Authors: Yangdi Jiang, Xiaotian Chang, Yi Liu, Lei Ding, Linglong Kong, Bei Jiang
We develop an advanced approach for extending Gaussian Differential Privacy (GDP) to general Riemannian manifolds. The concept of GDP stands out as a prominent privacy definition that strongly warrants extension to manifold settings, due to its central limit properties. By harnessing the power of the renowned Bishop-Gromov theorem in geometric analysis, we propose a Riemannian Gaussian distribution that integrates the Riemannian distance, allowing us to achieve GDP in Riemannian manifolds with bounded Ricci curvature. To the best of our knowledge, this work marks the first instance of extending the GDP framework to accommodate general Riemannian manifolds, encompassing curved spaces, and circumventing the reliance on tangent space summaries. We provide a simple algorithm to evaluate the privacy budget $\mu$ on any one-dimensional manifold and introduce a versatile Markov Chain Monte Carlo (MCMC)-based algorithm to calculate $\mu$ on any Riemannian manifold with constant curvature. Through simulations on one of the most prevalent manifolds in statistics, the unit sphere $S^d$, we demonstrate the superior utility of our Riemannian Gaussian mechanism in comparison to the previously proposed Riemannian Laplace mechanism for implementing GDP.
Authors: Hritik Bansal, Yonatan Bitton, Idan Szpektor, Kai-Wei Chang, Aditya Grover
Despite being (pre)trained on a massive amount of data, state-of-the-art video-language alignment models are not robust to semantically-plausible contrastive changes in the video captions. Our work addresses this by identifying a broad spectrum of contrast misalignments, such as replacing entities, actions, and flipping event order, which alignment models should be robust against. To this end, we introduce the VideoCon, a video-language alignment dataset constructed by a large language model that generates plausible contrast video captions and explanations for differences between original and contrast video captions. Then, a generative video-language model is finetuned with VideoCon to assess video-language entailment and generate explanations. Our VideoCon-based alignment model significantly outperforms current models. It exhibits a 12-point increase in AUC for the video-language alignment task on human-generated contrast captions. Finally, our model sets new state of the art zero-shot performance in temporally-extensive video-language tasks such as text-to-video retrieval (SSv2-Temporal) and video question answering (ATP-Hard). Moreover, our model shows superior performance on novel videos and human-crafted captions and explanations. Our code and data are available at https://github.com/Hritikbansal/videocon.
Authors: Zifeng Ding, Heling Cai, Jingpei Wu, Yunpu Ma, Ruotong Liao, Bo Xiong, Volker Tresp
In recent years, modeling evolving knowledge over temporal knowledge graphs (TKGs) has become a heated topic. Various methods have been proposed to forecast links on TKGs. Most of them are embedding-based, where hidden representations are learned to represent knowledge graph (KG) entities and relations based on the observed graph contexts. Although these methods show strong performance on traditional TKG forecasting (TKGF) benchmarks, they naturally face a strong challenge when they are asked to model the unseen zero-shot relations that has no prior graph context. In this paper, we try to mitigate this problem as follows. We first input the text descriptions of KG relations into large language models (LLMs) for generating relation representations, and then introduce them into embedding-based TKGF methods. LLM-empowered representations can capture the semantic information in the relation descriptions. This makes the relations, whether seen or unseen, with similar semantic meanings stay close in the embedding space, enabling TKGF models to recognize zero-shot relations even without any observed graph context. Experimental results show that our approach helps TKGF models to achieve much better performance in forecasting the facts with previously unseen relations, while still maintaining their ability in link forecasting regarding seen relations.
Authors: Cho-Jui Hsieh, Si Si, Felix X. Yu, Inderjit S. Dhillon
Large language models (LLMs) have demonstrated remarkable capabilities in solving complex open-domain tasks, guided by comprehensive instructions and demonstrations provided in the form of prompts. However, these prompts can be lengthy, often comprising hundreds of lines and thousands of tokens, and their design often requires considerable human effort. Recent research has explored automatic prompt engineering for short prompts, typically consisting of one or a few sentences. However, the automatic design of long prompts remains a challenging problem due to its immense search space. In this paper, we investigate the performance of greedy algorithms and genetic algorithms for automatic long prompt engineering. We demonstrate that a simple greedy approach with beam search outperforms other methods in terms of search efficiency. Moreover, we introduce two novel techniques that utilize search history to enhance the effectiveness of LLM-based mutation in our search algorithm. Our results show that the proposed automatic long prompt engineering algorithm achieves an average of 9.2% accuracy gain on eight tasks in Big Bench Hard, highlighting the significance of automating prompt designs to fully harness the capabilities of LLMs.
Authors: Juan Vazquez-Rodriguez (M-PSI), Grégoire Lefebvre, Julien Cumin, James L. Crowley (M-PSI)
Decades of research indicate that emotion recognition is more effective when drawing information from multiple modalities. But what if some modalities are sometimes missing? To address this problem, we propose a novel Transformer-based architecture for recognizing valence and arousal in a time-continuous manner even with missing input modalities. We use a coupling of cross-attention and self-attention mechanisms to emphasize relationships between modalities during time and enhance the learning process on weak salient inputs. Experimental results on the Ulm-TSST dataset show that our model exhibits an improvement of the concordance correlation coefficient evaluation of 37% when predicting arousal values and 30% when predicting valence values, compared to a late-fusion baseline approach.
Authors: Ara Vartanian, Xiaoxi Sun, Yun-Shiuan Chuang, Siddharth Suresh, Xiaojin Zhu, Timothy T. Rogers
This paper considers how interactions with AI algorithms can boost human creative thought. We employ a psychological task that demonstrates limits on human creativity, namely semantic feature generation: given a concept name, respondents must list as many of its features as possible. Human participants typically produce only a fraction of the features they know before getting "stuck." In experiments with humans and with a language AI (GPT-4) we contrast behavior in the standard task versus a variant in which participants can ask for algorithmically-generated hints. Algorithm choice is administered by a multi-armed bandit whose reward indicates whether the hint helped generating more features. Humans and the AI show similar benefits from hints, and remarkably, bandits learning from AI responses prefer the same prompting strategy as those learning from human behavior. The results suggest that strategies for boosting human creativity via computer interactions can be learned by bandits run on groups of simulated participants.
Authors: Gabriele Cesa, Arash Behboodi
In this work, we introduce a novel approach based on algebraic topology to enhance graph convolution and attention modules by incorporating local topological properties of the data. To do so, we consider the framework of sheaf neural networks, which has been previously leveraged to incorporate additional structure into graph neural networks' features and construct more expressive, non-isotropic messages. Specifically, given an input simplicial complex (e.g. generated by the cliques of a graph or the neighbors in a point cloud), we construct its local homology sheaf, which assigns to each node the vector space of its local homology. The intermediate features of our networks live in these vector spaces and we leverage the associated sheaf Laplacian to construct more complex linear messages between them. Moreover, we extend this approach by considering the persistent version of local homology associated with a weighted simplicial complex (e.g., built from pairwise distances of nodes embeddings). This i) solves the problem of the lack of a natural choice of basis for the local homology vector spaces and ii) makes the sheaf itself differentiable, which enables our models to directly optimize the topology of their intermediate features.
Authors: Guoyao Shen, Mengyu Li, Chad W. Farris, Stephan Anderson, Xin Zhang
Deep learning-based MRI reconstruction models have achieved superior performance these days. Most recently, diffusion models have shown remarkable performance in image generation, in-painting, super-resolution, image editing and more. As a generalized diffusion model, cold diffusion further broadens the scope and considers models built around arbitrary image transformations such as blurring, down-sampling, etc. In this paper, we propose a k-space cold diffusion model that performs image degradation and restoration in k-space without the need for Gaussian noise. We provide comparisons with multiple deep learning-based MRI reconstruction models and perform tests on a well-known large open-source MRI dataset. Our results show that this novel way of performing degradation can generate high-quality reconstruction images for accelerated MRI.
Authors: Kateryna Chumachenko, Alexandros Iosifidis, Moncef Gabbouj
This paper proposes an approach for improving performance of unimodal models with multimodal training. Our approach involves a multi-branch architecture that incorporates unimodal models with a multimodal transformer-based branch. By co-training these branches, the stronger multimodal branch can transfer its knowledge to the weaker unimodal branches through a multi-task objective, thereby improving the performance of the resulting unimodal models. We evaluate our approach on tasks of dynamic hand gesture recognition based on RGB and Depth, audiovisual emotion recognition based on speech and facial video, and audio-video-text based sentiment analysis. Our approach outperforms the conventionally trained unimodal counterparts. Interestingly, we also observe that optimization of the unimodal branches improves the multimodal branch, compared to a similar multimodal model trained from scratch.
Authors: Shashank Kotyan, Danilo Vasconcellos Vargas
Neural networks have demonstrated significant accuracy across various domains, yet their vulnerability to subtle input alterations remains a persistent challenge. Conventional methods like data augmentation, while effective to some extent, fall short in addressing unforeseen corruptions, limiting the adaptability of neural networks in real-world scenarios. In response, this paper introduces a novel paradigm known as the Mixture of Class-Specific Expert Architecture. The approach involves disentangling feature learning for individual classes, offering a nuanced enhancement in scalability and overall performance. By training dedicated network segments for each class and subsequently aggregating their outputs, the proposed architecture aims to mitigate vulnerabilities associated with common neural network structures. The study underscores the importance of comprehensive evaluation methodologies, advocating for the incorporation of benchmarks like the common corruptions benchmark. This inclusion provides nuanced insights into the vulnerabilities of neural networks, especially concerning their generalization capabilities and robustness to unforeseen distortions. The research aligns with the broader objective of advancing the development of highly robust learning systems capable of nuanced reasoning across diverse and challenging real-world scenarios. Through this contribution, the paper aims to foster a deeper understanding of neural network limitations and proposes a practical approach to enhance their resilience in the face of evolving and unpredictable conditions.
Authors: Slavomír Hanzely
Machine learning assumes a pivotal role in our data-driven world. The increasing scale of models and datasets necessitates quick and reliable algorithms for model training. This dissertation investigates adaptivity in machine learning optimizers. The ensuing chapters are dedicated to various facets of adaptivity, including: 1. personalization and user-specific models via personalized loss, 2. provable post-training model adaptations via meta-learning, 3. learning unknown hyperparameters in real time via hyperparameter variance reduction, 4. fast O(1/k^2) global convergence of second-order methods via stepsized Newton method regardless of the initialization and choice basis, 5. fast and scalable second-order methods via low-dimensional updates. This thesis contributes novel insights, introduces new algorithms with improved convergence guarantees, and improves analyses of popular practical algorithms.
Authors: Thomas L. Griffiths, Jian-Qiao Zhu, Erin Grant, R. Thomas McCoy
The success of methods based on artificial neural networks in creating intelligent machines seems like it might pose a challenge to explanations of human cognition in terms of Bayesian inference. We argue that this is not the case, and that in fact these systems offer new opportunities for Bayesian modeling. Specifically, we argue that Bayesian models of cognition and artificial neural networks lie at different levels of analysis and are complementary modeling approaches, together offering a way to understand human cognition that spans these levels. We also argue that the same perspective can be applied to intelligent machines, where a Bayesian approach may be uniquely valuable in understanding the behavior of large, opaque artificial neural networks that are trained on proprietary data.
Authors: Jannis Schönleber, Lukas Cavigelli, Renzo Andri, Matteo Perotti, Luca Benini
From classical HPC to deep learning, MatMul is at the heart of today's computing. The recent Maddness method approximates MatMul without the need for multiplication by using a hash-based version of product quantization (PQ) indexing into a look-up table (LUT). Stella Nera is the first Maddness accelerator and it achieves 15x higher area efficiency (GMAC/s/mm^2) and more than 25x higher energy efficiency (TMAC/s/W) than direct MatMul accelerators implemented in the same technology. The hash function is a decision tree, which allows for an efficient hardware implementation as the multiply-accumulate operations are replaced by decision tree passes and LUT lookups. The entire Maddness MatMul can be broken down into parts that allow an effective implementation with small computing units and memories, allowing it to reach extreme efficiency while remaining generically applicable for MatMul tasks. In a commercial 14nm technology and scaled to 3nm, we achieve an energy efficiency of 161 TOp/s/W@0.55V with a Top-1 accuracy on CIFAR-10 of more than 92.5% using ResNet9.
Authors: Zhuotong Chen, Qianxiao Li, Zheng Zhang
The performance of state-of-the-art machine learning models often deteriorates when testing on demographics that are under-represented in the training dataset. This problem has predominately been studied in a supervised learning setting where the data distribution is static. However, real-world applications often involve distribution shifts caused by the deployed models. For instance, the performance disparity against monitory users can lead to a high customer churn rate, thus the available data provided by active users are skewed due to the lack of minority users. This feedback effect further exacerbates the disparity among different demographic groups in future steps. To address this issue, we propose asymptotically fair participation as a condition to maintain long-term model performance over all demographic groups. In this work, we aim to address the problem of achieving asymptotically fair participation via optimal control formulation. Moreover, we design a surrogate retention system based on existing literature on evolutionary population dynamics to approximate the dynamics of distribution shifts on active user counts, from which the objective of achieving asymptotically fair participation is formulated as an optimal control problem, and the control variables are considered as the model parameters. We apply an efficient implementation of Pontryagin's maximum principle to estimate the optimal control solution. To evaluate the effectiveness of the proposed method, we design a generic simulation environment that simulates the population dynamics of the feedback effect between user retention and model performance. When we deploy the resulting models to the simulation environment, the optimal control solution accounts for long-term planning and leads to superior performance compared with existing baseline methods.
Authors: Syed Farhan Abbas, Nguyen Thanh Duc, Yoonguu Song, Kyungwon Kim, Boreom Lee
Due to the lack of automated methods, to diagnose cerebrovascular disease, time-of-flight magnetic resonance angiography (TOF-MRA) is assessed visually, making it time-consuming. The commonly used encoder-decoder architectures for cerebrovascular segmentation utilize redundant features, eventually leading to the extraction of low-level features multiple times. Additionally, convolutional neural networks (CNNs) suffer from performance degradation when the batch size is small, and deeper networks experience the vanishing gradient problem. Methods: In this paper, we attempt to solve these limitations and propose the 3D cerebrovascular attention UNet method, named CV-AttentionUNet, for precise extraction of brain vessel images. We proposed a sequence of preprocessing techniques followed by deeply supervised UNet to improve the accuracy of segmentation of the brain vessels leading to a stroke. To combine the low and high semantics, we applied the attention mechanism. This mechanism focuses on relevant associations and neglects irrelevant anatomical information. Furthermore, the inclusion of deep supervision incorporates different levels of features that prove to be beneficial for network convergence. Results: We demonstrate the efficiency of the proposed method by cross-validating with an unlabeled dataset, which was further labeled by us. We believe that the novelty of this algorithm lies in its ability to perform well on both labeled and unlabeled data with image processing-based enhancement. The results indicate that our method performed better than the existing state-of-the-art methods on the TubeTK dataset. Conclusion: The proposed method will help in accurate segmentation of cerebrovascular structure leading to stroke
Authors: Staphord Bengesi, Hoda El-Sayed, Md Kamruzzaman Sarker, Yao Houkpati, John Irungu, Timothy Oladunni
The launch of ChatGPT has garnered global attention, marking a significant milestone in the field of Generative Artificial Intelligence. While Generative AI has been in effect for the past decade, the introduction of ChatGPT has ignited a new wave of research and innovation in the AI domain. This surge in interest has led to the development and release of numerous cutting-edge tools, such as Bard, Stable Diffusion, DALL-E, Make-A-Video, Runway ML, and Jukebox, among others. These tools exhibit remarkable capabilities, encompassing tasks ranging from text generation and music composition, image creation, video production, code generation, and even scientific work. They are built upon various state-of-the-art models, including Stable Diffusion, transformer models like GPT-3 (recent GPT-4), variational autoencoders, and generative adversarial networks. This advancement in Generative AI presents a wealth of exciting opportunities and, simultaneously, unprecedented challenges. Throughout this paper, we have explored these state-of-the-art models, the diverse array of tasks they can accomplish, the challenges they pose, and the promising future of Generative Artificial Intelligence.
Authors: Amartya Banerjee, Christopher J. Hazard, Jacob Beel, Cade Mack, Jack Xia, Michael Resnick, Will Goddin
Nonparametric learning is a fundamental concept in machine learning that aims to capture complex patterns and relationships in data without making strong assumptions about the underlying data distribution. Owing to simplicity and familiarity, one of the most well-known algorithms under this paradigm is the $k$-nearest neighbors ($k$-NN) algorithm. Driven by the usage of machine learning in safety-critical applications, in this work, we shed new light on the traditional nearest neighbors algorithm from the perspective of information theory and propose a robust and interpretable framework for tasks such as classification, regression, and anomaly detection using a single model. Instead of using a traditional distance measure which needs to be scaled and contextualized, we use a novel formulation of \textit{surprisal} (amount of information required to explain the difference between the observed and expected result). Finally, we demonstrate this architecture's capability to perform at-par or above the state-of-the-art on classification, regression, and anomaly detection tasks using a single model with enhanced interpretability by providing novel concepts for characterizing data and predictions.
Authors: Sheldon C. Ebron Jr., Kan Yang
Federated Learning (FL) enables collaborative machine learning model training across multiple parties without sharing raw data. However, FL's distributed nature allows malicious clients to impact model training through Byzantine or backdoor attacks, using erroneous model updates. Existing defenses measure the deviation of each update from a 'ground-truth model update.' They often rely on a benign root dataset on the server or use trimmed mean or median for clipping, both methods having limitations.
We introduce FedTruth, a robust defense against model poisoning in FL. FedTruth doesn't assume specific data distributions nor requires a benign root dataset. It estimates a global model update with dynamic aggregation weights, considering contributions from all benign clients. Empirical studies demonstrate FedTruth's efficacy in mitigating the impacts of poisoned updates from both Byzantine and backdoor attacks.
Authors: Can Li, Sheng Shao, Junyi Qu, Shuchao Pang, Mehmet A. Orgun
Machine learning models for medical images can help physicians diagnose and manage diseases. However, due to the fact that medical image annotation requires a great deal of manpower and expertise, as well as the fact that clinical departments perform image annotation based on task orientation, there is the problem of having fewer medical image annotation data with more unlabeled data and having many datasets that annotate only a single organ. In this paper, we present UniMOS, the first universal framework for achieving the utilization of fully and partially labeled images as well as unlabeled images. Specifically, we construct a Multi-Organ Segmentation (MOS) module over fully/partially labeled data as the basenet and designed a new target adaptive loss. Furthermore, we incorporate a semi-supervised training module that combines consistent regularization and pseudolabeling techniques on unlabeled data, which significantly improves the segmentation of unlabeled data. Experiments show that the framework exhibits excellent performance in several medical image segmentation tasks compared to other advanced methods, and also significantly improves data utilization and reduces annotation cost. Code and models are available at: https://github.com/lw8807001/UniMOS.
