Authors: Rongxiang Wang, Felix Lin
Contemporary Speech Understanding (SU) involves a sophisticated pipeline: capturing real-time voice input, the pipeline encompasses a deep neural network with an encoder-decoder architecture enhanced by beam search. This network periodically assesses attention and Connectionist Temporal Classification (CTC) scores in its autoregressive output.
This paper aims to enhance SU performance on edge devices with limited resources. It pursues two intertwined goals: accelerating on-device execution and efficiently handling inputs that surpass the on-device model's capacity. While these objectives are well-established, we introduce innovative solutions that specifically address SU's distinctive challenges: 1. Late contextualization: Enables the parallel execution of a model's attentive encoder during input ingestion. 2. Pilot decoding: Alleviates temporal load imbalances. 3. Autoregression offramps: Facilitate offloading decisions based on partial output sequences.
Our techniques seamlessly integrate with existing SU models, pipelines, and frameworks, allowing for independent or combined application. Together, they constitute a hybrid solution for edge SU, exemplified by our prototype, XYZ. Evaluated on platforms equipped with 6-8 Arm cores, our system achieves State-of-the-Art (SOTA) accuracy, reducing end-to-end latency by 2x and halving offloading requirements.
Authors: Takiah Ebbs-Picken, David A. Romero, Carlos M. Da Silva, Cristina H. Amon
Conjugate heat transfer (CHT) models are vital for the design of many engineering systems. However, high-fidelity CHT models are computationally intensive, which limits their use in applications such as design optimization, where hundreds to thousands of model evaluations are required. In this work, we develop a modular deep convolutional encoder-decoder hierarchical (DeepEDH) neural network, a novel deep-learning-based surrogate modeling methodology for computationally intensive CHT models. Leveraging convective temperature dependencies, we propose a two-stage temperature prediction architecture that couples velocity and temperature models. The proposed DeepEDH methodology is demonstrated by modeling the pressure, velocity, and temperature fields for a liquid-cooled cold-plate-based battery thermal management system with variable channel geometry. A computational model of the cold plate is developed and solved using the finite element method (FEM), generating a dataset of 1,500 simulations. The FEM results are transformed and scaled from unstructured to structured, image-like meshes to create training and test datasets. The DeepEDH methodology's performance is examined in relation to data scaling, training dataset size, and network depth. Our performance analysis covers the impact of the novel architecture, separate field models, output geometry masks, multi-stage temperature models, and optimizations of the hyperparameters and architecture. Furthermore, we quantify the influence of the CHT thermal boundary condition on surrogate model performance, highlighting improved temperature model performance with higher heat fluxes. Compared to other deep learning neural network surrogate models, such as U-Net and DenseED, the proposed DeepEDH methodology for CHT models exhibits up to a 65% enhancement in the coefficient of determination ($R^{2}$).
Authors: Chenglin Yang, Siyuan Qiao, Yuan Cao, Yu Zhang, Tao Zhu, Alan Yuille, Jiahui Yu
Generative training has been demonstrated to be powerful for building visual-language models. However, on zero-shot discriminative benchmarks, there is still a performance gap between models trained with generative and discriminative objectives. In this paper, we aim to narrow this gap by improving the efficacy of generative training on classification tasks, without any finetuning processes or additional modules.
Specifically, we focus on narrowing the gap between the generative captioner and the CLIP classifier. We begin by analysing the predictions made by the captioner and classifier and observe that the caption generation inherits the distribution bias from the language model trained with pure text modality, making it less grounded on the visual signal. To tackle this problem, we redesign the scoring objective for the captioner to alleviate the distributional bias and focus on measuring the gain of information brought by the visual inputs. We further design a generative training objective to match the evaluation objective. We name our model trained and evaluated from the novel procedures as Information Gain (IG) captioner. We pretrain the models on the public Laion-5B dataset and perform a series of discriminative evaluations. For the zero-shot classification on ImageNet, IG captioner achieves $> 18\%$ improvements over the standard captioner, achieving comparable performances with the CLIP classifier. IG captioner also demonstrated strong performance on zero-shot image-text retrieval tasks on MSCOCO and Flickr30K. We hope this paper inspires further research towards unifying generative and discriminative training procedures for visual-language models.
