task on H. Our E2N method can be easily applied to any edge prediction task with superior performance and lower computational costs.
Our E2N method beats the best-known methods on the leaderboards for ogbl-ppa, ogbl-collab, and ogbl-ddi datasets by 25.89%, 24.19%, and 0.34% improvements, respectively.
Authors: Wenhui Cui, Woojae Jeong, Philipp Thölke, Takfarinas Medani, Karim Jerbi, Anand A. Joshi, Richard M. Leahy
To handle the scarcity and heterogeneity of electroencephalography (EEG) data for Brain-Computer Interface (BCI) tasks, and to harness the power of large publicly available data sets, we propose Neuro-GPT, a foundation model consisting of an EEG encoder and a GPT model. The foundation model is pre-trained on a large-scale data set using a self-supervised task that learns how to reconstruct masked EEG segments. We then fine-tune the model on a Motor Imagery Classification task to validate its performance in a low-data regime (9 subjects). Our experiments demonstrate that applying a foundation model can significantly improve classification performance compared to a model trained from scratch, which provides evidence for the generalizability of the foundation model and its ability to address challenges of data scarcity and heterogeneity in EEG.
Authors: Ruomeng Ding, Chaoyun Zhang, Lu Wang, Yong Xu, Minghua Ma, Wei Zhang, Si Qin, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang
Recent advancements in Large Language Models (LLMs) have revolutionized decision-making by breaking down complex problems into more manageable language sequences referred to as ``thoughts''. An effective thought design should consider three key perspectives: performance, efficiency, and flexibility. However, existing thought can at most exhibit two of these attributes. To address these limitations, we introduce a novel thought prompting approach called ``Everything of Thoughts'' (XoT) to defy the law of ``Penrose triangle of existing thought paradigms. XoT leverages pretrained reinforcement learning and Monte Carlo Tree Search (MCTS) to incorporate external domain knowledge into thoughts, thereby enhancing LLMs' capabilities and enabling them to generalize to unseen problems efficiently. Through the utilization of the MCTS-LLM collaborative thought revision framework, this approach autonomously produces high-quality comprehensive cognitive mappings with minimal LLM interactions. Additionally, XoT empowers LLMs to engage in unconstrained thinking, allowing for flexible cognitive mappings for problems with multiple solutions. We evaluate XoT on several challenging multi-solution problem-solving tasks, including Game of 24, 8-Puzzle, and Pocket Cube. Our results demonstrate that XoT significantly outperforms existing approaches. Notably, XoT can yield multiple solutions with just one LLM call, showcasing its remarkable proficiency in addressing complex problems across diverse domains.
Authors: Wang Qinsi, Ke Jinghan, Liang Zhi, Zhang Sihai
Neural Architecture Search (NAS) has emerged as a favoured method for unearthing effective neural architectures. Recent development of large models has intensified the demand for faster search speeds and more accurate search results. However, designing large models by NAS is challenging due to the dramatical increase of search space and the associated huge performance evaluation cost. Consider a typical modular search space widely used in NAS, in which a neural architecture consists of $m$ block nodes and a block node has $n$ alternative blocks. Facing the space containing $n^m$ candidate networks, existing NAS methods attempt to find the best one by searching and evaluating candidate networks directly.Different from the general strategy that takes architecture search as a whole problem, we propose a novel divide-and-conquer strategy by making use of the modular nature of the search space.Here, we introduce MathNAS, a general NAS framework based on mathematical programming.In MathNAS, the performances of the $m*n$ possible building blocks in the search space are calculated first, and then the performance of a network is directly predicted based on the performances of its building blocks. Although estimating block performances involves network training, just as what happens for network performance evaluation in existing NAS methods, predicting network performance is completely training-free and thus extremely fast. In contrast to the $n^m$ candidate networks to evaluate in existing NAS methods, which require training and a formidable computational burden, there are only $m*n$ possible blocks to handle in MathNAS. Therefore, our approach effectively reduces the complexity of network performance evaluation.Our code is available at https://github.com/wangqinsi1/MathNAS.
Authors: Wenqian Li, Shuran Fu, Fengrui Zhang, Yan Pang
Federated Learning (FL) enables collaborative model training while preserving the privacy of raw data. A challenge in this framework is the fair and efficient valuation of data, which is crucial for incentivizing clients to contribute high-quality data in the FL task. In scenarios involving numerous data clients within FL, it is often the case that only a subset of clients and datasets are pertinent to a specific learning task, while others might have either a negative or negligible impact on the model training process. This paper introduces a novel privacy-preserving method for evaluating client contributions and selecting relevant datasets without a pre-specified training algorithm in an FL task. Our proposed approach FedBary, utilizes Wasserstein distance within the federated context, offering a new solution for data valuation in the FL framework. This method ensures transparent data valuation and efficient computation of the Wasserstein barycenter and reduces the dependence on validation datasets. Through extensive empirical experiments and theoretical analyses, we demonstrate the potential of this data valuation method as a promising avenue for FL research.
Authors: Shahriar Golchin, Mihai Surdeanu
Data contamination, i.e., the presence of test data from downstream tasks in the training data of large language models (LLMs), is a potential major issue in measuring LLMs' real effectiveness on other tasks. We propose a straightforward yet effective method for identifying data contamination within LLMs. At its core, our approach starts by identifying potential contamination at the instance level; using this information, our approach then assesses wider contamination at the partition level. To estimate contamination of individual instances, we employ "guided instruction:" a prompt consisting of the dataset name, partition type, and the random-length initial segment of a reference instance, asking the LLM to complete it. An instance is flagged as contaminated if the LLM's output either exactly or nearly matches the latter segment of the reference. To understand if an entire partition is contaminated, we propose two ideas. The first idea marks a dataset partition as contaminated if the average overlap score with the reference instances (as measured by ROUGE-L or BLEURT) is statistically significantly better with the completions from guided instruction compared to a "general instruction" that does not include the dataset and partition name. The second idea marks a dataset partition as contaminated if a classifier based on GPT-4 with few-shot in-context learning prompt marks multiple generated completions as exact/near-exact matches of the corresponding reference instances. Our best method achieves an accuracy between 92% and 100% in detecting if an LLM is contaminated with seven datasets, containing train and test/validation partitions, when contrasted with manual evaluation by human experts. Further, our findings indicate that GPT-4 is contaminated with AG News, WNLI, and XSum datasets.
Authors: Haoran Liao, Derek S. Wang, Iskandar Sitdikov, Ciro Salcedo, Alireza Seif, Zlatko K. Minev
Quantum computers are actively competing to surpass classical supercomputers, but quantum errors remain their chief obstacle. The key to overcoming these on near-term devices has emerged through the field of quantum error mitigation, enabling improved accuracy at the cost of additional runtime. In practice, however, the success of mitigation is limited by a generally exponential overhead. Can classical machine learning address this challenge on today's quantum computers? Here, through both simulations and experiments on state-of-the-art quantum computers using up to 100 qubits, we demonstrate that machine learning for quantum error mitigation (ML-QEM) can drastically reduce overheads, maintain or even surpass the accuracy of conventional methods, and yield near noise-free results for quantum algorithms. We benchmark a variety of machine learning models -- linear regression, random forests, multi-layer perceptrons, and graph neural networks -- on diverse classes of quantum circuits, over increasingly complex device-noise profiles, under interpolation and extrapolation, and for small and large quantum circuits. These tests employ the popular digital zero-noise extrapolation method as an added reference. We further show how to scale ML-QEM to classically intractable quantum circuits by mimicking the results of traditional mitigation results, while significantly reducing overhead. Our results highlight the potential of classical machine learning for practical quantum computation.