Authors: Shiyuan Luo, Juntong Ni, Shengyu Chen, Runlong Yu, Yiqun Xie, Licheng Liu, Zhenong Jin, Huaxiu Yao, Xiaowei Jia
Modeling environmental ecosystems is critical for the sustainability of our planet, but is extremely challenging due to the complex underlying processes driven by interactions amongst a large number of physical variables. As many variables are difficult to measure at large scales, existing works often utilize a combination of observable features and locally available measurements or modeled values as input to build models for a specific study region and time period. This raises a fundamental question in advancing the modeling of environmental ecosystems: how to build a general framework for modeling the complex relationships amongst various environmental data over space and time? In this paper, we introduce a new framework, FREE, which maps available environmental data into a text space and then converts the traditional predictive modeling task in environmental science to the semantic recognition problem. The proposed FREE framework leverages recent advances in Large Language Models (LLMs) to supplement the original input features with natural language descriptions. This facilitates capturing the data semantics and also allows harnessing the irregularities of input features. When used for long-term prediction, FREE has the flexibility to incorporate newly collected observations to enhance future prediction. The efficacy of FREE is evaluated in the context of two societally important real-world applications, predicting stream water temperature in the Delaware River Basin and predicting annual corn yield in Illinois and Iowa. Beyond the superior predictive performance over multiple baseline methods, FREE is shown to be more data- and computation-efficient as it can be pre-trained on simulated data generated by physics-based models.
Authors: Achille Nazaret, Justin Hong, Elham Azizi, David Blei
Inferring causal relationships as directed acyclic graphs (DAGs) is an important but challenging problem. Differentiable Causal Discovery (DCD) is a promising approach to this problem, framing the search as a continuous optimization. But existing DCD methods are numerically unstable, with poor performance beyond tens of variables. In this paper, we propose Stable Differentiable Causal Discovery (SDCD), a new method that improves previous DCD methods in two ways: (1) It employs an alternative constraint for acyclicity; this constraint is more stable, both theoretically and empirically, and fast to compute. (2) It uses a training procedure tailored for sparse causal graphs, which are common in real-world scenarios. We first derive SDCD and prove its stability and correctness. We then evaluate it with both observational and interventional data and on both small-scale and large-scale settings. We find that SDCD outperforms existing methods in both convergence speed and accuracy and can scale to thousands of variables.
Authors: Xiaorong Wang, Clara Na, Emma Strubell, Sorelle Friedler, Sasha Luccioni
Despite the popularity of the `pre-train then fine-tune' paradigm in the NLP community, existing work quantifying energy costs and associated carbon emissions has largely focused on language model pre-training. Although a single pre-training run draws substantially more energy than fine-tuning, fine-tuning is performed more frequently by many more individual actors, and thus must be accounted for when considering the energy and carbon footprint of NLP. In order to better characterize the role of fine-tuning in the landscape of energy and carbon emissions in NLP, we perform a careful empirical study of the computational costs of fine-tuning across tasks, datasets, hardware infrastructure and measurement modalities. Our experimental results allow us to place fine-tuning energy and carbon costs into perspective with respect to pre-training and inference, and outline recommendations to NLP researchers and practitioners who wish to improve their fine-tuning energy efficiency.
Authors: Naoki Saito, Stefan C. Schonsheck, Eugene Shvarts
We propose new scattering networks for signals measured on simplicial complexes, which we call \emph{Multiscale Hodge Scattering Networks} (MHSNs). Our construction is based on multiscale basis dictionaries on simplicial complexes, i.e., the $\kappa$-GHWT and $\kappa$-HGLET, which we recently developed for simplices of dimension $\kappa \in \N$ in a given simplicial complex by generalizing the node-based Generalized Haar-Walsh Transform (GHWT) and Hierarchical Graph Laplacian Eigen Transform (HGLET). The $\kappa$-GHWT and the $\kk$-HGLET both form redundant sets (i.e., dictionaries) of multiscale basis vectors and the corresponding expansion coefficients of a given signal. Our MHSNs use a layered structure analogous to a convolutional neural network (CNN) to cascade the moments of the modulus of the dictionary coefficients. The resulting features are invariant to reordering of the simplices (i.e., node permutation of the underlying graphs). Importantly, the use of multiscale basis dictionaries in our MHSNs admits a natural pooling operation that is akin to local pooling in CNNs, and which may be performed either locally or per-scale. These pooling operations are harder to define in both traditional scattering networks based on Morlet wavelets, and geometric scattering networks based on Diffusion Wavelets. As a result, we are able to extract a rich set of descriptive yet robust features that can be used along with very simple machine learning methods (i.e., logistic regression or support vector machines) to achieve high-accuracy classification systems with far fewer parameters to train than most modern graph neural networks. Finally, we demonstrate the usefulness of our MHSNs in three distinct types of problems: signal classification, domain (i.e., graph/simplex) classification, and molecular dynamics prediction.
Authors: Sercan Aygun, M. Hassan Najafi
Hyperdimensional computing (HDC) is an emerging computing paradigm with significant promise for efficient and robust learning. In HDC, objects are encoded with high-dimensional vector symbolic sequences called hypervectors. The quality of hypervectors, defined by their distribution and independence, directly impacts the performance of HDC systems. Despite a large body of work on the processing parts of HDC systems, little to no attention has been paid to data encoding and the quality of hypervectors. Most prior studies have generated hypervectors using inherent random functions, such as MATLAB`s or Python`s random function. This work introduces an optimization technique for generating hypervectors by employing quasi-random sequences. These sequences have recently demonstrated their effectiveness in achieving accurate and low-discrepancy data encoding in stochastic computing systems. The study outlines the optimization steps for utilizing Sobol sequences to produce high-quality hypervectors in HDC systems. An optimization algorithm is proposed to select the most suitable Sobol sequences for generating minimally correlated hypervectors, particularly in applications related to symbol-oriented architectures. The performance of the proposed technique is evaluated in comparison to two traditional approaches of generating hypervectors based on linear-feedback shift registers and MATLAB random function. The evaluation is conducted for two applications: (i) language and (ii) headline classification. Our experimental results demonstrate accuracy improvements of up to 10.79%, depending on the vector size. Additionally, the proposed encoding hardware exhibits reduced energy consumption and a superior area-delay product.
Authors: Yongchao Chen
Human fingerprints serve as one unique and powerful characteristic for each person, from which policemen can recognize the identity. Similar to humans, many natural bodies and intrinsic mechanical qualities can also be uniquely identified from surface characteristics. To measure the elasto-plastic properties of one material, one formally sharp indenter is pushed into the measured body under constant force and retracted, leaving a unique residual imprint of the minute size from several micrometers to nanometers. However, one great challenge is how to map the optical image of this residual imprint into the real wanted mechanical properties, i.e., the tensile force curve. In this paper, we propose a novel method to use multi-fidelity neural networks (MFNN) to solve this inverse problem. We first actively train the NN model via pure simulation data, and then bridge the sim-to-real gap via transfer learning. The most innovative part is that we use NN to dig out the unknown physics and also implant the known physics into the transfer learning framework, thus highly improving the model stability and decreasing the data requirement. This work serves as one great example of applying machine learning into the real experimental research, especially under the constraints of data limitation and fidelity variance.
Authors: Nikita Dhawan, Nicole Mitchell, Zachary Charles, Zachary Garrett, Gintare Karolina Dziugaite
The federated learning paradigm has motivated the development of methods for aggregating multiple client updates into a global server model, without sharing client data. Many federated learning algorithms, including the canonical Federated Averaging (FedAvg), take a direct (possibly weighted) average of the client parameter updates, motivated by results in distributed optimization. In this work, we adopt a function space perspective and propose a new algorithm, FedFish, that aggregates local approximations to the functions learned by clients, using an estimate based on their Fisher information. We evaluate FedFish on realistic, large-scale cross-device benchmarks. While the performance of FedAvg can suffer as client models drift further apart, we demonstrate that FedFish is more robust to longer local training. Our evaluation across several settings in image and language benchmarks shows that FedFish outperforms FedAvg as local training epochs increase. Further, FedFish results in global networks that are more amenable to efficient personalization via local fine-tuning on the same or shifted data distributions. For instance, federated pretraining on the C4 dataset, followed by few-shot personalization on Stack Overflow, results in a 7% improvement in next-token prediction by FedFish over FedAvg.
Authors: Yanzhao Wu, Ka-Ho Chow, Wenqi Wei, Ling Liu
Deep neural network ensembles combine the wisdom of multiple deep neural networks to improve the generalizability and robustness over individual networks. It has gained increasing popularity to study deep ensemble techniques in the deep learning community. Some mission-critical applications utilize a large number of deep neural networks to form deep ensembles to achieve desired accuracy and resilience, which introduces high time and space costs for ensemble execution. However, it still remains a critical challenge whether a small subset of the entire deep ensemble can achieve the same or better generalizability and how to effectively identify these small deep ensembles for improving the space and time efficiency of ensemble execution. This paper presents a novel deep ensemble pruning approach, which can efficiently identify smaller deep ensembles and provide higher ensemble accuracy than the entire deep ensemble of a large number of member networks. Our hierarchical ensemble pruning approach (HQ) leverages three novel ensemble pruning techniques. First, we show that the focal diversity metrics can accurately capture the complementary capacity of the member networks of an ensemble, which can guide ensemble pruning. Second, we design a focal diversity based hierarchical pruning approach, which will iteratively find high quality deep ensembles with low cost and high accuracy. Third, we develop a focal diversity consensus method to integrate multiple focal diversity metrics to refine ensemble pruning results, where smaller deep ensembles can be effectively identified to offer high accuracy, high robustness and high efficiency. Evaluated using popular benchmark datasets, we demonstrate that the proposed hierarchical ensemble pruning approach can effectively identify high quality deep ensembles with better generalizability while being more time and space efficient in ensemble decision making.
Authors: Karl J. Friston, Lancelot Da Costa, Alexander Tschantz, Alex Kiefer, Tommaso Salvatori, Victorita Neacsu, Magnus Koudahl, Conor Heins, Noor Sajid, Dimitrije Markovic, Thomas Parr, Tim Verbelen, Christopher L Buckley
This paper concerns structure learning or discovery of discrete generative models. It focuses on Bayesian model selection and the assimilation of training data or content, with a special emphasis on the order in which data are ingested. A key move - in the ensuing schemes - is to place priors on the selection of models, based upon expected free energy. In this setting, expected free energy reduces to a constrained mutual information, where the constraints inherit from priors over outcomes (i.e., preferred outcomes). The resulting scheme is first used to perform image classification on the MNIST dataset to illustrate the basic idea, and then tested on a more challenging problem of discovering models with dynamics, using a simple sprite-based visual disentanglement paradigm and the Tower of Hanoi (cf., blocks world) problem. In these examples, generative models are constructed autodidactically to recover (i.e., disentangle) the factorial structure of latent states - and their characteristic paths or dynamics.
Authors: Jonghoe Ku, Yong-Hee Lee, Junsup Shin, In Kyu Lee, Hyun-Woo Kim
Accurate segmentation of coronary arteries is a pivotal process in assessing cardiovascular diseases. However, the intricate structure of the cardiovascular system presents significant challenges for automatic segmentation, especially when utilizing methodologies like the SYNTAX Score, which relies extensively on detailed structural information for precise risk stratification. To address these difficulties and cater to this need, we present MPSeg, an innovative multi-phase strategy designed for coronary artery segmentation. Our approach specifically accommodates these structural complexities and adheres to the principles of the SYNTAX Score. Initially, our method segregates vessels into two categories based on their unique morphological characteristics: Left Coronary Artery (LCA) and Right Coronary Artery (RCA). Specialized ensemble models are then deployed for each category to execute the challenging segmentation task. Due to LCA's higher complexity over RCA, a refinement model is utilized to scrutinize and correct initial class predictions on segmented areas. Notably, our approach demonstrated exceptional effectiveness when evaluated in the Automatic Region-based Coronary Artery Disease diagnostics using x-ray angiography imagEs (ARCADE) Segmentation Detection Algorithm challenge at MICCAI 2023.
Authors: Sang-Hyun Lee, Yoonjae Jung, Seung-Woo Seo
Hierarchical reinforcement learning (HRL) has led to remarkable achievements in diverse fields. However, existing HRL algorithms still cannot be applied to real-world navigation tasks. These tasks require an agent to perform safety-aware behaviors and interact with surrounding objects in dynamic environments. In addition, an agent in these tasks should perform consistent and structured exploration as they are long-horizon and have complex structures with diverse objects and task-specific rules. Designing HRL agents that can handle these challenges in real-world navigation tasks is an open problem. In this paper, we propose imagination-augmented HRL (IAHRL), a new and general navigation algorithm that allows an agent to learn safe and interactive behaviors in real-world navigation tasks. Our key idea is to train a hierarchical agent in which a high-level policy infers interactions by interpreting behaviors imagined with low-level policies. Specifically, the high-level policy is designed with a permutation-invariant attention mechanism to determine which low-level policy generates the most interactive behavior, and the low-level policies are implemented with an optimization-based behavior planner to generate safe and structured behaviors following task-specific rules. To evaluate our algorithm, we introduce five complex urban driving tasks, which are among the most challenging real-world navigation tasks. The experimental results indicate that our hierarchical agent performs safety-aware behaviors and properly interacts with surrounding vehicles, achieving higher success rates and lower average episode steps than baselines in urban driving tasks.
Authors: Wei Huang, Aichun Zhu, Hui Liu
Phenotype-based screening has attracted much attention for identifying cell-active compounds. Transcriptional and proteomic profiles of cell population or single cells are informative phenotypic measures of cellular responses to perturbations. In this paper, we proposed a deep learning framework based on encoder-decoder architecture that maps the initial cellular states to a latent space, in which we assume the effects of drug perturbation on cellular states follow linear additivity. Next, we introduced the cycle consistency constraints to enforce that initial cellular state subjected to drug perturbations would produce the perturbed cellular responses, and, conversely, removal of drug perturbation from the perturbed cellular states would restore the initial cellular states. The cycle consistency constraints and linear modeling in latent space enable to learn interpretable and transferable drug perturbation representations, so that our model can predict cellular response to unseen drugs. We validated our model on three different types of datasets, including bulk transcriptional responses, bulk proteomic responses, and single-cell transcriptional responses to drug perturbations. The experimental results show that our model achieves better performance than existing state-of-the-art methods.
Authors: Alvin Chiu, Mithun Ghosh, Reyan Ahmed, Kwang-Sung Jun, Stephen Kobourov, Michael T. Goodrich
Graph neural networks have been successful for machine learning, as well as for combinatorial and graph problems such as the Subgraph Isomorphism Problem and the Traveling Salesman Problem. We describe an approach for computing graph sparsifiers by combining a graph neural network and Monte Carlo Tree Search. We first train a graph neural network that takes as input a partial solution and proposes a new node to be added as output. This neural network is then used in a Monte Carlo search to compute a sparsifier. The proposed method consistently outperforms several standard approximation algorithms on different types of graphs and often finds the optimal solution.
Authors: Chen Zhang, Xiaofeng Cao, Weiyang Liu, Ivor Tsang, James Kwok
We study the problem of teaching multiple learners simultaneously in the nonparametric iterative teaching setting, where the teacher iteratively provides examples to the learner for accelerating the acquisition of a target concept. This problem is motivated by the gap between current single-learner teaching setting and the real-world scenario of human instruction where a teacher typically imparts knowledge to multiple students. Under the new problem formulation, we introduce a novel framework -- Multi-learner Nonparametric Teaching (MINT). In MINT, the teacher aims to instruct multiple learners, with each learner focusing on learning a scalar-valued target model. To achieve this, we frame the problem as teaching a vector-valued target model and extend the target model space from a scalar-valued reproducing kernel Hilbert space used in single-learner scenarios to a vector-valued space. Furthermore, we demonstrate that MINT offers significant teaching speed-up over repeated single-learner teaching, particularly when the multiple learners can communicate with each other. Lastly, we conduct extensive experiments to validate the practicality and efficiency of MINT.
Authors: David Black, Declan Byrne, Anna Walke, Sidong Liu, Antonio Di leva, Sadahiro Kaneko, Walter Stummer, Septimiu Salcudean, Eric Suero Molina
Complete resection of malignant gliomas is hampered by the difficulty in distinguishing tumor cells at the infiltration zone. Fluorescence guidance with 5-ALA assists in reaching this goal. Using hyperspectral imaging, previous work characterized five fluorophores' emission spectra in most human brain tumors. In this paper, the effectiveness of these five spectra was explored for different tumor and tissue classification tasks in 184 patients (891 hyperspectral measurements) harboring low- (n=30) and high-grade gliomas (n=115), non-glial primary brain tumors (n=19), radiation necrosis (n=2), miscellaneous (n=10) and metastases (n=8). Four machine learning models were trained to classify tumor type, grade, glioma margins and IDH mutation. Using random forests and multi-layer perceptrons, the classifiers achieved average test accuracies of 74-82%, 79%, 81%, and 93% respectively. All five fluorophore abundances varied between tumor margin types and tumor grades (p < 0.01). For tissue type, at least four of the five fluorophore abundances were found to be significantly different (p < 0.01) between all classes. These results demonstrate the fluorophores' differing abundances in different tissue classes, as well as the value of the five fluorophores as potential optical biomarkers, opening new opportunities for intraoperative classification systems in fluorescence-guided neurosurgery.
Authors: Nikhil Potu Surya Prakash, Joohwan Seo, Jongeun Choi, Roberto Horowitz
In Robust Control and Data Driven Robust Control design methodologies, multiple plant transfer functions or a family of transfer functions are considered and a common controller is designed such that all the plants that fall into this family are stabilized. Though the plants are stabilized, the controller might be sub-optimal for each of the plants when the variations in the plants are large. This paper presents a way of clustering stable linear dynamical systems for the design of robust controllers within each of the clusters such that the controllers are optimal for each of the clusters. First a k-medoids algorithm for hard clustering will be presented for stable Linear Time Invariant (LTI) systems and then a Gaussian Mixture Models (GMM) clustering for a special class of LTI systems, common for Hard Disk Drive plants, will be presented.
Authors: Alireza Bagheri Rajeoni, Breanna Pederson, Ali Firooz, Hamed Abdollahi, Andrew K. Smith, Daniel G. Clair, Susan M. Lessner, Homayoun Valafar
Pathological alterations in the human vascular system underlie many chronic diseases, such as atherosclerosis and aneurysms. However, manually analyzing diagnostic images of the vascular system, such as computed tomographic angiograms (CTAs) is a time-consuming and tedious process. To address this issue, we propose a deep learning model to segment the vascular system in CTA images of patients undergoing surgery for peripheral arterial disease (PAD). Our study focused on accurately segmenting the vascular system (1) from the descending thoracic aorta to the iliac bifurcation and (2) from the descending thoracic aorta to the knees in CTA images using deep learning techniques. Our approach achieved average Dice accuracies of 93.5% and 80.64% in test dataset for (1) and (2), respectively, highlighting its high accuracy and potential clinical utility. These findings demonstrate the use of deep learning techniques as a valuable tool for medical professionals to analyze the health of the vascular system efficiently and accurately. Please visit the GitHub page for this paper at https://github.com/pip-alireza/TransOnet.
Authors: Maolin Wang, Dun Zeng, Zenglin Xu, Ruocheng Guo, Xiangyu Zhao
Knowledge graphs (KGs), which consist of triples, are inherently incomplete and always require completion procedure to predict missing triples. In real-world scenarios, KGs are distributed across clients, complicating completion tasks due to privacy restrictions. Many frameworks have been proposed to address the issue of federated knowledge graph completion. However, the existing frameworks, including FedE, FedR, and FEKG, have certain limitations. = FedE poses a risk of information leakage, FedR's optimization efficacy diminishes when there is minimal overlap among relations, and FKGE suffers from computational costs and mode collapse issues. To address these issues, we propose a novel method, i.e., Federated Latent Embedding Sharing Tensor factorization (FLEST), which is a novel approach using federated tensor factorization for KG completion. FLEST decompose the embedding matrix and enables sharing of latent dictionary embeddings to lower privacy risks. Empirical results demonstrate FLEST's effectiveness and efficiency, offering a balanced solution between performance and privacy. FLEST expands the application of federated tensor factorization in KG completion tasks.