Authors: Ahmet F. Budak, Keren Zhu, David Z. Pan
The high simulation cost has been a bottleneck of practical analog/mixed-signal design automation. Many learning-based algorithms require thousands of simulated data points, which is impractical for expensive to simulate circuits. We propose a learning-based algorithm that can be trained using a small amount of data and, therefore, scalable to tasks with expensive simulations. Our efficient algorithm solves the post-layout performance optimization problem where simulations are known to be expensive. Our comprehensive study also solves the schematic-level sizing problem. For efficient optimization, we utilize Bayesian Neural Networks as a regression model to approximate circuit performance. For layout-aware optimization, we handle the problem as a multi-fidelity optimization problem and improve efficiency by exploiting the correlations from cheaper evaluations. We present three test cases to demonstrate the efficiency of our algorithms. Our tests prove that the proposed approach is more efficient than conventional baselines and state-of-the-art algorithms.
Authors: Chancharik Mitra, Brandon Huang, Trevor Darrell, Roei Herzig
The combination of strong visual backbones and Large Language Model (LLM) reasoning has led to Large Multimodal Models (LMMs) becoming the current standard for a wide range of vision and language (VL) tasks. However, recent research has shown that even the most advanced LMMs still struggle to capture aspects of compositional visual reasoning, such as attributes and relationships between objects. One solution is to utilize scene graphs (SGs)--a formalization of objects and their relations and attributes that has been extensively used as a bridge between the visual and textual domains. Yet, scene graph data requires scene graph annotations, which are expensive to collect and thus not easily scalable. Moreover, finetuning an LMM based on SG data can lead to catastrophic forgetting of the pretraining objective. To overcome this, inspired by chain-of-thought methods, we propose Compositional Chain-of-Thought (CCoT), a novel zero-shot Chain-of-Thought prompting method that utilizes SG representations in order to extract compositional knowledge from an LMM. Specifically, we first generate an SG using the LMM, and then use that SG in the prompt to produce a response. Through extensive experiments, we find that the proposed CCoT approach not only improves LMM performance on several vision and language VL compositional benchmarks but also improves the performance of several popular LMMs on general multimodal benchmarks, without the need for fine-tuning or annotated ground-truth SGs.
Authors: Evelyn Mannix, Howard Bondell
In this paper we present an improved approach to prototypical semi-supervised learning for computer vision, in the context of leveraging a frozen foundation model as the backbone of our neural network. As a general tool, we propose parametric von-Mises Fisher Stochastic Neighbour Embedding (vMF-SNE) to create mappings with neural networks between high-dimensional latent spaces that preserve local structure. This enables us to pretrain the projection head of our network using the high-quality embeddings of the foundation model with vMF-SNE. We also propose soft multi-view pseudolabels, where predictions across multiple views are combined to provide a more reliable supervision signal compared to a consistency or swapped assignment approach. We demonstrate that these ideas improve upon P}redicting View-Assignments with Support Samples (PAWS), a current state-of-the-art semi-supervised learning method, as well as Robust PAWS (RoPAWS), over a range of benchmarking datasets. We also introduce simple $k$-means prototype selection, a technique that provides superior performance to other unsupervised label selection approaches in this context. These changes improve upon PAWS by an average of +2.9% for CIFAR-10 and +5.7% for CIFAR-100 with four labels per class, and by +15.2% for DeepWeeds, a particularly challenging dataset for semi-supervised learning. We also achieve new state-of-the-art results in semi-supervised learning in this small label regime for CIFAR-10 - 95.8% (+0.7%) and CIFAR-100 - 76.6% (+12.0%).