Authors: Tao Wang, Yuanbin Chen, Xinlin Zhang, Yuanbo Zhou, Junlin Lan, Bizhe Bai, Tao Tan, Min Du, Qinquan Gao, Tong Tong
Supervised learning algorithms based on Convolutional Neural Networks have become the benchmark for medical image segmentation tasks, but their effectiveness heavily relies on a large amount of labeled data. However, annotating medical image datasets is a laborious and time-consuming process. Inspired by semi-supervised algorithms that use both labeled and unlabeled data for training, we propose the PLGDF framework, which builds upon the mean teacher network for segmenting medical images with less annotation. We propose a novel pseudo-label utilization scheme, which combines labeled and unlabeled data to augment the dataset effectively. Additionally, we enforce the consistency between different scales in the decoder module of the segmentation network and propose a loss function suitable for evaluating the consistency. Moreover, we incorporate a sharpening operation on the predicted results, further enhancing the accuracy of the segmentation.
Extensive experiments on three publicly available datasets demonstrate that the PLGDF framework can largely improve performance by incorporating the unlabeled data. Meanwhile, our framework yields superior performance compared to six state-of-the-art semi-supervised learning methods. The codes of this study are available at https://github.com/ortonwang/PLGDF.
Authors: Wenqing Wu
Highly parallelized workloads like machine learning training, inferences and general HPC tasks are greatly accelerated using GPU devices. In a cloud computing cluster, serving a GPU's computation power through multi-tasks sharing is highly demanded since there are always more task requests than the number of GPU available. Existing GPU sharing solutions focus on reducing task-level waiting time or task-level switching costs when multiple jobs competing for a single GPU. Non-stopped computation requests come with different priorities, having non-symmetric impact on QoS for sharing a GPU device. Existing work missed the kernel-level optimization opportunity brought by this setting. To address this problem, we present a novel kernel-level scheduling strategy called FIKIT: Filling Inter-kernel Idle Time. FIKIT incorporates task-level priority information, fine-grained kernel identification, and kernel measurement, allowing low priorities task's execution during high priority task's inter-kernel idle time. Thereby, filling the GPU's device runtime fully, and reduce overall GPU sharing impact to cloud services. Across a set of ML models, the FIKIT based inference system accelerated high priority tasks by 1.33 to 14.87 times compared to the JCT in GPU sharing mode, and more than half of the cases are accelerated by more than 3.5 times. Alternatively, under preemptive sharing, the low-priority tasks have a comparable to default GPU sharing mode JCT, with a 0.84 to 1 times ratio. We further limit the kernel measurement and runtime fine-grained kernel scheduling overhead to less than 10%.
Authors: Fan Xu, Nan Wang, Xuezhi Wen, Meiqi Gao, Chaoqun Guo, Xibin Zhao
Graph anomaly detection plays a crucial role in identifying exceptional instances in graph data that deviate significantly from the majority. It has gained substantial attention in various domains of information security, including network intrusion, financial fraud, and malicious comments, et al. Existing methods are primarily developed in an unsupervised manner due to the challenge in obtaining labeled data. For lack of guidance from prior knowledge in unsupervised manner, the identified anomalies may prove to be data noise or individual data instances. In real-world scenarios, a limited batch of labeled anomalies can be captured, making it crucial to investigate the few-shot problem in graph anomaly detection. Taking advantage of this potential, we propose a novel few-shot Graph Anomaly Detection model called FMGAD (Few-shot Message-Enhanced Contrastive-based Graph Anomaly Detector). FMGAD leverages a self-supervised contrastive learning strategy within and across views to capture intrinsic and transferable structural representations. Furthermore, we propose the Deep-GNN message-enhanced reconstruction module, which extensively exploits the few-shot label information and enables long-range propagation to disseminate supervision signals to deeper unlabeled nodes. This module in turn assists in the training of self-supervised contrastive learning. Comprehensive experimental results on six real-world datasets demonstrate that FMGAD can achieve better performance than other state-of-the-art methods, regardless of artificially injected anomalies or domain-organic anomalies.
Authors: Tobias Dam, Maximilian Henzl, Lukas Daniel Klausner
Users are more aware than ever of the importance of their own data, thanks to reports about security breaches and leaks of private, often sensitive data in recent years. Additionally, the GDPR has been in effect in the European Union for over three years and many people have encountered its effects in one way or another. Consequently, more and more users are actively protecting their personal data. One way to do this is to make of the right to erasure guaranteed in the GDPR, which has potential implications for a number of different fields, such as big data and machine learning.
Our paper presents an in-depth analysis about the impact of the use of the right to erasure on the performance of machine learning models on classification tasks. We conduct various experiments utilising different datasets as well as different machine learning algorithms to analyse a variety of deletion behaviour scenarios. Due to the lack of credible data on actual user behaviour, we make reasonable assumptions for various deletion modes and biases and provide insight into the effects of different plausible scenarios for right to erasure usage on data quality of machine learning. Our results show that the impact depends strongly on the amount of data deleted, the particular characteristics of the dataset and the bias chosen for deletion and assumptions on user behaviour.
Authors: Raffaele Marino, Lorenzo Giambagli, Lorenzo Chicchi, Lorenzo Buffoni, Duccio Fanelli
In a world increasingly reliant on machine learning, the interpretability of these models remains a substantial challenge, with many equating their functionality to an enigmatic black box. This study seeks to bridge machine learning and dynamical systems. Recognizing the deep parallels between dense neural networks and dynamical systems, particularly in the light of non-linearities and successive transformations, this manuscript introduces the Engineered Ordinary Differential Equations as Classification Algorithms (EODECAs). Uniquely designed as neural networks underpinned by continuous ordinary differential equations, EODECAs aim to capitalize on the well-established toolkit of dynamical systems. Unlike traditional deep learning models, which often suffer from opacity, EODECAs promise both high classification performance and intrinsic interpretability. They are naturally invertible, granting them an edge in understanding and transparency over their counterparts. By bridging these domains, we hope to usher in a new era of machine learning models where genuine comprehension of data processes complements predictive prowess.
Authors: Rasoul Nikbakht, Farhana Javed, Farhad Rezazadeh, Nikolaos Bartzoudis, Josep Mangues-Bafalluy
The paper introduces an advanced Decentralized Energy Marketplace (DEM) integrating blockchain technology and artificial intelligence to manage energy exchanges among smart homes with energy storage systems. The proposed framework uses Non-Fungible Tokens (NFTs) to represent unique energy profiles in a transparent and secure trading environment. Leveraging Federated Deep Reinforcement Learning (FDRL), the system promotes collaborative and adaptive energy management strategies, maintaining user privacy. A notable innovation is the use of smart contracts, ensuring high efficiency and integrity in energy transactions. Extensive evaluations demonstrate the system's scalability and the effectiveness of the FDRL method in optimizing energy distribution. This research significantly contributes to developing sophisticated decentralized smart grid infrastructures. Our approach broadens potential blockchain and AI applications in sustainable energy systems and addresses incentive alignment and transparency challenges in traditional energy trading mechanisms. The implementation of this paper is publicly accessible at \url{https://github.com/RasoulNik/DEM}.
Authors: Chenyu Jiang, Zhen Jia, Shuai Zheng, Yida Wang, Chuan Wu
Multi-task model training has been adopted to enable a single deep neural network model (often a large language model) to handle multiple tasks (e.g., question answering and text summarization). Multi-task training commonly receives input sequences of highly different lengths due to the diverse contexts of different tasks. Padding (to the same sequence length) or packing (short examples into long sequences of the same length) is usually adopted to prepare input samples for model training, which is nonetheless not space or computation efficient. This paper proposes a dynamic micro-batching approach to tackle sequence length variation and enable efficient multi-task model training. We advocate pipeline-parallel training of the large model with variable-length micro-batches, each of which potentially comprises a different number of samples. We optimize micro-batch construction using a dynamic programming-based approach, and handle micro-batch execution time variation through dynamic pipeline and communication scheduling, enabling highly efficient pipeline training. Extensive evaluation on the FLANv2 dataset demonstrates up to 4.39x higher training throughput when training T5, and 3.25x when training GPT, as compared with packing-based baselines. DynaPipe's source code is publicly available at https://github.com/awslabs/optimizing-multitask-training-through-dynamic-pipelines.
Authors: Lorena Poenaru-Olaru, Natalia Karpova, Luis Cruz, Jan Rellermeyer, Arie van Deursen
Anomaly detection techniques are essential in automating the monitoring of IT systems and operations. These techniques imply that machine learning algorithms are trained on operational data corresponding to a specific period of time and that they are continuously evaluated on newly emerging data. Operational data is constantly changing over time, which affects the performance of deployed anomaly detection models. Therefore, continuous model maintenance is required to preserve the performance of anomaly detectors over time. In this work, we analyze two different anomaly detection model maintenance techniques in terms of the model update frequency, namely blind model retraining and informed model retraining. We further investigate the effects of updating the model by retraining it on all the available data (full-history approach) and on only the newest data (sliding window approach). Moreover, we investigate whether a data change monitoring tool is capable of determining when the anomaly detection model needs to be updated through retraining.
Authors: Ryan Donghan Kwon, Dohyun Lim, Yoonha Lee, Seung Won Lee
The advent of deep learning has significantly propelled the capabilities of automated medical image diagnosis, providing valuable tools and resources in the realm of healthcare and medical diagnostics. This research delves into the development and evaluation of a Deep Residual Convolutional Neural Network (CNN) for the multi-class diagnosis of chest infections, utilizing chest X-ray images. The implemented model, trained and validated on a dataset amalgamated from diverse sources, demonstrated a robust overall accuracy of 93%. However, nuanced disparities in performance across different classes, particularly Fibrosis, underscored the complexity and challenges inherent in automated medical image diagnosis. The insights derived pave the way for future research, focusing on enhancing the model's proficiency in classifying conditions that present more subtle and nuanced visual features in the images, as well as optimizing and refining the model architecture and training process. This paper provides a comprehensive exploration into the development, implementation, and evaluation of the model, offering insights and directions for future research and development in the field.
Authors: Jiaeli Shi, Najah Ghalyan, Kostis Gourgoulias, John Buford, Sean Moran
Machine learning models trained on sensitive or private data can inadvertently memorize and leak that information. Machine unlearning seeks to retroactively remove such details from model weights to protect privacy. We contribute a lightweight unlearning algorithm that leverages the Fisher Information Matrix (FIM) for selective forgetting. Prior work in this area requires full retraining or large matrix inversions, which are computationally expensive. Our key insight is that the diagonal elements of the FIM, which measure the sensitivity of log-likelihood to changes in weights, contain sufficient information for effective forgetting. Specifically, we compute the FIM diagonal over two subsets -- the data to retain and forget -- for all trainable weights. This diagonal representation approximates the complete FIM while dramatically reducing computation. We then use it to selectively update weights to maximize forgetting of the sensitive subset while minimizing impact on the retained subset. Experiments show that our algorithm can successfully forget any randomly selected subsets of training data across neural network architectures. By leveraging the FIM diagonal, our approach provides an interpretable, lightweight, and efficient solution for machine unlearning with practical privacy benefits.
Authors: Harshil Patel, Aniruddha Panda, Tymofii Nikolaienko, Stanislav Jaso, Alejandro Lopez, Kaushic Kalyanaraman
Microkinetics allows detailed modelling of chemical transformations occurring in many industrially relevant reactions. Traditional way of solving the microkinetics model for Fischer-Tropsch synthesis (FTS) becomes inefficient when it comes to more advanced real-time applications. In this work, we address these challenges by using physics-informed neural networks(PINNs) for modelling FTS microkinetics. We propose a computationally efficient and accurate method, enabling the ultra-fast solution of the existing microkinetics models in realistic process conditions. The proposed PINN model computes the fraction of vacant catalytic sites, a key quantity in FTS microkinetics, with median relative error (MRE) of 0.03%, and the FTS product formation rates with MRE of 0.1%. Compared to conventional equation solvers, the model achieves up to 1E+06 times speed-up when running on GPUs, thus being fast enough for multi-scale and multi-physics reactor modelling and enabling its applications in real-time process control and optimization.
Authors: Mauricio Diaz-Ortiz Jr, Benjamin Kempinski, Daphne Cornelisse, Yoram Bachrach, Tal Kachman
We show how solution concepts from cooperative game theory can be used to tackle the problem of pruning neural networks.
The ever-growing size of deep neural networks (DNNs) increases their performance, but also their computational requirements. We introduce a method called Game Theory Assisted Pruning (GTAP), which reduces the neural network's size while preserving its predictive accuracy. GTAP is based on eliminating neurons in the network based on an estimation of their joint impact on the prediction quality through game theoretic solutions. Specifically, we use a power index akin to the Shapley value or Banzhaf index, tailored using a procedure similar to Dropout (commonly used to tackle overfitting problems in machine learning).
Empirical evaluation of both feedforward networks and convolutional neural networks shows that this method outperforms existing approaches in the achieved tradeoff between the number of parameters and model accuracy.
Authors: Ruixing Zhang, Liangzhe Han, Leilei Sun, Yunqi Liu, Jibin Wang, Weifeng Lv
User profiling and region analysis are two tasks of significant commercial value. However, in practical applications, modeling different features typically involves four main steps: data preparation, data processing, model establishment, evaluation, and optimization. This process is time-consuming and labor-intensive. Repeating this workflow for each feature results in abundant development time for tasks and a reduced overall volume of task development. Indeed, human mobility data contains a wealth of information. Several successful cases suggest that conducting in-depth analysis of population movement data could potentially yield meaningful profiles about users and areas. Nonetheless, most related works have not thoroughly utilized the semantic information within human mobility data and trained on a fixed number of the regions. To tap into the rich information within population movement, based on the perspective that Regions Are Who walk them, we propose a large spatiotemporal model based on trajectories (RAW). It possesses the following characteristics: 1) Tailored for trajectory data, introducing a GPT-like structure with a parameter count of up to 1B; 2) Introducing a spatiotemporal fine-tuning module, interpreting trajectories as collection of users to derive arbitrary region embedding. This framework allows rapid task development based on the large spatiotemporal model. We conducted extensive experiments to validate the effectiveness of our proposed large spatiotemporal model. It's evident that our proposed method, relying solely on human mobility data without additional features, exhibits a certain level of relevance in user profiling and region analysis. Moreover, our model showcases promising predictive capabilities in trajectory generation tasks based on the current state, offering the potential for further innovative work utilizing this large spatiotemporal model.
Authors: Matthew McTeer, Robin Henderson, Quentin M Anstee, Paolo Missier
Overlapping asymmetric datasets are common in data science and pose questions of how they can be incorporated together into a predictive analysis. In healthcare datasets there is often a small amount of information that is available for a larger number of patients such as an electronic health record, however a small number of patients may have had extensive further testing. Common solutions such as missing imputation can often be unwise if the smaller cohort is significantly different in scale to the larger sample, therefore the aim of this research is to develop a new method which can model the smaller cohort against a particular response, whilst considering the larger cohort also. Motivated by non-parametric models, and specifically flexible smoothing techniques via generalized additive models, we model a twice penalized P-Spline approximation method to firstly prevent over/under-fitting of the smaller cohort and secondly to consider the larger cohort. This second penalty is created through discrepancies in the marginal value of covariates that exist in both the smaller and larger cohorts. Through data simulations, parameter tunings and model adaptations to consider a continuous and binary response, we find our twice penalized approach offers an enhanced fit over a linear B-Spline and once penalized P-Spline approximation. Applying to a real-life dataset relating to a person's risk of developing Non-Alcoholic Steatohepatitis, we see an improved model fit performance of over 65%. Areas for future work within this space include adapting our method to not require dimensionality reduction and also consider parametric modelling methods. However, to our knowledge this is the first work to propose additional marginal penalties in a flexible regression of which we can report a vastly improved model fit that is able to consider asymmetric datasets, without the need for missing data imputation.
Authors: Robin Staab, Nikola Jovanović, Mislav Balunović, Martin Vechev
Aiming to train and deploy predictive models, organizations collect large amounts of detailed client data, risking the exposure of private information in the event of a breach. To mitigate this, policymakers increasingly demand compliance with the data minimization (DM) principle, restricting data collection to only that data which is relevant and necessary for the task. Despite regulatory pressure, the problem of deploying machine learning models that obey DM has so far received little attention. In this work, we address this challenge in a comprehensive manner. We propose a novel vertical DM (vDM) workflow based on data generalization, which by design ensures that no full-resolution client data is collected during training and deployment of models, benefiting client privacy by reducing the attack surface in case of a breach. We formalize and study the corresponding problem of finding generalizations that both maximize data utility and minimize empirical privacy risk, which we quantify by introducing a diverse set of policy-aligned adversarial scenarios. Finally, we propose a range of baseline vDM algorithms, as well as Privacy-aware Tree (PAT), an especially effective vDM algorithm that outperforms all baselines across several settings. We plan to release our code as a publicly available library, helping advance the standardization of DM for machine learning. Overall, we believe our work can help lay the foundation for further exploration and adoption of DM principles in real-world applications.
Authors: Xuan Zhao, Klaus Broelemann, Salvatore Ruggieri, Gjergji Kasneci
The importance of achieving fairness in machine learning models cannot be overstated. Recent research has pointed out that fairness should be examined from a causal perspective, and several fairness notions based on the on Pearl's causal framework have been proposed. In this paper, we construct a reweighting scheme of datasets to address causal fairness. Our approach aims at mitigating bias by considering the causal relationships among variables and incorporating them into the reweighting process. The proposed method adopts two neural networks, whose structures are intentionally used to reflect the structures of a causal graph and of an interventional graph. The two neural networks can approximate the causal model of the data, and the causal model of interventions. Furthermore, reweighting guided by a discriminator is applied to achieve various fairness notions. Experiments on real-world datasets show that our method can achieve causal fairness on the data while remaining close to the original data for downstream tasks.
Authors: Rémy Sun, Li Yang, Diane Lingrand, Frédéric Precioso
Online High Definition Map (HDMap) estimation from sensors offers a low-cost alternative to manually acquired HDMaps. As such, it promises to lighten costs for already HDMap-reliant Autonomous Driving systems, and potentially even spread their use to new systems. In this paper, we propose to improve online HDMap estimation by accounting for already existing maps. We identify 3 reasonable types of useful existing maps (minimalist, noisy, and outdated). We also introduce MapEX, a novel online HDMap estimation framework that accounts for existing maps. MapEX achieves this by encoding map elements into query tokens and by refining the matching algorithm used to train classic query based map estimation models. We demonstrate that MapEX brings significant improvements on the nuScenes dataset. For instance, MapEX - given noisy maps - improves by 38% over the MapTRv2 detector it is based on and by 16% over the current SOTA.
Authors: Junliang Wang, Qinghua Zhang, Guanhua Zhu, Guoxi Sun
The prediction of the remaining useful life (RUL) of rolling bearings is a pivotal issue in industrial production. A crucial approach to tackling this issue involves transforming vibration signals into health indicators (HI) to aid model training. This paper presents an end-to-end HI construction method, vector quantised variational autoencoder (VQ-VAE), which addresses the need for dimensionality reduction of latent variables in traditional unsupervised learning methods such as autoencoder. Moreover, concerning the inadequacy of traditional statistical metrics in reflecting curve fluctuations accurately, two novel statistical metrics, mean absolute distance (MAD) and mean variance (MV), are introduced. These metrics accurately depict the fluctuation patterns in the curves, thereby indicating the model's accuracy in discerning similar features. On the PMH2012 dataset, methods employing VQ-VAE for label construction achieved lower values for MAD and MV. Furthermore, the ASTCN prediction model trained with VQ-VAE labels demonstrated commendable performance, attaining the lowest values for MAD and MV.
Authors: Clément Scherding (1), Georgios Rigas (2), Denis Sipp (3), Peter J Schmid (4), Taraneh Sayadi (1 and 5) ((1) Institut Jean le Rond d'Alembert, Sorbonne University, (2) Department of Aeronautics, Imperial College London, (3) DAAA, Onera, (4) Department of Mechanical Engineering, KAUST, (5) Institute for Combustion Technology, Aachen University)
Many engineering applications rely on the evaluation of expensive, non-linear high-dimensional functions. In this paper, we propose the RONAALP algorithm (Reduced Order Nonlinear Approximation with Active Learning Procedure) to incrementally learn a fast and accurate reduced-order surrogate model of a target function on-the-fly as the application progresses. First, the combination of nonlinear auto-encoder, community clustering and radial basis function networks allows to learn an efficient and compact surrogate model with limited training data. Secondly, the active learning procedure overcome any extrapolation issue when evaluating the surrogate model outside of its initial training range during the online stage. This results in generalizable, fast and accurate reduced-order models of high-dimensional functions. The method is demonstrated on three direct numerical simulations of hypersonic flows in chemical nonequilibrium. Accurate simulations of these flows rely on detailed thermochemical gas models that dramatically increase the cost of such calculations. Using RONAALP to learn a reduced-order thermodynamic model surrogate on-the-fly, the cost of such simulation was reduced by up to 75% while maintaining an error of less than 10% on relevant quantities of interest.
Authors: Adam D. Cobb, Brian Matejek, Daniel Elenius, Anirban Roy, Susmit Jha
We introduce a new amortized likelihood ratio estimator for likelihood-free simulation-based inference (SBI). Our estimator is simple to train and estimates the likelihood ratio using a single forward pass of the neural estimator. Our approach directly computes the likelihood ratio between two competing parameter sets which is different from the previous approach of comparing two neural network output values. We refer to our model as the direct neural ratio estimator (DNRE). As part of introducing the DNRE, we derive a corresponding Monte Carlo estimate of the posterior. We benchmark our new ratio estimator and compare to previous ratio estimators in the literature. We show that our new ratio estimator often outperforms these previous approaches. As a further contribution, we introduce a new derivative estimator for likelihood ratio estimators that enables us to compare likelihood-free Hamiltonian Monte Carlo (HMC) with random-walk Metropolis-Hastings (MH). We show that HMC is equally competitive, which has not been previously shown. Finally, we include a novel real-world application of SBI by using our neural ratio estimator to design a quadcopter. Code is available at https://github.com/SRI-CSL/dnre.
Authors: Yue Fan, Anna Kukleva, Dengxin Dai, Bernt Schiele
Semi-supervised learning (SSL) methods effectively leverage unlabeled data to improve model generalization. However, SSL models often underperform in open-set scenarios, where unlabeled data contain outliers from novel categories that do not appear in the labeled set. In this paper, we study the challenging and realistic open-set SSL setting, where the goal is to both correctly classify inliers and to detect outliers. Intuitively, the inlier classifier should be trained on inlier data only. However, we find that inlier classification performance can be largely improved by incorporating high-confidence pseudo-labeled data, regardless of whether they are inliers or outliers. Also, we propose to utilize non-linear transformations to separate the features used for inlier classification and outlier detection in the multi-task learning framework, preventing adverse effects between them. Additionally, we introduce pseudo-negative mining, which further boosts outlier detection performance. The three ingredients lead to what we call Simple but Strong Baseline (SSB) for open-set SSL. In experiments, SSB greatly improves both inlier classification and outlier detection performance, outperforming existing methods by a large margin. Our code will be released at https://github.com/YUE-FAN/SSB.
Authors: Huy Truong, Andrés Tello, Alexander Lazovik, Victoria Degeler
Pressure and flow estimation in Water Distribution Networks (WDN) allows water management companies to optimize their control operations. For many years, mathematical simulation tools have been the most common approach to reconstructing an estimate of the WDN hydraulics. However, pure physics-based simulations involve several challenges, e.g. partially observable data, high uncertainty, and extensive manual configuration. Thus, data-driven approaches have gained traction to overcome such limitations. In this work, we combine physics-based modeling and Graph Neural Networks (GNN), a data-driven approach, to address the pressure estimation problem. First, we propose a new data generation method using a mathematical simulation but not considering temporal patterns and including some control parameters that remain untouched in previous works; this contributes to a more diverse training data. Second, our training strategy relies on random sensor placement making our GNN-based estimation model robust to unexpected sensor location changes. Third, a realistic evaluation protocol considers real temporal patterns and additionally injects the uncertainties intrinsic to real-world scenarios. Finally, a multi-graph pre-training strategy allows the model to be reused for pressure estimation in unseen target WDNs. Our GNN-based model estimates the pressure of a large-scale WDN in The Netherlands with a MAE of 1.94mH$_2$O and a MAPE of 7%, surpassing the performance of previous studies. Likewise, it outperformed previous approaches on other WDN benchmarks, showing a reduction of absolute error up to approximately 52% in the best cases.
Authors: Gianluca M. Bencomo, Jake C. Snell, Thomas L. Griffiths
Bayesian filtering approximates the true underlying behavior of a time-varying system by inverting an explicit generative model to convert noisy measurements into state estimates. This process typically requires either storage, inversion, and multiplication of large matrices or Monte Carlo estimation, neither of which are practical in high-dimensional state spaces such as the weight spaces of artificial neural networks. Here, we frame the standard Bayesian filtering problem as optimization over a time-varying objective. Instead of maintaining matrices for the filtering equations or simulating particles, we specify an optimizer that defines the Bayesian filter implicitly. In the linear-Gaussian setting, we show that every Kalman filter has an equivalent formulation using K steps of gradient descent. In the nonlinear setting, our experiments demonstrate that our framework results in filters that are effective, robust, and scalable to high-dimensional systems, comparing well against the standard toolbox of Bayesian filtering solutions. We suggest that it is easier to fine-tune an optimizer than it is to specify the correct filtering equations, making our framework an attractive option for high-dimensional filtering problems.
Authors: Thomas M. Moerland, Matthias Müller-Brockhausen, Zhao Yang, Andrius Bernatavicius, Koen Ponse, Tom Kouwenhoven, Andreas Sauter, Michiel van der Meer, Bram Renting, Aske Plaat
Due to the empirical success of reinforcement learning, an increasing number of students study the subject. However, from our practical teaching experience, we see students entering the field (bachelor, master and early PhD) often struggle. On the one hand, textbooks and (online) lectures provide the fundamentals, but students find it hard to translate between equations and code. On the other hand, public codebases do provide practical examples, but the implemented algorithms tend to be complex, and the underlying test environments contain multiple reinforcement learning challenges at once. Although this is realistic from a research perspective, it often hinders educational conceptual understanding. To solve this issue we introduce EduGym, a set of educational reinforcement learning environments and associated interactive notebooks tailored for education. Each EduGym environment is specifically designed to illustrate a certain aspect/challenge of reinforcement learning (e.g., exploration, partial observability, stochasticity, etc.), while the associated interactive notebook explains the challenge and its possible solution approaches, connecting equations and code in a single document. An evaluation among RL students and researchers shows 86% of them think EduGym is a useful tool for reinforcement learning education. All notebooks are available from https://sites.google.com/view/edu-gym/home, while the full software package can be installed from https://github.com/RLG-Leiden/edugym.
Authors: Boris Sedlak, Victor Casamayor Pujol, Praveen Kumar Donta, Schahram Dustdar
Compute Continuum (CC) systems comprise a vast number of devices distributed over computational tiers. Evaluating business requirements, i.e., Service Level Objectives (SLOs), requires collecting data from all those devices; if SLOs are violated, devices must be reconfigured to ensure correct operation. If done centrally, this dramatically increases the number of devices and variables that must be considered, while creating an enormous communication overhead. To address this, we (1) introduce a causality filter based on Markov blankets (MB) that limits the number of variables that each device must track, (2) evaluate SLOs decentralized on a device basis, and (3) infer optimal device configuration for fulfilling SLOs. We evaluated our methodology by analyzing video stream transformations and providing device configurations that ensure the Quality of Service (QoS). The devices thus perceived their environment and acted accordingly -- a form of decentralized intelligence.
Authors: Boris Sedlak, Victor Casamayor Pujol, Praveen Kumar Donta, Schahram Dustdar
Machine Learning (ML) is a common tool to interpret and predict the behavior of distributed computing systems, e.g., to optimize the task distribution between devices. As more and more data is created by Internet of Things (IoT) devices, data processing and ML training are carried out by edge devices in close proximity. To ensure Quality of Service (QoS) throughout these operations, systems are supervised and dynamically adapted with the help of ML. However, as long as ML models are not retrained, they fail to capture gradual shifts in the variable distribution, leading to an inaccurate view of the system state. Moreover, as the prediction accuracy decreases, the reporting device should actively resolve uncertainties to improve the model's precision. Such a level of self-determination could be provided by Active Inference (ACI) -- a concept from neuroscience that describes how the brain constantly predicts and evaluates sensory information to decrease long-term surprise. We encompassed these concepts in a single action-perception cycle, which we implemented for distributed agents in a smart manufacturing use case. As a result, we showed how our ACI agent was able to quickly and traceably solve an optimization problem while fulfilling QoS requirements.
Authors: Benjamin Feuer, Chinmay Hegde, Niv Cohen
Tabular classification has traditionally relied on supervised algorithms, which estimate the parameters of a prediction model using its training data. Recently, Prior-Data Fitted Networks (PFNs) such as TabPFN have successfully learned to classify tabular data in-context: the model parameters are designed to classify new samples based on labelled training samples given after the model training. While such models show great promise, their applicability to real-world data remains limited due to the computational scale needed. Here we study the following question: given a pre-trained PFN for tabular data, what is the best way to summarize the labelled training samples before feeding them to the model? We conduct an initial investigation of sketching and feature-selection methods for TabPFN, and note certain key differences between it and conventionally fitted tabular models.
Authors: Thien Le, Luana Ruiz, Stefanie Jegelka
Large-scale graph machine learning is challenging as the complexity of learning models scales with the graph size. Subsampling the graph is a viable alternative, but sampling on graphs is nontrivial as graphs are non-Euclidean. Existing graph sampling techniques require not only computing the spectra of large matrices but also repeating these computations when the graph changes, e.g., grows. In this paper, we introduce a signal sampling theory for a type of graph limit -- the graphon. We prove a Poincar\'e inequality for graphon signals and show that complements of node subsets satisfying this inequality are unique sampling sets for Paley-Wiener spaces of graphon signals. Exploiting connections with spectral clustering and Gaussian elimination, we prove that such sampling sets are consistent in the sense that unique sampling sets on a convergent graph sequence converge to unique sampling sets on the graphon. We then propose a related graphon signal sampling algorithm for large graphs, and demonstrate its good empirical performance on graph machine learning tasks.
Authors: João Simões Catulo, Cláudia Soares, Marta Guimarães
Space is becoming more crowded in Low Earth Orbit due to increased space activity. Such a dense space environment increases the risk of collisions between space objects endangering the whole space population. Therefore, the need to consider collision avoidance as part of routine operations is evident to satellite operators. Current procedures rely on the analysis of multiple collision warnings by human analysts. However, with the continuous growth of the space population, this manual approach may become unfeasible, highlighting the importance of automation in risk assessment. In 2019, ESA launched a competition to study the feasibility of applying machine learning in collision risk estimation and released a dataset that contained sequences of Conjunction Data Messages (CDMs) in support of real close encounters. The competition results showed that the naive forecast and its variants are strong predictors for this problem, which suggests that the CDMs may follow the Markov property. The proposed work investigates this theory by benchmarking Hidden Markov Models (HMM) in predicting the risk of collision between two resident space objects by using one feature of the entire dataset: the sequence of the probability in the CDMs. In addition, Bayesian statistics are used to infer a joint distribution for the parameters of the models, which allows the development of robust and reliable probabilistic predictive models that can incorporate physical or prior knowledge about the problem within a rigorous theoretical framework and provides prediction uncertainties that nicely reflect the accuracy of the predicted risk. This work shows that the implemented HMM outperforms the naive solution in some metrics, which further adds to the idea that the collision warnings may be Markovian and suggests that this is a powerful method to be further explored.
Authors: Jingyun Feng, Lin Zhang, Lili Yang
In disentangled representation learning, the goal is to achieve a compact representation that consists of all interpretable generative factors in the observational data. Learning disentangled representations for graphs becomes increasingly important as graph data rapidly grows. Existing approaches often rely on Variational Auto-Encoder (VAE) or its causal structure learning-based refinement, which suffer from sub-optimality in VAEs due to the independence factor assumption and unavailability of concept labels, respectively. In this paper, we propose an unsupervised solution, dubbed concept-free causal disentanglement, built on a theoretically provable tight upper bound approximating the optimal factor. This results in an SCM-like causal structure modeling that directly learns concept structures from data. Based on this idea, we propose Concept-free Causal VGAE (CCVGAE) by incorporating a novel causal disentanglement layer into Variational Graph Auto-Encoder. Furthermore, we prove concept consistency under our concept-free causal disentanglement framework, hence employing it to enhance the meta-learning framework, called concept-free causal Meta-Graph (CC-Meta-Graph). We conduct extensive experiments to demonstrate the superiority of the proposed models: CCVGAE and CC-Meta-Graph, reaching up to $29\%$ and $11\%$ absolute improvements over baselines in terms of AUC, respectively.
Authors: Renjiu Hu, Qihao Zhang, Pascal Spincemaille, Thanh D. Nguyen, Yi Wang
Purpose: To develop biophysics-based method for estimating perfusion Q from arterial spin labeling (ASL) images using deep learning. Methods: A 3D U-Net (QTMnet) was trained to estimate perfusion from 4D tracer propagation images. The network was trained and tested on simulated 4D tracer concentration data based on artificial vasculature structure generated by constrained constructive optimization (CCO) method. The trained network was further tested in a synthetic brain ASL image based on vasculature network extracted from magnetic resonance (MR) angiography. The estimations from both trained network and a conventional kinetic model were compared in ASL images acquired from eight healthy volunteers. Results: QTMnet accurately reconstructed perfusion Q from concentration data. Relative error of the synthetic brain ASL image was 7.04% for perfusion Q, lower than the error using single-delay ASL model: 25.15% for Q, and multi-delay ASL model: 12.62% for perfusion Q. Conclusion: QTMnet provides accurate estimation on perfusion parameters and is a promising approach as a clinical ASL MRI image processing pipeline.
Authors: Vukasin Bozic, Danilo Dordevic, Daniele Coppola, Joseph Thommes
This work presents an analysis of the effectiveness of using standard shallow feed-forward networks to mimic the behavior of the attention mechanism in the original Transformer model, a state-of-the-art architecture for sequence-to-sequence tasks. We substitute key elements of the attention mechanism in the Transformer with simple feed-forward networks, trained using the original components via knowledge distillation. Our experiments, conducted on the IWSLT2017 dataset, reveal the capacity of these "attentionless Transformers" to rival the performance of the original architecture. Through rigorous ablation studies, and experimenting with various replacement network types and sizes, we offer insights that support the viability of our approach. This not only sheds light on the adaptability of shallow feed-forward networks in emulating attention mechanisms but also underscores their potential to streamline complex architectures for sequence-to-sequence tasks.
Authors: Shourya Verma
Panoptic segmentation is an important computer vision task which combines semantic and instance segmentation. It plays a crucial role in domains of medical image analysis, self-driving vehicles, and robotics by providing a comprehensive understanding of visual environments. Traditionally, deep learning panoptic segmentation models have relied on dense and accurately annotated training data, which is expensive and time consuming to obtain. Recent advancements in self-supervised learning approaches have shown great potential in leveraging synthetic and unlabelled data to generate pseudo-labels using self-training to improve the performance of instance and semantic segmentation models. The three available methods for self-supervised panoptic segmentation use proposal-based transformer architectures which are computationally expensive, complicated and engineered for specific tasks. The aim of this work is to develop a framework to perform embedding-based self-supervised panoptic segmentation using self-training in a synthetic-to-real domain adaptation problem setting.
Authors: Shafagh Keyvanian, Michelle J. Johnson, Nadia Figueroa
A realistic human kinematic model that satisfies anatomical constraints is essential for human-robot interaction, biomechanics and robot-assisted rehabilitation. Modeling realistic joint constraints, however, is challenging as human arm motion is constrained by joint limits, inter- and intra-joint dependencies, self-collisions, individual capabilities and muscular or neurological constraints which are difficult to represent. Hence, physicians and researchers have relied on simple box-constraints, ignoring important anatomical factors. In this paper, we propose a data-driven method to learn realistic anatomically constrained upper-limb range of motion (RoM) boundaries from motion capture data. This is achieved by fitting a one-class support vector machine to a dataset of upper-limb joint space exploration motions with an efficient hyper-parameter tuning scheme. Our approach outperforms similar works focused on valid RoM learning. Further, we propose an impairment index (II) metric that offers a quantitative assessment of capability/impairment when comparing healthy and impaired arms. We validate the metric on healthy subjects physically constrained to emulate hemiplegia and different disability levels as stroke patients.
Authors: Said Ouala, Bertrand Chapron, Fabrice Collard, Lucile Gaultier, Ronan Fablet
Artificial intelligence and deep learning are currently reshaping numerical simulation frameworks by introducing new modeling capabilities. These frameworks are extensively investigated in the context of model correction and parameterization where they demonstrate great potential and often outperform traditional physical models. Most of these efforts in defining hybrid dynamical systems follow {offline} learning strategies in which the neural parameterization (called here sub-model) is trained to output an ideal correction. Yet, these hybrid models can face hard limitations when defining what should be a relevant sub-model response that would translate into a good forecasting performance. End-to-end learning schemes, also referred to as online learning, could address such a shortcoming by allowing the deep learning sub-models to train on historical data. However, defining end-to-end training schemes for the calibration of neural sub-models in hybrid systems requires working with an optimization problem that involves the solver of the physical equations. Online learning methodologies thus require the numerical model to be differentiable, which is not the case for most modeling systems. To overcome this difficulty and bypass the differentiability challenge of physical models, we present an efficient and practical online learning approach for hybrid systems. The method, called EGA for Euler Gradient Approximation, assumes an additive neural correction to the physical model, and an explicit Euler approximation of the gradients. We demonstrate that the EGA converges to the exact gradients in the limit of infinitely small time steps. Numerical experiments are performed on various case studies, including prototypical ocean-atmosphere dynamics. Results show significant improvements over offline learning, highlighting the potential of end-to-end online learning for hybrid modeling.