Authors: Junwon Seo, Sangyoon Lee, Kwang In Kim, Jaeho Lee
Neural field is an emerging paradigm in data representation that trains a neural network to approximate the given signal. A key obstacle that prevents its widespread adoption is the encoding speed-generating neural fields requires an overfitting of a neural network, which can take a significant number of SGD steps to reach the desired fidelity level. In this paper, we delve into the impacts of data transformations on the speed of neural field training, specifically focusing on how permuting pixel locations affect the convergence speed of SGD. Counterintuitively, we find that randomly permuting the pixel locations can considerably accelerate the training. To explain this phenomenon, we examine the neural field training through the lens of PSNR curves, loss landscapes, and error patterns. Our analyses suggest that the random pixel permutations remove the easy-to-fit patterns, which facilitate easy optimization in the early stage but hinder capturing fine details of the signal.
Authors: Ying Wang, Shashank Jere, Soumya Banerjee, Lingjia Liu, Sachin Shetty, Shehadi Dayekh
Jamming and intrusion detection are critical in 5G research, aiming to maintain reliability, prevent user experience degradation, and avoid infrastructure failure. This paper introduces an anonymous jamming detection model for 5G based on signal parameters from the protocol stacks. The system uses supervised and unsupervised learning for real-time, high-accuracy detection of jamming, including unknown types. Supervised models reach an AUC of 0.964 to 1, compared to LSTM models with an AUC of 0.923 to 1. However, the need for data annotation limits the supervised approach. To address this, an unsupervised auto-encoder-based anomaly detection is presented with an AUC of 0.987. The approach is resistant to adversarial training samples. For transparency and domain knowledge injection, a Bayesian network-based causation analysis is introduced.
Authors: Dayu Hu, Zhibin Dong, Ke Liang, Jun Wang, Siwei Wang, Xinwang Liu
Single-cell multi-view clustering enables the exploration of cellular heterogeneity within the same cell from different views. Despite the development of several multi-view clustering methods, two primary challenges persist. Firstly, most existing methods treat the information from both single-cell RNA (scRNA) and single-cell Assay of Transposase Accessible Chromatin (scATAC) views as equally significant, overlooking the substantial disparity in data richness between the two views. This oversight frequently leads to a degradation in overall performance. Additionally, the majority of clustering methods necessitate manual specification of the number of clusters by users. However, for biologists dealing with cell data, precisely determining the number of distinct cell types poses a formidable challenge. To this end, we introduce scUNC, an innovative multi-view clustering approach tailored for single-cell data, which seamlessly integrates information from different views without the need for a predefined number of clusters. The scUNC method comprises several steps: initially, it employs a cross-view fusion network to create an effective embedding, which is then utilized to generate initial clusters via community detection. Subsequently, the clusters are automatically merged and optimized until no further clusters can be merged. We conducted a comprehensive evaluation of scUNC using three distinct single-cell datasets. The results underscored that scUNC outperforms the other baseline methods.
Authors: Dayu Hu, Ke Liang, Xinwang Liu
In recent years, the field of single-cell RNA sequencing has seen a surge in the development of clustering methods. These methods enable the identification of cell subpopulations, thereby facilitating the understanding of tumor microenvironments. Despite their utility, most existing clustering algorithms primarily focus on the attribute information provided by the cell matrix or the network structure between cells, often neglecting the network between genes. This oversight could lead to loss of information and clustering results that lack clinical significance. To address this limitation, we develop an advanced single-cell clustering model incorporating dual-graph alignment, which integrates gene network information into the clustering process based on self-supervised and unsupervised optimization. Specifically, we designed a graph-based autoencoder enhanced by an attention mechanism to effectively capture relationships between cells. Moreover, we performed the node2vec method on Protein-Protein Interaction (PPI) networks to derive the gene network structure and maintained this structure throughout the clustering process. Our proposed method has been demonstrated to be effective through experimental results, showcasing its ability to optimize clustering outcomes while preserving the original associations between cells and genes. This research contributes to obtaining accurate cell subpopulations and generates clustering results that more closely resemble real-world biological scenarios. It provides better insights into the characteristics and distribution of diseased cells, ultimately building a foundation for early disease diagnosis and treatment.