Authors: Marvin Schmitt, Stefan T. Radev, Paul-Christian Bürkner
We present multimodal neural posterior estimation (MultiNPE), a method to integrate heterogeneous data from different sources in simulation-based inference with neural networks. Inspired by advances in attention-based deep fusion learning, it empowers researchers to analyze data from different domains and infer the parameters of complex mathematical models with increased accuracy. We formulate different multimodal fusion approaches for MultiNPE (early, late, and hybrid) and evaluate their performance in three challenging numerical experiments. MultiNPE not only outperforms na\"ive baselines on a benchmark model, but also achieves superior inference on representative scientific models from neuroscience and cardiology. In addition, we systematically investigate the impact of partially missing data on the different fusion strategies. Across our different experiments, late and hybrid fusion techniques emerge as the methods of choice for practical applications of multimodal simulation-based inference.
Authors: Lihan Zha, Yuchen Cui, Li-Heng Lin, Minae Kwon, Montserrat Gonzalez Arenas, Andy Zeng, Fei Xia, Dorsa Sadigh
Today's robot policies exhibit subpar performance when faced with the challenge of generalizing to novel environments. Human corrective feedback is a crucial form of guidance to enable such generalization. However, adapting to and learning from online human corrections is a non-trivial endeavor: not only do robots need to remember human feedback over time to retrieve the right information in new settings and reduce the intervention rate, but also they would need to be able to respond to feedback that can be arbitrary corrections about high-level human preferences to low-level adjustments to skill parameters. In this work, we present Distillation and Retrieval of Online Corrections (DROC), a large language model (LLM)-based system that can respond to arbitrary forms of language feedback, distill generalizable knowledge from corrections, and retrieve relevant past experiences based on textual and visual similarity for improving performance in novel settings. DROC is able to respond to a sequence of online language corrections that address failures in both high-level task plans and low-level skill primitives. We demonstrate that DROC effectively distills the relevant information from the sequence of online corrections in a knowledge base and retrieves that knowledge in settings with new task or object instances. DROC outperforms other techniques that directly generate robot code via LLMs by using only half of the total number of corrections needed in the first round and requires little to no corrections after two iterations. We show further results, videos, prompts and code on https://sites.google.com/stanford.edu/droc .
Authors: Shabarish Chenakkod, Michał Dereziński, Xiaoyu Dong, Mark Rudelson
A random $m\times n$ matrix $S$ is an oblivious subspace embedding (OSE) with parameters $\epsilon>0$, $\delta\in(0,1/3)$ and $d\leq m\leq n$, if for any $d$-dimensional subspace $W\subseteq R^n$,
$P\big(\,\forall_{x\in W}\ (1+\epsilon)^{-1}\|x\|\leq\|Sx\|\leq (1+\epsilon)\|x\|\,\big)\geq 1-\delta.$
It is known that the embedding dimension of an OSE must satisfy $m\geq d$, and for any $\theta > 0$, a Gaussian embedding matrix with $m\geq (1+\theta) d$ is an OSE with $\epsilon = O_\theta(1)$. However, such optimal embedding dimension is not known for other embeddings. Of particular interest are sparse OSEs, having $s\ll m$ non-zeros per column, with applications to problems such as least squares regression and low-rank approximation.
We show that, given any $\theta > 0$, an $m\times n$ random matrix $S$ with $m\geq (1+\theta)d$ consisting of randomly sparsified $\pm1/\sqrt s$ entries and having $s= O(\log^4(d))$ non-zeros per column, is an oblivious subspace embedding with $\epsilon = O_{\theta}(1)$. Our result addresses the main open question posed by Nelson and Nguyen (FOCS 2013), who conjectured that sparse OSEs can achieve $m=O(d)$ embedding dimension, and it improves on $m=O(d\log(d))$ shown by Cohen (SODA 2016). We use this to construct the first oblivious subspace embedding with $O(d)$ embedding dimension that can be applied faster than current matrix multiplication time, and to obtain an optimal single-pass algorithm for least squares regression. We further extend our results to construct even sparser non-oblivious embeddings, leading to the first subspace embedding with low distortion $\epsilon=o(1)$ and optimal embedding dimension $m=O(d/\epsilon^2)$ that can be applied in current matrix multiplication time.
Authors: Keivalya Pandya
Chat models are capable of answering a wide range of questions, however, the accuracy of their responses is highly uncertain. In this research, we propose a specialized PEFT-MedAware model where we utilize parameter-efficient fine-tuning (PEFT) to enhance the Falcon-1b large language model on specialized MedQuAD data consisting of 16,407 medical QA pairs, leveraging only 0.44% of its trainable parameters to enhance computational efficiency. The paper adopts data preprocessing and PEFT to optimize model performance, complemented by a BitsAndBytesConfig for efficient transformer training. The resulting model was capable of outperforming other LLMs in medical question-answering tasks in specific domains with greater accuracy utilizing limited computational resources making it suitable for deployment in resource-constrained environments. We propose further improvements through expanded datasets, larger models, and feedback mechanisms for sustained medical relevancy. Our work highlights the efficiency gains and specialized capabilities of PEFT in medical AI, outpacing standard models in precision without extensive resource demands. The proposed model and data are released for research purposes only.
Authors: Marcel Marais, Mate Hartstein, George Cevora
Good weight initialisation is an important step in successful training of Artificial Neural Networks. Over time a number of improvements have been proposed to this process. In this paper we introduce a novel weight initialisation technique called the Straddled Matrix Initialiser. This initialisation technique is motivated by our assumption that major, global-scale relationships in data are linear with only smaller effects requiring complex non-linearities. Combination of Straddled Matrix and ReLU activation function initialises a Neural Network as a de facto linear model, which we postulate should be a better starting point for optimisation given our assumptions. We test this by training autoencoders on three datasets using Straddled Matrix and seven other state-of-the-art weight initialisation techniques. In all our experiments the Straddeled Matrix Initialiser clearly outperforms all other methods.
Authors: Soham Chitnis, Kiran Mantripragada, Faisal Z. Qureshi
The Hyperspectral Unxming problem is to find the pure spectral signal of the underlying materials (endmembers) and their proportions (abundances). The proposed method builds upon the recently proposed method, Latent Dirichlet Variational Autoencoder (LDVAE). It assumes that abundances can be encoded as Dirichlet Distributions while mixed pixels and endmembers are represented by Multivariate Normal Distributions. However, LDVAE does not leverage spatial information present in an HSI; we propose an Isotropic CNN encoder with spatial attention to solve the hyperspectral unmixing problem. We evaluated our model on Samson, Hydice Urban, Cuprite, and OnTech-HSI-Syn-21 datasets. Our model also leverages the transfer learning paradigm for Cuprite Dataset, where we train the model on synthetic data and evaluate it on real-world data. We are able to observe the improvement in the results for the endmember extraction and abundance estimation by incorporating the spatial information. Code can be found at https://github.com/faisalqureshi/cnn-ldvae
Authors: Xiaohui Zhang, Jaehong Yoon, Mohit Bansal, Huaxiu Yao
Multimodal learning, which integrates data from diverse sensory modes, plays a pivotal role in artificial intelligence. However, existing multimodal learning methods often struggle with challenges where some modalities appear more dominant than others during multimodal learning, resulting in suboptimal performance. To address this challenge, we propose MLA (Multimodal Learning with Alternating Unimodal Adaptation). MLA reframes the conventional joint multimodal learning process by transforming it into an alternating unimodal learning process, thereby minimizing interference between modalities. Simultaneously, it captures cross-modal interactions through a shared head, which undergoes continuous optimization across different modalities. This optimization process is controlled by a gradient modification mechanism to prevent the shared head from losing previously acquired information. During the inference phase, MLA utilizes a test-time uncertainty-based model fusion mechanism to integrate multimodal information. Extensive experiments are conducted on five diverse datasets, encompassing scenarios with complete modalities and scenarios with missing modalities. These experiments demonstrate the superiority of MLA over competing prior approaches.
Authors: Sai Saketh Rambhatla, Ishan Misra
In this work, we show that text-to-image generative models can be 'inverted' to assess their own text-image understanding capabilities in a completely automated manner.
Our method, called SelfEval, uses the generative model to compute the likelihood of real images given text prompts, making the generative model directly applicable to discriminative tasks.
Using SelfEval, we repurpose standard datasets created for evaluating multimodal text-image discriminative models to evaluate generative models in a fine-grained manner: assessing their performance on attribute binding, color recognition, counting, shape recognition, spatial understanding.
To the best of our knowledge SelfEval is the first automated metric to show a high degree of agreement for measuring text-faithfulness with the gold-standard human evaluations across multiple models and benchmarks.
Moreover, SelfEval enables us to evaluate generative models on challenging tasks such as Winoground image-score where they demonstrate competitive performance to discriminative models.
We also show severe drawbacks of standard automated metrics such as CLIP-score to measure text faithfulness on benchmarks such as DrawBench, and how SelfEval sidesteps these issues.
We hope SelfEval enables easy and reliable automated evaluation for diffusion models.
Authors: Rohit Girdhar, Mannat Singh, Andrew Brown, Quentin Duval, Samaneh Azadi, Sai Saketh Rambhatla, Akbar Shah, Xi Yin, Devi Parikh, Ishan Misra
We present Emu Video, a text-to-video generation model that factorizes the generation into two steps: first generating an image conditioned on the text, and then generating a video conditioned on the text and the generated image. We identify critical design decisions--adjusted noise schedules for diffusion, and multi-stage training--that enable us to directly generate high quality and high resolution videos, without requiring a deep cascade of models as in prior work. In human evaluations, our generated videos are strongly preferred in quality compared to all prior work--81% vs. Google's Imagen Video, 90% vs. Nvidia's PYOCO, and 96% vs. Meta's Make-A-Video. Our model outperforms commercial solutions such as RunwayML's Gen2 and Pika Labs. Finally, our factorizing approach naturally lends itself to animating images based on a user's text prompt, where our generations are preferred 96% over prior work.
Authors: Julian Arnold, Niels Lörch, Flemming Holtorf, Frank Schäfer
Despite the widespread use and success of machine-learning techniques for detecting phase transitions from data, their working principle and fundamental limits remain elusive. Here, we explain the inner workings and identify potential failure modes of these techniques by rooting popular machine-learning indicators of phase transitions in information-theoretic concepts. Using tools from information geometry, we prove that several machine-learning indicators of phase transitions approximate the square root of the system's (quantum) Fisher information from below -- a quantity that is known to indicate phase transitions but is often difficult to compute from data. We numerically demonstrate the quality of these bounds for phase transitions in classical and quantum systems.
Authors: Emmanuel Caron, Stephane Chretien
Recent extensive numerical experiments in high scale machine learning have allowed to uncover a quite counterintuitive phase transition, as a function of the ratio between the sample size and the number of parameters in the model. As the number of parameters $p$ approaches the sample size $n$, the generalisation error increases, but surprisingly, it starts decreasing again past the threshold $p=n$. This phenomenon, brought to the theoretical community attention in \cite{belkin2019reconciling}, has been thoroughly investigated lately, more specifically for simpler models than deep neural networks, such as the linear model when the parameter is taken to be the minimum norm solution to the least-squares problem, firstly in the asymptotic regime when $p$ and $n$ tend to infinity, see e.g. \cite{hastie2019surprises}, and recently in the finite dimensional regime and more specifically for linear models \cite{bartlett2020benign}, \cite{tsigler2020benign}, \cite{lecue2022geometrical}. In the present paper, we propose a finite sample analysis of non-linear models of \textit{ridge} type, where we investigate the \textit{overparametrised regime} of the double descent phenomenon for both the \textit{estimation problem} and the \textit{prediction} problem. Our results provide a precise analysis of the distance of the best estimator from the true parameter as well as a generalisation bound which complements recent works of \cite{bartlett2020benign} and \cite{chinot2020benign}. Our analysis is based on tools closely related to the continuous Newton method \cite{neuberger2007continuous} and a refined quantitative analysis of the performance in prediction of the minimum $\ell_2$-norm solution.
Authors: Min Du, Nesime Tatbul, Brian Rivers, Akhilesh Kumar Gupta, Lucas Hu, Wei Wang, Ryan Marcus, Shengtian Zhou, Insup Lee, Justin Gottschlich
Class distribution skews in imbalanced datasets may lead to models with prediction bias towards majority classes, making fair assessment of classifiers a challenging task. Metrics such as Balanced Accuracy are commonly used to evaluate a classifier's prediction performance under such scenarios. However, these metrics fall short when classes vary in importance. In this paper, we propose a simple and general-purpose evaluation framework for imbalanced data classification that is sensitive to arbitrary skews in class cardinalities and importances. Experiments with several state-of-the-art classifiers tested on real-world datasets from three different domains show the effectiveness of our framework - not only in evaluating and ranking classifiers, but also training them.
Authors: Mridul Agarwal, Qinbo Bai, Vaneet Aggarwal
We consider the problem of tabular infinite horizon concave utility reinforcement learning (CURL) with convex constraints. For this, we propose a model-based learning algorithm that also achieves zero constraint violations. Assuming that the concave objective and the convex constraints have a solution interior to the set of feasible occupation measures, we solve a tighter optimization problem to ensure that the constraints are never violated despite the imprecise model knowledge and model stochasticity. We use Bellman error-based analysis for tabular infinite-horizon setups which allows analyzing stochastic policies. Combining the Bellman error-based analysis and tighter optimization equation, for $T$ interactions with the environment, we obtain a high-probability regret guarantee for objective which grows as $\Tilde{O}(1/\sqrt{T})$, excluding other factors. The proposed method can be applied for optimistic algorithms to obtain high-probability regret bounds and also be used for posterior sampling algorithms to obtain a loose Bayesian regret bounds but with significant improvement in computational complexity.
Authors: Leonardo Ranaldi, Aria Nourbakhsh, Arianna Patrizi, Elena Sofia Ruzzetti, Dario Onorati, Francesca Fallucchi, Fabio Massimo Zanzotto
Pre-trained Transformers are challenging human performances in many NLP tasks. The massive datasets used for pre-training seem to be the key to their success on existing tasks. In this paper, we explore how a range of pre-trained Natural Language Understanding models perform on definitely unseen sentences provided by classification tasks over a DarkNet corpus. Surprisingly, results show that syntactic and lexical neural networks perform on par with pre-trained Transformers even after fine-tuning. Only after what we call extreme domain adaptation, that is, retraining with the masked language model task on all the novel corpus, pre-trained Transformers reach their standard high results. This suggests that huge pre-training corpora may give Transformers unexpected help since they are exposed to many of the possible sentences.
Authors: Paul Swoboda, Bjoern Andres, Andrea Hornakova, Florian Bernard, Jannik Irmai, Paul Roetzer, Bogdan Savchynskyy, David Stein, Ahmed Abbas
Structured prediction problems are one of the fundamental tools in machine learning. In order to facilitate algorithm development for their numerical solution, we collect in one place a large number of datasets in easy to read formats for a diverse set of problem classes. We provide archival links to datasets, description of the considered problems and problem formats, and a short summary of problem characteristics including size, number of instances etc. For reference we also give a non-exhaustive selection of algorithms proposed in the literature for their solution. We hope that this central repository will make benchmarking and comparison to established works easier. We welcome submission of interesting new datasets and algorithms for inclusion in our archive.
Authors: Francesco Stranieri, Fabio Stella
In this study, we analyze and compare the performance of state-of-the-art deep reinforcement learning algorithms for solving the supply chain inventory management problem. This complex sequential decision-making problem consists of determining the optimal quantity of products to be produced and shipped across different warehouses over a given time horizon. In particular, we present a mathematical formulation of a two-echelon supply chain environment with stochastic and seasonal demand, which allows managing an arbitrary number of warehouses and product types. Through a rich set of numerical experiments, we compare the performance of different deep reinforcement learning algorithms under various supply chain structures, topologies, demands, capacities, and costs. The results of the experimental plan indicate that deep reinforcement learning algorithms outperform traditional inventory management strategies, such as the static (s, Q)-policy. Furthermore, this study provides detailed insight into the design and development of an open-source software library that provides a customizable environment for solving the supply chain inventory management problem using a wide range of data-driven approaches.
Authors: Jingyan Wang, Ashwin Pananjady
We consider the problem of sequential evaluation, in which an evaluator observes candidates in a sequence and assigns scores to these candidates in an online, irrevocable fashion. Motivated by the psychology literature that has studied sequential bias in such settings -- namely, dependencies between the evaluation outcome and the order in which the candidates appear -- we propose a natural model for the evaluator's rating process that captures the lack of calibration inherent to such a task. We conduct crowdsourcing experiments to demonstrate various facets of our model. We then proceed to study how to correct sequential bias under our model by posing this as a statistical inference problem. We propose a near-linear time, online algorithm for this task and prove guarantees in terms of two canonical ranking metrics. We also prove that our algorithm is information theoretically optimal, by establishing matching lower bounds in both metrics. Finally, we perform a host of numerical experiments to show that our algorithm often outperforms the de facto method of using the rankings induced by the reported scores, both in simulation and on the crowdsourcing data that we collected.
Authors: Shoujin Wang, Xiuzhen Zhang, Yan Wang, Huan Liu, Francesco Ricci
Recommender systems (RSs) aim to help users to effectively retrieve items of their interests from a large catalogue. For a quite long period of time, researchers and practitioners have been focusing on developing accurate RSs. Recent years have witnessed an increasing number of threats to RSs, coming from attacks, system and user generated noise, system bias. As a result, it has become clear that a strict focus on RS accuracy is limited and the research must consider other important factors, e.g., trustworthiness. For end users, a trustworthy RS (TRS) should not only be accurate, but also transparent, unbiased and fair as well as robust to noise or attacks. These observations actually led to a paradigm shift of the research on RSs: from accuracy-oriented RSs to TRSs. However, researchers lack a systematic overview and discussion of the literature in this novel and fast developing field of TRSs. To this end, in this paper, we provide an overview of TRSs, including a discussion of the motivation and basic concepts of TRSs, a presentation of the challenges in building TRSs, and a perspective on the future directions in this area. We also provide a novel conceptual framework to support the construction of TRSs.
Authors: Zi Wang, Haoming Fang, Chen Qian, Boxuan Shi, Lijun Bao, Liuhong Zhu, Jianjun Zhou, Wenping Wei, Jianzhong Lin, Di Guo, Xiaobo Qu
Magnetic resonance imaging (MRI) is an essential diagnostic tool that suffers from prolonged scan time. To alleviate this limitation, advanced fast MRI technology attracts extensive research interests. Recent deep learning has shown its great potential in improving image quality and reconstruction speed. Faithful coil sensitivity estimation is vital for MRI reconstruction. However, most deep learning methods still rely on pre-estimated sensitivity maps and ignore their inaccuracy, resulting in the significant quality degradation of reconstructed images. In this work, we propose a Joint Deep Sensitivity estimation and Image reconstruction network, called JDSI. During the image artifacts removal, it gradually provides more faithful sensitivity maps with high-frequency information, leading to improved image reconstructions. To understand the behavior of the network, the mutual promotion of sensitivity estimation and image reconstruction is revealed through the visualization of network intermediate results. Results on in vivo datasets and radiologist reader study demonstrate that, for both calibration-based and calibrationless reconstruction, the proposed JDSI achieves the state-of-the-art performance visually and quantitatively, especially when the acceleration factor is high. Additionally, JDSI owns nice robustness to patients and autocalibration signals.
Authors: Andrei Margeloiu, Nikola Simidjievski, Pietro Lio, Mateja Jamnik
Neural network models often struggle with high-dimensional but small sample-size tabular datasets. One reason is that current weight initialisation methods assume independence between weights, which can be problematic when there are insufficient samples to estimate the model's parameters accurately. In such small data scenarios, leveraging additional structures can improve the model's performance and training stability. To address this, we propose GCondNet, a general approach to enhance neural networks by leveraging implicit structures present in tabular data. We create a graph between samples for each data dimension, and utilise Graph Neural Networks (GNNs) for extracting this implicit structure, and for conditioning the parameters of the first layer of an underlying predictor network. By creating many small graphs, GCondNet exploits the data's high-dimensionality, and thus improves the performance of an underlying predictor network. We demonstrate the effectiveness of our method on 9 real-world datasets, where GCondNet outperforms 15 standard and state-of-the-art methods. The results show that GCondNet is a versatile framework for injecting graph-regularisation into various types of neural networks, including MLPs and tabular Transformers.
Authors: Kentaroh Toyoda, Rachel Gan Kai Ying, Allan NengSheng Zhang, Tan Puay Siew
Process mining discovers and analyzes a process model from historical event logs. The prior art methods use the key attributes of case-id, activity, and timestamp hidden in an event log as clues to discover a process model. However, a user needs to specify them manually, and this can be an exhaustive task. In this paper, we propose a two-stage key attribute identification method to avoid such a manual investigation, and thus this is a step toward fully automated process discovery. One of the challenging tasks is how to avoid exhaustive computation due to combinatorial explosion. For this, we narrow down candidates for each key attribute by using supervised machine learning in the first stage and identify the best combination of the key attributes by discovering process models and evaluating them in the second stage. Our computational complexity can be reduced from $\mathcal{O}(N^3)$ to $\mathcal{O}(k^3)$ where $N$ and $k$ are the numbers of columns and candidates we keep in the first stage, respectively, and usually $k$ is much smaller than $N$. We evaluated our method with 14 open datasets and showed that our method could identify the key attributes even with $k = 2$ for about 20 seconds for many datasets.
Authors: Alexandre Capone, Geoff Pleiss, Sandra Hirche
While Gaussian processes are a mainstay for various engineering and scientific applications, the uncertainty estimates don't satisfy frequentist guarantees and can be miscalibrated in practice. State-of-the-art approaches for designing calibrated models rely on inflating the Gaussian process posterior variance, which yields confidence intervals that are potentially too coarse. To remedy this, we present a calibration approach that generates predictive quantiles using a computation inspired by the vanilla Gaussian process posterior variance but using a different set of hyperparameters chosen to satisfy an empirical calibration constraint. This results in a calibration approach that is considerably more flexible than existing approaches, which we optimize to yield tight predictive quantiles. Our approach is shown to yield a calibrated model under reasonable assumptions. Furthermore, it outperforms existing approaches in sharpness when employed for calibrated regression.
Authors: Jong-Ryul Lee, Yong-Hyuk Moon
As deep learning models become popular, there is a lot of need for deploying them to diverse device environments. Because it is costly to develop and optimize a neural network for every single environment, there is a line of research to search neural networks for multiple target environments efficiently. However, existing works for such a situation still suffer from requiring many GPUs and expensive costs. Motivated by this, we propose a novel neural network optimization framework named Bespoke for low-cost deployment. Our framework searches for a lightweight model by replacing parts of an original model with randomly selected alternatives, each of which comes from a pretrained neural network or the original model. In the practical sense, Bespoke has two significant merits. One is that it requires near zero cost for designing the search space of neural networks. The other merit is that it exploits the sub-networks of public pretrained neural networks, so the total cost is minimal compared to the existing works. We conduct experiments exploring Bespoke's the merits, and the results show that it finds efficient models for multiple targets with meager cost.
Authors: David Neumann, Andreas Lutz, Karsten Müller, Wojciech Samek
Recommender systems have become ubiquitous in the past years. They solve the tyranny of choice problem faced by many users, and are utilized by many online businesses to drive engagement and sales. Besides other criticisms, like creating filter bubbles within social networks, recommender systems are often reproved for collecting considerable amounts of personal data. However, to personalize recommendations, personal information is fundamentally required. A recent distributed learning scheme called federated learning has made it possible to learn from personal user data without its central collection. Consequently, we present a recommender system for movie recommendations, which provides privacy and thus trustworthiness on multiple levels: First and foremost, it is trained using federated learning and thus, by its very nature, privacy-preserving, while still enabling users to benefit from global insights. Furthermore, a novel federated learning scheme, called FedQ, is employed, which not only addresses the problem of non-i.i.d.-ness and small local datasets, but also prevents input data reconstruction attacks by aggregating client updates early. Finally, to reduce the communication overhead, compression is applied, which significantly compresses the exchanged neural network parametrizations to a fraction of their original size. We conjecture that this may also improve data privacy through its lossy quantization stage.
Authors: Minting Pan, Xiangming Zhu, Yitao Zheng, Yunbo Wang, Xiaokang Yang
World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios like autonomous driving, noncontrollable dynamics that are independent or sparsely dependent on action signals often exist, making it challenging to learn effective world models. To address this issue, we propose Iso-Dream++, a model-based reinforcement learning approach that has two main contributions. First, we optimize the inverse dynamics to encourage the world model to isolate controllable state transitions from the mixed spatiotemporal variations of the environment. Second, we perform policy optimization based on the decoupled latent imaginations, where we roll out noncontrollable states into the future and adaptively associate them with the current controllable state. This enables long-horizon visuomotor control tasks to benefit from isolating mixed dynamics sources in the wild, such as self-driving cars that can anticipate the movement of other vehicles, thereby avoiding potential risks. On top of our previous work, we further consider the sparse dependencies between controllable and noncontrollable states, address the training collapse problem of state decoupling, and validate our approach in transfer learning setups. Our empirical study demonstrates that Iso-Dream++ outperforms existing reinforcement learning models significantly on CARLA and DeepMind Control.
Authors: Chudi Zhong, Zhi Chen, Jiachang Liu, Margo Seltzer, Cynthia Rudin
In real applications, interaction between machine learning models and domain experts is critical; however, the classical machine learning paradigm that usually produces only a single model does not facilitate such interaction. Approximating and exploring the Rashomon set, i.e., the set of all near-optimal models, addresses this practical challenge by providing the user with a searchable space containing a diverse set of models from which domain experts can choose. We present algorithms to efficiently and accurately approximate the Rashomon set of sparse, generalized additive models with ellipsoids for fixed support sets and use these ellipsoids to approximate Rashomon sets for many different support sets. The approximated Rashomon set serves as a cornerstone to solve practical challenges such as (1) studying the variable importance for the model class; (2) finding models under user-specified constraints (monotonicity, direct editing); and (3) investigating sudden changes in the shape functions. Experiments demonstrate the fidelity of the approximated Rashomon set and its effectiveness in solving practical challenges.
Authors: Jie Xu, Yazhou Ren, Xiaolong Wang, Lei Feng, Zheng Zhang, Gang Niu, Xiaofeng Zhu
Multi-view clustering (MVC) aims at exploring category structures among multi-view data in self-supervised manners. Multiple views provide more information than single views and thus existing MVC methods can achieve satisfactory performance. However, their performance might seriously degenerate when the views are noisy in practical multi-view scenarios. In this paper, we first formally investigate the drawback of noisy views and then propose a theoretically grounded deep MVC method (namely MVCAN) to address this issue. Specifically, we propose a novel MVC objective that enables un-shared parameters and inconsistent clustering predictions across multiple views to reduce the side effects of noisy views. Furthermore, a two-level multi-view iterative optimization is designed to generate robust learning targets for refining individual views' representation learning. Theoretical analysis reveals that MVCAN works by achieving the multi-view consistency, complementarity, and noise robustness. Finally, experiments on extensive public datasets demonstrate that MVCAN outperforms state-of-the-art methods and is robust against the existence of noisy views.
Authors: Geunwoo Kim, Pierre Baldi, Stephen McAleer
Agents capable of carrying out general tasks on a computer can improve efficiency and productivity by automating repetitive tasks and assisting in complex problem-solving. Ideally, such agents should be able to solve new computer tasks presented to them through natural language commands. However, previous approaches to this problem require large amounts of expert demonstrations and task-specific reward functions, both of which are impractical for new tasks. In this work, we show that a pre-trained large language model (LLM) agent can execute computer tasks guided by natural language using a simple prompting scheme where the agent Recursively Criticizes and Improves its output (RCI). The RCI approach significantly outperforms existing LLM methods for automating computer tasks and surpasses supervised learning (SL) and reinforcement learning (RL) approaches on the MiniWoB++ benchmark. We compare multiple LLMs and find that RCI with the InstructGPT-3+RLHF LLM is state-of-the-art on MiniWoB++, using only a handful of demonstrations per task rather than tens of thousands, and without a task-specific reward function. Furthermore, we demonstrate RCI prompting's effectiveness in enhancing LLMs' reasoning abilities on a suite of natural language reasoning tasks, outperforming chain of thought (CoT) prompting with external feedback. We find that RCI combined with CoT performs better than either separately. Our code can be found here: https://github.com/posgnu/rci-agent.
Authors: Dongyeop Jang, Tae-Rim Yun, Choong-Yeol Lee, Young-Kyu Kwon, Chang-Eop Kim
Traditional Korean medicine (TKM) emphasizes individualized diagnosis and treatment. This uniqueness makes AI modeling difficult due to limited data and implicit processes. Large language models (LLMs) have demonstrated impressive medical inference, even without advanced training in medical texts. This study assessed the capabilities of GPT-4 in TKM, using the Korean National Licensing Examination for Korean Medicine Doctors (K-NLEKMD) as a benchmark. The K-NLEKMD, administered by a national organization, encompasses 12 major subjects in TKM. We optimized prompts with Chinese-term annotation, English translation for questions and instruction, exam-optimized instruction, and self-consistency. GPT-4 with optimized prompts achieved 66.18% accuracy, surpassing both the examination's average pass mark of 60% and the 40% minimum for each subject. The gradual introduction of language-related prompts and prompting techniques enhanced the accuracy from 51.82% to its maximum accuracy. GPT-4 showed low accuracy in subjects including public health & medicine-related law, internal medicine (2) which are localized in Korea and TKM. The model's accuracy was lower for questions requiring TKM-specialized knowledge. It exhibited higher accuracy in diagnosis-based and recall-based questions than in intervention-based questions. A positive correlation was observed between the consistency and accuracy of GPT-4's responses. This study unveils both the potential and challenges of applying LLMs to TKM. These findings underline the potential of LLMs like GPT-4 in culturally adapted medicine, especially TKM, for tasks such as clinical assistance, medical education, and research. But they also point towards the necessity for the development of methods to mitigate cultural bias inherent in large language models and validate their efficacy in real-world clinical settings.
Authors: Alexandr Sedykh, Maninadh Podapaka, Asel Sagingalieva, Karan Pinto, Markus Pflitsch, Alexey Melnikov
Finding the distribution of the velocities and pressures of a fluid (by solving the Navier-Stokes equations) is a principal task in the chemical, energy, and pharmaceutical industries, as well as in mechanical engineering and the design of pipeline systems. With existing solvers, such as OpenFOAM and Ansys, simulations of fluid dynamics in intricate geometries are computationally expensive and require re-simulation whenever the geometric parameters or the initial and boundary conditions are altered. Physics-informed neural networks are a promising tool for simulating fluid flows in complex geometries, as they can adapt to changes in the geometry and mesh definitions, allowing for generalization across different shapes. We present a hybrid quantum physics-informed neural network that simulates laminar fluid flows in 3D Y-shaped mixers. Our approach combines the expressive power of a quantum model with the flexibility of a physics-informed neural network, resulting in a 21% higher accuracy compared to a purely classical neural network. Our findings highlight the potential of machine learning approaches, and in particular hybrid quantum physics-informed neural network, for complex shape optimization tasks in computational fluid dynamics. By improving the accuracy of fluid simulations in complex geometries, our research using hybrid quantum models contributes to the development of more efficient and reliable fluid dynamics solvers.
Authors: Tucker Stewart, Katherine Stern, Grant O'Keefe, Ankur Teredesai, Juhua Hu
Sepsis is a syndrome that develops in the body in response to the presence of an infection. Characterized by severe organ dysfunction, sepsis is one of the leading causes of mortality in Intensive Care Units (ICUs) worldwide. These complications can be reduced through early application of antibiotics. Hence, the ability to anticipate the onset of sepsis early is crucial to the survival and well-being of patients. Current machine learning algorithms deployed inside medical infrastructures have demonstrated poor performance and are insufficient for anticipating sepsis onset early. Recently, deep learning methodologies have been proposed to predict sepsis, but some fail to capture the time of onset (e.g., classifying patients' entire visits as developing sepsis or not) and others are unrealistic for deployment in clinical settings (e.g., creating training instances using a fixed time to onset, where the time of onset needs to be known apriori). In this paper, we first propose a novel but realistic prediction framework that predicts each morning whether sepsis onset will occur within the next 24 hours using the most recent data collected the previous night, when patient-provider ratios are higher due to cross-coverage resulting in limited observation to each patient. However, as we increase the prediction rate into daily, the number of negative instances will increase, while that of positive instances remain the same. This causes a severe class imbalance problem making it hard to capture these rare sepsis cases. To address this, we propose a nightly profile representation learning (NPRL) approach. We prove that NPRL can theoretically alleviate the rare event problem and our empirical study using data from a level-1 trauma center demonstrates the effectiveness of our proposal.
Authors: Akihiro Fujii, Hideki Tsunashima, Yoshihiro Fukuhara, Koji Shimizu, Satoshi Watanabe
Deep-learning inverse techniques have attracted significant attention in recent years. Among them, the neural adjoint (NA) method, which employs a neural network surrogate simulator, has demonstrated impressive performance in the design tasks of artificial electromagnetic materials (AEM). However, the impact of the surrogate simulators' accuracy on the solutions in the NA method remains uncertain. Furthermore, achieving sufficient optimization becomes challenging in this method when the surrogate simulator is large, and computational resources are limited. Additionally, the behavior under constraints has not been studied, despite its importance from the engineering perspective. In this study, we investigated the impact of surrogate simulators' accuracy on the solutions and discovered that the more accurate the surrogate simulator is, the better the solutions become. We then developed an extension of the NA method, named Neural Lagrangian (NeuLag) method, capable of efficiently optimizing a sufficient number of solution candidates. We then demonstrated that the NeuLag method can find optimal solutions even when handling sufficient candidates is difficult due to the use of a large and accurate surrogate simulator. The resimulation errors of the NeuLag method were approximately 1/50 compared to previous methods for three AEM tasks. Finally, we performed optimization under constraint using NA and NeuLag, and confirmed their potential in optimization with soft or hard constraints. We believe our method holds potential in areas that require large and accurate surrogate simulators.
Authors: Kevin Vanslette
This article expands the framework of Bayesian inference and provides direct probabilistic methods for approaching inference tasks that are typically handled with information theory. We treat Bayesian probability updating as a random process and uncover intrinsic quantitative features of joint probability distributions called inferential moments. Inferential moments quantify shape information about how a prior distribution is expected to update in response to yet to be obtained information. Further, we quantify the unique probability distribution whose statistical moments are the inferential moments in question. We find a power series expansion of the mutual information in terms of inferential moments, which implies a connection between inferential theoretic logic and elements of information theory. Of particular interest is the inferential deviation, which is the expected variation of the probability of one variable in response to an inferential update of another. We explore two applications that analyze the inferential deviations of a Bayesian network to improve decision-making. We implement simple greedy algorithms for exploring sensor tasking using inferential deviations that generally outperform similar greedy mutual information algorithms in terms of root mean squared error between epistemic probability estimates and the ground truth probabilities they are estimating.
Authors: Hailan Ma, Zhenhong Sun, Daoyi Dong, Chunlin Chen, Herschel Rabitz
Quantum state tomography (QST) is the process of reconstructing the state of a quantum system (mathematically described as a density matrix) through a series of different measurements, which can be solved by learning a parameterized function to translate experimentally measured statistics into physical density matrices. However, the specific structure of quantum measurements for characterizing a quantum state has been neglected in previous work. In this paper, we explore the similarity between highly structured sentences in natural language and intrinsically structured measurements in QST. To fully leverage the intrinsic quantum characteristics involved in QST, we design a quantum-aware transformer (QAT) model to capture the complex relationship between measured frequencies and density matrices. In particular, we query quantum operators in the architecture to facilitate informative representations of quantum data and integrate the Bures distance into the loss function to evaluate quantum state fidelity, thereby enabling the reconstruction of quantum states from measured data with high fidelity. Extensive simulations and experiments (on IBM quantum computers) demonstrate the superiority of the QAT in reconstructing quantum states with favorable robustness against experimental noise.
Authors: Maximilian Mueller, Tiffany Vlaar, David Rolnick, Matthias Hein
Sharpness-aware minimization (SAM) was proposed to reduce sharpness of minima and has been shown to enhance generalization performance in various settings. In this work we show that perturbing only the affine normalization parameters (typically comprising 0.1% of the total parameters) in the adversarial step of SAM can outperform perturbing all of the parameters.This finding generalizes to different SAM variants and both ResNet (Batch Normalization) and Vision Transformer (Layer Normalization) architectures. We consider alternative sparse perturbation approaches and find that these do not achieve similar performance enhancement at such extreme sparsity levels, showing that this behaviour is unique to the normalization layers. Although our findings reaffirm the effectiveness of SAM in improving generalization performance, they cast doubt on whether this is solely caused by reduced sharpness.
Authors: Yifei Ming, Yixuan Li
Recent large vision-language models such as CLIP have shown remarkable out-of-distribution (OOD) detection and generalization performance. However, their zero-shot in-distribution (ID) accuracy is often limited for downstream datasets. Recent CLIP-based fine-tuning methods such as prompt learning have demonstrated significant improvements in ID classification and OOD generalization where OOD labels are available. Nonetheless, it remains unclear whether the model is reliable to semantic shifts without OOD labels. In this paper, we aim to bridge the gap and present a comprehensive study to understand how fine-tuning impact OOD detection for few-shot downstream tasks. By framing OOD detection as multi-modal concept matching, we establish a connection between fine-tuning methods and various OOD scores. Our results suggest that a proper choice of OOD scores is essential for CLIP-based fine-tuning. In particular, the maximum concept matching (MCM) score provides a promising solution consistently. We also show that prompt learning demonstrates the state-of-the-art OOD detection performance over the zero-shot counterpart.
Authors: Laura Manduchi, Moritz Vandenhirtz, Alain Ryser, Julia Vogt
We propose Tree Variational Autoencoder (TreeVAE), a new generative hierarchical clustering model that learns a flexible tree-based posterior distribution over latent variables. TreeVAE hierarchically divides samples according to their intrinsic characteristics, shedding light on hidden structures in the data. It adapts its architecture to discover the optimal tree for encoding dependencies between latent variables. The proposed tree-based generative architecture enables lightweight conditional inference and improves generative performance by utilizing specialized leaf decoders. We show that TreeVAE uncovers underlying clusters in the data and finds meaningful hierarchical relations between the different groups on a variety of datasets, including real-world imaging data. We present empirically that TreeVAE provides a more competitive log-likelihood lower bound than the sequential counterparts. Finally, due to its generative nature, TreeVAE is able to generate new samples from the discovered clusters via conditional sampling.