Authors: Romain Lacombe, Kerrie Wu, Eddie Dilworth
Evaluating the accuracy of outputs generated by Large Language Models (LLMs) is especially important in the climate science and policy domain. We introduce the Expert Confidence in Climate Statements (ClimateX) dataset, a novel, curated, expert-labeled dataset consisting of 8094 climate statements collected from the latest Intergovernmental Panel on Climate Change (IPCC) reports, labeled with their associated confidence levels. Using this dataset, we show that recent LLMs can classify human expert confidence in climate-related statements, especially in a few-shot learning setting, but with limited (up to 47%) accuracy. Overall, models exhibit consistent and significant over-confidence on low and medium confidence statements. We highlight implications of our results for climate communication, LLMs evaluation strategies, and the use of LLMs in information retrieval systems.
Authors: Georgios Makridis, Georgios Fatouros, Vasileios Koukos, Dimitrios Kotios, Dimosthenis Kyriazis, Ioannis Soldatos
Although much work has been done on explainability in the computer vision and natural language processing (NLP) fields, there is still much work to be done to explain methods applied to time series as time series by nature can not be understood at first sight. In this paper, we present a Deep Neural Network (DNN) in a teacher-student architecture (distillation model) that offers interpretability in time-series classification tasks. The explainability of our approach is based on transforming the time series to 2D plots and applying image highlight methods (such as LIME and GradCam), making the predictions interpretable. At the same time, the proposed approach offers increased accuracy competing with the baseline model with the trade-off of increasing the training time.
Authors: Jacob Schnell, Jieke Wang, Lu Qi, Vincent Tao Hu, Meng Tang
Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthetic images improves many perception tasks, such as image classification, object detection, and semantic segmentation. We are the first to explore generative data augmentations for scribble-supervised semantic segmentation. We propose a generative data augmentation method that leverages a ControlNet diffusion model conditioned on semantic scribbles to produce high-quality training data. However, naive implementations of generative data augmentations may inadvertently harm the performance of the downstream segmentor rather than improve it. We leverage classifier-free diffusion guidance to enforce class consistency and introduce encode ratios to trade off data diversity for data realism. Using the guidance scale and encode ratio, we are able to generate a spectrum of high-quality training images. We propose multiple augmentation schemes and find that these schemes significantly impact model performance, especially in the low-data regime. Our framework further reduces the gap between the performance of scribble-supervised segmentation and that of fully-supervised segmentation. We also show that our framework significantly improves segmentation performance on small datasets, even surpassing fully-supervised segmentation.
Authors: Corneliu Cofaru, Johan Loeckx
This paper proposes a knowledge-driven AutoML architecture for pipeline and deep feature synthesis. The main goal is to render the AutoML process explainable and to leverage domain knowledge in the synthesis of pipelines and features. The architecture explores several novel ideas: first, the construction of pipelines and deep features is approached in an unified way. Next, synthesis is driven by a shared knowledge system, interactively queried as to what pipeline operations to use or features to compute. Lastly, the synthesis processes takes decisions at runtime using partial solutions and results of their application on data. Two experiments are conducted to demonstrate the functionality of a na\"{\i}ve implementation of the proposed architecture and to discuss its advantages, trade-offs as well as future potential for AutoML.