Authors: Ayush Tewari, Tianwei Yin, George Cazenavette, Semon Rezchikov, Joshua B. Tenenbaum, Frédo Durand, William T. Freeman, Vincent Sitzmann
Denoising diffusion models are a powerful type of generative models used to capture complex distributions of real-world signals. However, their applicability is limited to scenarios where training samples are readily available, which is not always the case in real-world applications. For example, in inverse graphics, the goal is to generate samples from a distribution of 3D scenes that align with a given image, but ground-truth 3D scenes are unavailable and only 2D images are accessible. To address this limitation, we propose a novel class of denoising diffusion probabilistic models that learn to sample from distributions of signals that are never directly observed. Instead, these signals are measured indirectly through a known differentiable forward model, which produces partial observations of the unknown signal. Our approach involves integrating the forward model directly into the denoising process. This integration effectively connects the generative modeling of observations with the generative modeling of the underlying signals, allowing for end-to-end training of a conditional generative model over signals. During inference, our approach enables sampling from the distribution of underlying signals that are consistent with a given partial observation. We demonstrate the effectiveness of our method on three challenging computer vision tasks. For instance, in the context of inverse graphics, our model enables direct sampling from the distribution of 3D scenes that align with a single 2D input image.
Authors: Xavier Suau, Federico Danieli, T. Anderson Keller, Arno Blaas, Chen Huang, Jason Ramapuram, Dan Busbridge, Luca Zappella
Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transformation-related information from the representations, which might harm performance for specific downstream tasks that require such information. We propose 2D strUctured and EquivarianT representations (coined DUET), which are 2d representations organized in a matrix structure, and equivariant with respect to transformations acting on the input data. DUET representations maintain information about an input transformation, while remaining semantically expressive. Compared to SimCLR (Chen et al., 2020) (unstructured and invariant) and ESSL (Dangovski et al., 2022) (unstructured and equivariant), the structured and equivariant nature of DUET representations enables controlled generation with lower reconstruction error, while controllability is not possible with SimCLR or ESSL. DUET also achieves higher accuracy for several discriminative tasks, and improves transfer learning.
Authors: Leander Girrbach, Anders Christensen, Ole Winther, Zeynep Akata, A. Sophia Koepke
Neural Persistence is a prominent measure for quantifying neural network complexity, proposed in the emerging field of topological data analysis in deep learning. In this work, however, we find both theoretically and empirically that the variance of network weights and spatial concentration of large weights are the main factors that impact neural persistence. Whilst this captures useful information for linear classifiers, we find that no relevant spatial structure is present in later layers of deep neural networks, making neural persistence roughly equivalent to the variance of weights. Additionally, the proposed averaging procedure across layers for deep neural networks does not consider interaction between layers. Based on our analysis, we propose an extension of the filtration underlying neural persistence to the whole neural network instead of single layers, which is equivalent to calculating neural persistence on one particular matrix. This yields our deep graph persistence measure, which implicitly incorporates persistent paths through the network and alleviates variance-related issues through standardisation. Code is available at https://github.com/ExplainableML/Deep-Graph-Persistence .
Authors: Samantha Chen, Yusu Wang
Learning distance functions between complex objects, such as the Wasserstein distance to compare point sets, is a common goal in machine learning applications. However, functions on such complex objects (e.g., point sets and graphs) are often required to be invariant to a wide variety of group actions e.g. permutation or rigid transformation. Therefore, continuous and symmetric product functions (such as distance functions) on such complex objects must also be invariant to the product of such group actions. We call these functions symmetric and factor-wise group invariant (or SFGI functions in short). In this paper, we first present a general neural network architecture for approximating SFGI functions. The main contribution of this paper combines this general neural network with a sketching idea to develop a specific and efficient neural network which can approximate the $p$-th Wasserstein distance between point sets. Very importantly, the required model complexity is independent of the sizes of input point sets. On the theoretical front, to the best of our knowledge, this is the first result showing that there exists a neural network with the capacity to approximate Wasserstein distance with bounded model complexity. Our work provides an interesting integration of sketching ideas for geometric problems with universal approximation of symmetric functions. On the empirical front, we present a range of results showing that our newly proposed neural network architecture performs comparatively or better than other models (including a SOTA Siamese Autoencoder based approach). In particular, our neural network generalizes significantly better and trains much faster than the SOTA Siamese AE. Finally, this line of investigation could be useful in exploring effective neural network design for solving a broad range of geometric optimization problems (e.g., $k$-means in a metric space).
Authors: Ningyuan Huang, Ron Levie, Soledad Villar
Graph neural networks (GNNs) are commonly described as being permutation equivariant with respect to node relabeling in the graph. This symmetry of GNNs is often compared to the translation equivariance of Euclidean convolution neural networks (CNNs). However, these two symmetries are fundamentally different: The translation equivariance of CNNs corresponds to symmetries of the fixed domain acting on the image signals (sometimes known as active symmetries), whereas in GNNs any permutation acts on both the graph signals and the graph domain (sometimes described as passive symmetries). In this work, we focus on the active symmetries of GNNs, by considering a learning setting where signals are supported on a fixed graph. In this case, the natural symmetries of GNNs are the automorphisms of the graph. Since real-world graphs tend to be asymmetric, we relax the notion of symmetries by formalizing approximate symmetries via graph coarsening. We present a bias-variance formula that quantifies the tradeoff between the loss in expressivity and the gain in the regularity of the learned estimator, depending on the chosen symmetry group. To illustrate our approach, we conduct extensive experiments on image inpainting, traffic flow prediction, and human pose estimation with different choices of symmetries. We show theoretically and empirically that the best generalization performance can be achieved by choosing a suitably larger group than the graph automorphism, but smaller than the permutation group.
Authors: Sebastian Mizera
Recent advances in machine learning establish the ability of certain neural-network architectures called neural operators to approximate maps between function spaces. Motivated by a prospect of employing them in fundamental physics, we examine applications to scattering processes in quantum mechanics. We use an iterated variant of Fourier neural operators to learn the physics of Schr\"odinger operators, which map from the space of initial wave functions and potentials to the final wave functions. These deep operator learning ideas are put to test in two concrete problems: a neural operator predicting the time evolution of a wave packet scattering off a central potential in $1+1$ dimensions, and the double-slit experiment in $2+1$ dimensions. At inference, neural operators can become orders of magnitude more efficient compared to traditional finite-difference solvers.
Authors: Ali Bouland, Shengyuan Niu, Sai Tej Paruchuri, Andrew Kurdila, John Burns, Eugenio Schuster
This paper studies convergence rates for some value function approximations that arise in a collection of reproducing kernel Hilbert spaces (RKHS) $H(\Omega)$. By casting an optimal control problem in a specific class of native spaces, strong rates of convergence are derived for the operator equation that enables offline approximations that appear in policy iteration. Explicit upper bounds on error in value function and controller approximations are derived in terms of power function $\mathcal{P}_{H,N}$ for the space of finite dimensional approximants $H_N$ in the native space $H(\Omega)$. These bounds are geometric in nature and refine some well-known, now classical results concerning convergence of approximations of value functions.
Authors: Shengbo Wang, Shuo Gao, Chenyu Tang, Edoardo Occhipinti, Cong Li, Shurui Wang, Jiaqi Wang, Hubin Zhao, Guohua Hu, Arokia Nathan, Ravinder Dahiya, Luigi Occhipinti
Efficient operation of intelligent machines in the real world requires methods that allow them to understand and predict the uncertainties presented by the unstructured environments with good accuracy, scalability and generalization, similar to humans. Current methods rely on pretrained networks instead of continuously learning from the dynamic signal properties of working environments and suffer inherent limitations, such as data-hungry procedures, and limited generalization capabilities. Herein, we present a memristor-based differential neuromorphic computing, perceptual signal processing and learning method for intelligent machines. The main features of environmental information such as amplification (>720%) and adaptation (<50%) of mechanical stimuli encoded in memristors, are extracted to obtain human-like processing in unstructured environments. The developed method takes advantage of the intrinsic multi-state property of memristors and exhibits good scalability and generalization, as confirmed by validation in two different application scenarios: object grasping and autonomous driving. In the former, a robot hand experimentally realizes safe and stable grasping through fast learning (in ~1 ms) the unknown object features (e.g., sharp corner and smooth surface) with a single memristor. In the latter, the decision-making information of 10 unstructured environments in autonomous driving (e.g., overtaking cars, pedestrians) is accurately (94%) extracted with a 40*25 memristor array. By mimicking the intrinsic nature of human low-level perception mechanisms, the electronic memristive neuromorphic circuit-based method, presented here shows the potential for adapting to diverse sensing technologies and helping intelligent machines generate smart high-level decisions in the real world.
Authors: Yen-Jen Wang, Bike Zhang, Jianyu Chen, Koushil Sreenath
Large language models (LLMs) pre-trained on vast internet-scale data have showcased remarkable capabilities across diverse domains. Recently, there has been escalating interest in deploying LLMs for robotics, aiming to harness the power of foundation models in real-world settings. However, this approach faces significant challenges, particularly in grounding these models in the physical world and in generating dynamic robot motions. To address these issues, we introduce a novel paradigm in which we use few-shot prompts collected from the physical environment, enabling the LLM to autoregressively generate low-level control commands for robots without task-specific fine-tuning. Experiments across various robots and environments validate that our method can effectively prompt a robot to walk. We thus illustrate how LLMs can proficiently function as low-level feedback controllers for dynamic motion control even in high-dimensional robotic systems. The project website and source code can be found at: https://prompt2walk.github.io/ .
Authors: Zenan Li, Fan Nie, Qiao Sun, Fang Da, Hang Zhao
Offline Reinforcement Learning (RL) has emerged as a promising framework for learning policies without active interactions, making it especially appealing for autonomous driving tasks. Recent successes of Transformers inspire casting offline RL as sequence modeling, which performs well in long-horizon tasks. However, they are overly optimistic in stochastic environments with incorrect assumptions that the same goal can be consistently achieved by identical actions. In this paper, we introduce an UNcertainty-awaRE deciSion Transformer (UNREST) for planning in stochastic driving environments without introducing additional transition or complex generative models. Specifically, UNREST estimates state uncertainties by the conditional mutual information between transitions and returns, and segments sequences accordingly. Discovering the `uncertainty accumulation' and `temporal locality' properties of driving environments, UNREST replaces the global returns in decision transformers with less uncertain truncated returns, to learn from true outcomes of agent actions rather than environment transitions. We also dynamically evaluate environmental uncertainty during inference for cautious planning. Extensive experimental results demonstrate UNREST's superior performance in various driving scenarios and the power of our uncertainty estimation strategy.
Authors: Luca Ambrogioni
Uncovering the mechanisms behind long-term memory is one of the most fascinating open problems in neuroscience and artificial intelligence. Artificial associative memory networks have been used to formalize important aspects of biological memory. Generative diffusion models are a type of generative machine learning techniques that have shown great performance in many tasks. Like associative memory systems, these networks define a dynamical system that converges to a set of target states. In this work we show that generative diffusion models can be interpreted as energy-based models and that, when trained on discrete patterns, their energy function is (asymptotically) identical to that of modern Hopfield networks. This equivalence allows us to interpret the supervised training of diffusion models as a synaptic learning process that encodes the associative dynamics of a modern Hopfield network in the weight structure of a deep neural network. Leveraging this connection, we formulate a generalized framework for understanding the formation of long-term memory, where creative generation and memory recall can be seen as parts of a unified continuum.
Authors: Md Mahbubur Rahman, Ira Ceka, Chengzhi Mao, Saikat Chakraborty, Baishakhi Ray, Wei Le
Deep learning vulnerability detection has shown promising results in recent years. However, an important challenge that still blocks it from being very useful in practice is that the model is not robust under perturbation and it cannot generalize well over the out-of-distribution (OOD) data, e.g., applying a trained model to unseen projects in real world. We hypothesize that this is because the model learned non-robust features, e.g., variable names, that have spurious correlations with labels. When the perturbed and OOD datasets no longer have the same spurious features, the model prediction fails. To address the challenge, in this paper, we introduced causality into deep learning vulnerability detection. Our approach CausalVul consists of two phases. First, we designed novel perturbations to discover spurious features that the model may use to make predictions. Second, we applied the causal learning algorithms, specifically, do-calculus, on top of existing deep learning models to systematically remove the use of spurious features and thus promote causal based prediction. Our results show that CausalVul consistently improved the model accuracy, robustness and OOD performance for all the state-of-the-art models and datasets we experimented. To the best of our knowledge, this is the first work that introduces do calculus based causal learning to software engineering models and shows it's indeed useful for improving the model accuracy, robustness and generalization. Our replication package is located at https://figshare.com/s/0ffda320dcb96c249ef2.
Authors: Zhenyu Tao, Wei Xu, Xiaohu You
The proliferation of diverse wireless services in 5G and beyond has led to the emergence of network slicing technologies. Among these, admission control plays a crucial role in achieving service-oriented optimization goals through the selective acceptance of service requests. Although deep reinforcement learning (DRL) forms the foundation in many admission control approaches thanks to its effectiveness and flexibility, initial instability with excessive convergence delay of DRL models hinders their deployment in real-world networks. We propose a digital twin (DT) accelerated DRL solution to address this issue. Specifically, we first formulate the admission decision-making process as a semi-Markov decision process, which is subsequently simplified into an equivalent discrete-time Markov decision process to facilitate the implementation of DRL methods. A neural network-based DT is established with a customized output layer for queuing systems, trained through supervised learning, and then employed to assist the training phase of the DRL model. Extensive simulations show that the DT-accelerated DRL improves resource utilization by over 40% compared to the directly trained state-of-the-art dueling deep Q-learning model. This improvement is achieved while preserving the model's capability to optimize the long-term rewards of the admission process.
Authors: Yangruibo Ding, Zijian Wang, Wasi Uddin Ahmad, Hantian Ding, Ming Tan, Nihal Jain, Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, Bing Xiang
Code completion models have made significant progress in recent years, yet current popular evaluation datasets, such as HumanEval and MBPP, predominantly focus on code completion tasks within a single file. This over-simplified setting falls short of representing the real-world software development scenario where repositories span multiple files with numerous cross-file dependencies, and accessing and understanding cross-file context is often required to complete the code correctly.
To fill in this gap, we propose CrossCodeEval, a diverse and multilingual code completion benchmark that necessitates an in-depth cross-file contextual understanding to complete the code accurately. CrossCodeEval is built on a diverse set of real-world, open-sourced, permissively-licensed repositories in four popular programming languages: Python, Java, TypeScript, and C#. To create examples that strictly require cross-file context for accurate completion, we propose a straightforward yet efficient static-analysis-based approach to pinpoint the use of cross-file context within the current file.
Extensive experiments on state-of-the-art code language models like CodeGen and StarCoder demonstrate that CrossCodeEval is extremely challenging when the relevant cross-file context is absent, and we see clear improvements when adding these context into the prompt. However, despite such improvements, the pinnacle of performance remains notably unattained even with the highest-performing model, indicating that CrossCodeEval is also capable of assessing model's capability in leveraging extensive context to make better code completion. Finally, we benchmarked various methods in retrieving cross-file context, and show that CrossCodeEval can also be used to measure the capability of code retrievers.
Authors: Lucca Portes Cavalheiro, Simon Bernard, Jean Paul Barddal, Laurent Heutte
High dimension, low sample size (HDLSS) problems are numerous among real-world applications of machine learning. From medical images to text processing, traditional machine learning algorithms are usually unsuccessful in learning the best possible concept from such data. In a previous work, we proposed a dissimilarity-based approach for multi-view classification, the Random Forest Dissimilarity (RFD), that perfoms state-of-the-art results for such problems. In this work, we transpose the core principle of this approach to solving HDLSS classification problems, by using the RF similarity measure as a learned precomputed SVM kernel (RFSVM). We show that such a learned similarity measure is particularly suited and accurate for this classification context. Experiments conducted on 40 public HDLSS classification datasets, supported by rigorous statistical analyses, show that the RFSVM method outperforms existing methods for the majority of HDLSS problems and remains at the same time very competitive for low or non-HDLSS problems.
Authors: Patrick Holzer, Tania Jacob, Shubham Kavane
Federated clustering, an integral aspect of federated machine learning, enables multiple data sources to collaboratively cluster their data, maintaining decentralization and preserving privacy. In this paper, we introduce a novel federated clustering algorithm named Dynamically Weighted Federated k-means (DWF k-means) based on Lloyd's method for k-means clustering, to address the challenges associated with distributed data sources and heterogeneous data. Our proposed algorithm combines the benefits of traditional clustering techniques with the privacy and scalability benefits offered by federated learning. The algorithm facilitates collaborative clustering among multiple data owners, allowing them to cluster their local data collectively while exchanging minimal information with the central coordinator. The algorithm optimizes the clustering process by adaptively aggregating cluster assignments and centroids from each data source, thereby learning a global clustering solution that reflects the collective knowledge of the entire federated network. We address the issue of empty clusters, which commonly arises in the context of federated clustering. We conduct experiments on multiple datasets and data distribution settings to evaluate the performance of our algorithm in terms of clustering score, accuracy, and v-measure. The results demonstrate that our approach can match the performance of the centralized classical k-means baseline, and outperform existing federated clustering methods like k-FED in realistic scenarios.
Authors: Namjoon Suh, Xiaofeng Lin, Din-Yin Hsieh, Merhdad Honarkhah, Guang Cheng
Diffusion model has become a main paradigm for synthetic data generation in many subfields of modern machine learning, including computer vision, language model, or speech synthesis. In this paper, we leverage the power of diffusion model for generating synthetic tabular data. The heterogeneous features in tabular data have been main obstacles in tabular data synthesis, and we tackle this problem by employing the auto-encoder architecture. When compared with the state-of-the-art tabular synthesizers, the resulting synthetic tables from our model show nice statistical fidelities to the real data, and perform well in downstream tasks for machine learning utilities. We conducted the experiments over $15$ publicly available datasets. Notably, our model adeptly captures the correlations among features, which has been a long-standing challenge in tabular data synthesis. Our code is available at https://github.com/UCLA-Trustworthy-AI-Lab/AutoDiffusion.
Authors: Ryan Rezai, Jason Wang
Closed drafting or "pick and pass" is a popular game mechanic where each round players select a card or other playable element from their hand and pass the rest to the next player. In this paper, we establish first-principle methods for studying the interpretability, generalizability, and memory of Deep Q-Network (DQN) models playing closed drafting games. In particular, we use a popular family of closed drafting games called "Sushi Go Party", in which we achieve state-of-the-art performance. We fit decision rules to interpret the decision-making strategy of trained DRL agents by comparing them to the ranking preferences of different types of human players. As Sushi Go Party can be expressed as a set of closely-related games based on the set of cards in play, we quantify the generalizability of DRL models trained on various sets of cards, establishing a method to benchmark agent performance as a function of environment unfamiliarity. Using the explicitly calculable memory of other player's hands in closed drafting games, we create measures of the ability of DRL models to learn memory.
Authors: Shahin Doroudian, Zekun Wu, Aidong Lu
The understanding of visual analytics process can benefit visualization researchers from multiple aspects, including improving visual designs and developing advanced interaction functions. However, the log files of user behaviors are still hard to analyze due to the complexity of sensemaking and our lack of knowledge on the related user behaviors. This work presents a study on a comprehensive data collection of user behaviors, and our analysis approach with time-series classification methods. We have chosen a classical visualization application, Covid-19 data analysis, with common analysis tasks covering geo-spatial, time-series and multi-attributes. Our user study collects user behaviors on a diverse set of visualization tasks with two comparable systems, desktop and immersive visualizations. We summarize the classification results with three time-series machine learning algorithms at two scales, and explore the influences of behavior features. Our results reveal that user behaviors can be distinguished during the process of visual analytics and there is a potentially strong association between the physical behaviors of users and the visualization tasks they perform. We also demonstrate the usage of our models by interpreting open sessions of visual analytics, which provides an automatic way to study sensemaking without tedious manual annotations.
Authors: Alessandro Scagliotti, Sara Farinelli
The term "Normalizing Flows" is related to the task of constructing invertible transport maps between probability measures by means of deep neural networks. In this paper, we consider the problem of recovering the $W_2$-optimal transport map $T$ between absolutely continuous measures $\mu,\nu\in\mathcal{P}(\mathbb{R}^n)$ as the flow of a linear-control neural ODE. We first show that, under suitable assumptions on $\mu,\nu$ and on the controlled vector fields, the optimal transport map is contained in the $C^0_c$-closure of the flows generated by the system. Assuming that discrete approximations $\mu_N,\nu_N$ of the original measures $\mu,\nu$ are available, we use a discrete optimal coupling $\gamma_N$ to define an optimal control problem. With a $\Gamma$-convergence argument, we prove that its solutions correspond to flows that approximate the optimal transport map $T$. Finally, taking advantage of the Pontryagin Maximum Principle, we propose an iterative numerical scheme for the resolution of the optimal control problem, resulting in an algorithm for the practical computation of the approximated optimal transport map.
Authors: Weikang Wan, Yifeng Zhu, Rutav Shah, Yuke Zhu
We introduce LOTUS, a continual imitation learning algorithm that empowers a physical robot to continuously and efficiently learn to solve new manipulation tasks throughout its lifespan. The core idea behind LOTUS is constructing an ever-growing skill library from a sequence of new tasks with a small number of human demonstrations. LOTUS starts with a continual skill discovery process using an open-vocabulary vision model, which extracts skills as recurring patterns presented in unsegmented demonstrations. Continual skill discovery updates existing skills to avoid catastrophic forgetting of previous tasks and adds new skills to solve novel tasks. LOTUS trains a meta-controller that flexibly composes various skills to tackle vision-based manipulation tasks in the lifelong learning process. Our comprehensive experiments show that LOTUS outperforms state-of-the-art baselines by over 11% in success rate, showing its superior knowledge transfer ability compared to prior methods. More results and videos can be found on the project website: https://ut-austin-rpl.github.io/Lotus/.
Authors: Ethan Pronovost, Meghana Reddy Ganesina, Noureldin Hendy, Zeyu Wang, Andres Morales, Kai Wang, Nicholas Roy
Automated creation of synthetic traffic scenarios is a key part of validating the safety of autonomous vehicles (AVs). In this paper, we propose Scenario Diffusion, a novel diffusion-based architecture for generating traffic scenarios that enables controllable scenario generation. We combine latent diffusion, object detection and trajectory regression to generate distributions of synthetic agent poses, orientations and trajectories simultaneously. To provide additional control over the generated scenario, this distribution is conditioned on a map and sets of tokens describing the desired scenario. We show that our approach has sufficient expressive capacity to model diverse traffic patterns and generalizes to different geographical regions.
Authors: Zhipeng Yao, Guisong Chang, Jiaqi Zhang, Qi Zhang, Yu Zhang, Dazhou Li
In the field of deep learning, Stochastic Gradient Descent (SGD) and its momentum-based variants are the predominant choices for optimization algorithms. Despite all that, these momentum strategies, which accumulate historical gradients by using a fixed $\beta$ hyperparameter to smooth the optimization processing, often neglect the potential impact of the variance of historical gradients on the current gradient estimation. In the gradient variance during training, fluctuation indicates the objective function does not meet the Lipschitz continuity condition at all time, which raises the troublesome optimization problem. This paper aims to explore the potential benefits of reducing the variance of historical gradients to make optimizer converge to flat solutions. Moreover, we proposed a new optimization method based on reducing the variance. We employed the Wiener filter theory to enhance the first moment estimation of SGD, notably introducing an adaptive weight to optimizer. Specifically, the adaptive weight dynamically changes along with temporal fluctuation of gradient variance during deep learning model training. Experimental results demonstrated our proposed adaptive weight optimizer, SGDF (Stochastic Gradient Descent With Filter), can achieve satisfactory performance compared with state-of-the-art optimizers.
Authors: Derek Lilienthal, Paul Mello, Magdalini Eirinaki, Stas Tiomkin
While recommender systems have become an integral component of the Web experience, their heavy reliance on user data raises privacy and security concerns. Substituting user data with synthetic data can address these concerns, but accurately replicating these real-world datasets has been a notoriously challenging problem. Recent advancements in generative AI have demonstrated the impressive capabilities of diffusion models in generating realistic data across various domains. In this work we introduce a Score-based Diffusion Recommendation Module (SDRM), which captures the intricate patterns of real-world datasets required for training highly accurate recommender systems. SDRM allows for the generation of synthetic data that can replace existing datasets to preserve user privacy, or augment existing datasets to address excessive data sparsity. Our method outperforms competing baselines such as generative adversarial networks, variational autoencoders, and recently proposed diffusion models in synthesizing various datasets to replace or augment the original data by an average improvement of 4.30% in Recall@$k$ and 4.65% in NDCG@$k$.
Authors: Jing Hu, Qinrui Fan, Shu Hu, Siwei Lyu, Xi Wu, Xin Wang
In the field of clinical medicine, computed tomography (CT) is an effective medical imaging modality for the diagnosis of various pathologies. Compared with X-ray images, CT images can provide more information, including multi-planar slices and three-dimensional structures for clinical diagnosis. However, CT imaging requires patients to be exposed to large doses of ionizing radiation for a long time, which may cause irreversible physical harm. In this paper, we propose an Uncertainty-aware MedNeRF (UMedNeRF) network based on generated radiation fields. The network can learn a continuous representation of CT projections from 2D X-ray images by obtaining the internal structure and depth information and using adaptive loss weights to ensure the quality of the generated images. Our model is trained on publicly available knee and chest datasets, and we show the results of CT projection rendering with a single X-ray and compare our method with other methods based on generated radiation fields.
Authors: Shahriar Golchin, Mihai Surdeanu
We propose the Data Contamination Quiz, a simple and effective approach to detect data contamination in large language models (LLMs) and estimate the amount of it. Specifically, we frame data contamination detection as a series of multiple-choice questions. We devise a quiz format wherein three perturbed versions of each dataset instance are created. These changes only include word-level perturbations, replacing words with their contextual synonyms, ensuring both the semantic and sentence structure remain exactly the same as the original instance. Together with the original instance, these perturbed versions constitute the choices in the quiz. Given that the only distinguishing signal among these choices is the exact wording, an LLM, when tasked with identifying the original instance from the choices, opts for the original if it has memorized it in its pre-training phase--a trait intrinsic to LLMs. A dataset partition is then marked as contaminated if the LLM's performance on the quiz surpasses what random chance suggests. Our evaluation spans seven datasets and their respective splits (train and test/validation) on two state-of-the-art LLMs: GPT-4 and GPT-3.5. While lacking access to the pre-training data, our results suggest that our approach not only enhances the detection of data contamination but also provides an accurate estimation of its extent, even when the contamination signal is weak.
Authors: Sheng Liu, Lei Xing, James Zou
Large language models (LLMs) demonstrate emergent in-context learning capabilities, where they adapt to new tasks based on example demonstrations. However, in-context learning has seen limited effectiveness in many settings, is difficult to quantitatively control and takes up context window space. To overcome these limitations, we propose an alternative approach that recasts in-context learning as in-context vectors (ICV). Using ICV has two steps. We first use a forward pass on demonstration examples to create the in-context vector from the latent embedding of the LLM. This vector captures essential information about the intended task. On a new query, instead of adding demonstrations to the prompt, we shift the latent states of the LLM using the ICV. The ICV approach has several benefits: 1) it enables the LLM to more effectively follow the demonstration examples; 2) it's easy to control by adjusting the magnitude of the ICV; 3) it reduces the length of the prompt by removing the in-context demonstrations; 4) ICV is computationally much more efficient than fine-tuning. We demonstrate that ICV achieves better performance compared to standard in-context learning and fine-tuning on diverse tasks including safety, style transfer, role-playing and formatting. Moreover, we show that we can flexibly teach LLM to simultaneously follow different types of instructions by simple vector arithmetics on the corresponding ICVs.
Authors: Cécile Trottet, Manuel Schürch, Ahmed Allam, Imon Barua, Liubov Petelytska, Oliver Distler, Anna-Maria Hoffmann-Vold, Michael Krauthammer, the EUSTAR collaborators
In this paper, we propose a deep generative time series approach using latent temporal processes for modeling and holistically analyzing complex disease trajectories. We aim to find meaningful temporal latent representations of an underlying generative process that explain the observed disease trajectories in an interpretable and comprehensive way. To enhance the interpretability of these latent temporal processes, we develop a semi-supervised approach for disentangling the latent space using established medical concepts. By combining the generative approach with medical knowledge, we leverage the ability to discover novel aspects of the disease while integrating medical concepts into the model. We show that the learned temporal latent processes can be utilized for further data analysis and clinical hypothesis testing, including finding similar patients and clustering the disease into new sub-types. Moreover, our method enables personalized online monitoring and prediction of multivariate time series including uncertainty quantification. We demonstrate the effectiveness of our approach in modeling systemic sclerosis, showcasing the potential of our machine learning model to capture complex disease trajectories and acquire new medical knowledge.
Authors: Thinh Viet Le, Vassilis Kekatos
Variational quantum approaches have shown great promise in finding near-optimal solutions to computationally challenging tasks. Nonetheless, enforcing constraints in a disciplined fashion has been largely unexplored. To address this gap, this work proposes a hybrid quantum-classical algorithmic paradigm termed VQEC that extends the celebrated VQE to handle optimization with constraints. As with the standard VQE, the vector of optimization variables is captured by the state of a variational quantum circuit (VQC). To deal with constraints, VQEC optimizes a Lagrangian function classically over both the VQC parameters as well as the dual variables associated with constraints. To comply with the quantum setup, variables are updated via a perturbed primal-dual method leveraging the parameter shift rule. Among a wide gamut of potential applications, we showcase how VQEC can approximately solve quadratically-constrained binary optimization (QCBO) problems, find stochastic binary policies satisfying quadratic constraints on the average and in probability, and solve large-scale linear programs (LP) over the probability simplex. Under an assumption on the error for the VQC to approximate an arbitrary probability mass function (PMF), we provide bounds on the optimality gap attained by a VQC. Numerical tests on a quantum simulator investigate the effect of various parameters and corroborate that VQEC can generate high-quality solutions.
Authors: Vivek Shankar, Xiaoli Yang, Vrishab Krishna, Brent Tan, Oscar Silva, Rebecca Rojansky, Andrew Ng, Fabiola Valvert, Edward Briercheck, David Weinstock, Yasodha Natkunam, Sebastian Fernandez-Pol, Pranav Rajpurkar
The accurate classification of lymphoma subtypes using hematoxylin and eosin (H&E)-stained tissue is complicated by the wide range of morphological features these cancers can exhibit. We present LymphoML - an interpretable machine learning method that identifies morphologic features that correlate with lymphoma subtypes. Our method applies steps to process H&E-stained tissue microarray cores, segment nuclei and cells, compute features encompassing morphology, texture, and architecture, and train gradient-boosted models to make diagnostic predictions. LymphoML's interpretable models, developed on a limited volume of H&E-stained tissue, achieve non-inferior diagnostic accuracy to pathologists using whole-slide images and outperform black box deep-learning on a dataset of 670 cases from Guatemala spanning 8 lymphoma subtypes. Using SHapley Additive exPlanation (SHAP) analysis, we assess the impact of each feature on model prediction and find that nuclear shape features are most discriminative for DLBCL (F1-score: 78.7%) and classical Hodgkin lymphoma (F1-score: 74.5%). Finally, we provide the first demonstration that a model combining features from H&E-stained tissue with features from a standardized panel of 6 immunostains results in a similar diagnostic accuracy (85.3%) to a 46-stain panel (86.1%).
Authors: Hanpeng Hu, Junwei Su, Juntao Zhao, Yanghua Peng, Yibo Zhu, Haibin Lin, Chuan Wu
Deep Neural Networks (DNNs) have shown excellent performance in a wide range of machine learning applications. Knowing the latency of running a DNN model or tensor program on a specific device is useful in various tasks, such as DNN graph- or tensor-level optimization and device selection. Considering the large space of DNN models and devices that impede direct profiling of all combinations, recent efforts focus on building a predictor to model the performance of DNN models on different devices. However, none of the existing attempts have achieved a cost model that can accurately predict the performance of various tensor programs while supporting both training and inference accelerators. We propose CDMPP, an efficient tensor program latency prediction framework for both cross-model and cross-device prediction. We design an informative but efficient representation of tensor programs, called compact ASTs, and a pre-order-based positional encoding method, to capture the internal structure of tensor programs. We develop a domain-adaption-inspired method to learn domain-invariant representations and devise a KMeans-based sampling algorithm, for the predictor to learn from different domains (i.e., different DNN operators and devices). Our extensive experiments on a diverse range of DNN models and devices demonstrate that CDMPP significantly outperforms state-of-the-art baselines with 14.03% and 10.85% prediction error for cross-model and cross-device prediction, respectively, and one order of magnitude higher training efficiency. The implementation and the expanded dataset are available at https://github.com/joapolarbear/cdmpp.
Authors: Romain Ilbert, Thai V. Hoang, Zonghua Zhang, Themis Palpanas
Balancing the trade-off between accuracy and robustness is a long-standing challenge in time series forecasting. While most of existing robust algorithms have achieved certain suboptimal performance on clean data, sustaining the same performance level in the presence of data perturbations remains extremely hard. In this paper, we study a wide array of perturbation scenarios and propose novel defense mechanisms against adversarial attacks using real-world telecom data. We compare our strategy against two existing adversarial training algorithms under a range of maximal allowed perturbations, defined using $\ell_{\infty}$-norm, $\in [0.1,0.4]$. Our findings reveal that our hybrid strategy, which is composed of a classifier to detect adversarial examples, a denoiser to eliminate noise from the perturbed data samples, and a standard forecaster, achieves the best performance on both clean and perturbed data. Our optimal model can retain up to $92.02\%$ the performance of the original forecasting model in terms of Mean Squared Error (MSE) on clean data, while being more robust than the standard adversarially trained models on perturbed data. Its MSE is 2.71$\times$ and 2.51$\times$ lower than those of comparing methods on normal and perturbed data, respectively. In addition, the components of our models can be trained in parallel, resulting in better computational efficiency. Our results indicate that we can optimally balance the trade-off between the performance and robustness of forecasting models by improving the classifier and denoiser, even in the presence of sophisticated and destructive poisoning attacks.
Authors: Jaykumar Kasundra, Claudia Schulz, Melicaalsadat Mirsafian, Stavroula Skylaki
In the Machine Learning (ML) model development lifecycle, training candidate models using an offline holdout dataset and identifying the best model for the given task is only the first step. After the deployment of the selected model, continuous model monitoring and model retraining is required in many real-world applications. There are multiple reasons for retraining, including data or concept drift, which may be reflected on the model performance as monitored by an appropriate metric. Another motivation for retraining is the acquisition of increasing amounts of data over time, which may be used to retrain and improve the model performance even in the absence of drifts. We examine the impact of various retraining decision points on crucial factors, such as model performance and resource utilization, in the context of Multilabel Classification models. We explain our key decision points and propose a reference framework for designing an effective model retraining strategy.
Authors: Alexander Rutherford, Benjamin Ellis, Matteo Gallici, Jonathan Cook, Andrei Lupu, Gardar Ingvarsson, Timon Willi, Akbir Khan, Christian Schroeder de Witt, Alexandra Souly, Saptarashmi Bandyopadhyay, Mikayel Samvelyan, Minqi Jiang, Robert Tjarko Lange, Shimon Whiteson, Bruno Lacerda, Nick Hawes, Tim Rocktaschel, Chris Lu, Jakob Nicolaus Foerster
Benchmarks play an important role in the development of machine learning algorithms. For example, research in reinforcement learning (RL) has been heavily influenced by available environments and benchmarks. However, RL environments are traditionally run on the CPU, limiting their scalability with typical academic compute. Recent advancements in JAX have enabled the wider use of hardware acceleration to overcome these computational hurdles, enabling massively parallel RL training pipelines and environments. This is particularly useful for multi-agent reinforcement learning (MARL) research. First of all, multiple agents must be considered at each environment step, adding computational burden, and secondly, the sample complexity is increased due to non-stationarity, decentralised partial observability, or other MARL challenges. In this paper, we present JaxMARL, the first open-source code base that combines ease-of-use with GPU enabled efficiency, and supports a large number of commonly used MARL environments as well as popular baseline algorithms. When considering wall clock time, our experiments show that per-run our JAX-based training pipeline is up to 12500x faster than existing approaches. This enables efficient and thorough evaluations, with the potential to alleviate the evaluation crisis of the field. We also introduce and benchmark SMAX, a vectorised, simplified version of the popular StarCraft Multi-Agent Challenge, which removes the need to run the StarCraft II game engine. This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL. We provide code at https://github.com/flairox/jaxmarl.
Authors: Brian Moser, Federico Raue, Jörn Hees, Andreas Dengel
Neural Architecture Search (NAS) defines the design of Neural Networks as a search problem. Unfortunately, NAS is computationally intensive because of various possibilities depending on the number of elements in the design and the possible connections between them. In this work, we extensively analyze the role of the dataset size based on several sampling approaches for reducing the dataset size (unsupervised and supervised cases) as an agnostic approach to reduce search time. We compared these techniques with four common NAS approaches in NAS-Bench-201 in roughly 1,400 experiments on CIFAR-100. One of our surprising findings is that in most cases we can reduce the amount of training data to 25\%, consequently reducing search time to 25\%, while at the same time maintaining the same accuracy as if training on the full dataset. Additionally, some designs derived from subsets out-perform designs derived from the full dataset by up to 22 p.p. accuracy.
Authors: SayedHassan Khatoonabadi, Diego Elias Costa, Suhaib Mujahid, Emad Shihab
Pull Requests (PRs) that are neither progressed nor resolved clutter the list of PRs, making it difficult for the maintainers to manage and prioritize unresolved PRs. To automatically track, follow up, and close such inactive PRs, Stale bot was introduced by GitHub. Despite its increasing adoption, there are ongoing debates on whether using Stale bot alleviates or exacerbates the problem of inactive PRs. To better understand if and how Stale bot helps projects in their pull-based development workflow, we perform an empirical study of 20 large and popular open-source projects. We find that Stale bot can help deal with a backlog of unresolved PRs as the projects closed more PRs within the first few months of adoption. Moreover, Stale bot can help improve the efficiency of the PR review process as the projects reviewed PRs that ended up merged and resolved PRs that ended up closed faster after the adoption. However, Stale bot can also negatively affect the contributors as the projects experienced a considerable decrease in their number of active contributors after the adoption. Therefore, relying solely on Stale bot to deal with inactive PRs may lead to decreased community engagement and an increased probability of contributor abandonment.