Authors: Botao Ren, Botian Xu, Tengyu Liu, Jingyi Wang, Zhidong Deng
Neuroscience studies have shown that the human visual system utilizes high-level feedback information to guide lower-level perception, enabling adaptation to signals of different characteristics. In light of this, we propose Feedback multi-Level feature Extractor (Flex) to incorporate a similar mechanism for object detection. Flex refines feature selection based on image-wise and instance-level feedback information in response to image quality variation and classification uncertainty. Experimental results show that Flex offers consistent improvement to a range of existing SOTA methods on the challenging aerial object detection datasets including DOTA-v1.0, DOTA-v1.5, and HRSC2016. Although the design originates in aerial image detection, further experiments on MS COCO also reveal our module's efficacy in general detection models. Quantitative and qualitative analyses indicate that the improvements are closely related to image qualities, which match our motivation.
Authors: Jacob R. Epifano, Stephen Glass, Ravi P. Ramachandran, Sharad Patel, Aaron J. Masino, Ghulam Rasool
This study investigated the performance, explainability, and robustness of deployed artificial intelligence (AI) models in predicting mortality during the COVID-19 pandemic and beyond. The first study of its kind, we found that Bayesian Neural Networks (BNNs) and intelligent training techniques allowed our models to maintain performance amidst significant data shifts. Our results emphasize the importance of developing robust AI models capable of matching or surpassing clinician predictions, even under challenging conditions. Our exploration of model explainability revealed that stochastic models generate more diverse and personalized explanations thereby highlighting the need for AI models that provide detailed and individualized insights in real-world clinical settings. Furthermore, we underscored the importance of quantifying uncertainty in AI models which enables clinicians to make better-informed decisions based on reliable predictions. Our study advocates for prioritizing implementation science in AI research for healthcare and ensuring that AI solutions are practical, beneficial, and sustainable in real-world clinical environments. By addressing unique challenges and complexities in healthcare settings, researchers can develop AI models that effectively improve clinical practice and patient outcomes.
Authors: Zizhang Chen, Ryan Paul Badman, Lachele Foley, Robert Woods, Pengyu Hong
Molecular representation learning (MRL) is a powerful tool for bridging the gap between machine learning and chemical sciences, as it converts molecules into numerical representations while preserving their chemical features. These encoded representations serve as a foundation for various downstream biochemical studies, including property prediction and drug design. MRL has had great success with proteins and general biomolecule datasets. Yet, in the growing sub-field of glycoscience (the study of carbohydrates, where longer carbohydrates are also called glycans), MRL methods have been barely explored. This under-exploration can be primarily attributed to the limited availability of comprehensive and well-curated carbohydrate-specific datasets and a lack of Machine learning (ML) pipelines specifically tailored to meet the unique problems presented by carbohydrate data. Since interpreting and annotating carbohydrate-specific data is generally more complicated than protein data, domain experts are usually required to get involved. The existing MRL methods, predominately optimized for proteins and small biomolecules, also cannot be directly used in carbohydrate applications without special modifications. To address this challenge, accelerate progress in glycoscience, and enrich the data resources of the MRL community, we introduce GlycoNMR. GlycoNMR contains two laboriously curated datasets with 2,609 carbohydrate structures and 211,543 annotated nuclear magnetic resonance (NMR) chemical shifts for precise atomic-level prediction. We tailored carbohydrate-specific features and adapted existing MRL models to tackle this problem effectively. For illustration, we benchmark four modified MRL models on our new datasets.
Authors: Xiaodan Du, Nicholas Kolkin, Greg Shakhnarovich, Anand Bhattad
Generative models have been shown to be capable of synthesizing highly detailed and realistic images. It is natural to suspect that they implicitly learn to model some image intrinsics such as surface normals, depth, or shadows. In this paper, we present compelling evidence that generative models indeed internally produce high-quality scene intrinsic maps. We introduce Intrinsic LoRA (I LoRA), a universal, plug-and-play approach that transforms any generative model into a scene intrinsic predictor, capable of extracting intrinsic scene maps directly from the original generator network without needing additional decoders or fully fine-tuning the original network. Our method employs a Low-Rank Adaptation (LoRA) of key feature maps, with newly learned parameters that make up less than 0.6% of the total parameters in the generative model. Optimized with a small set of labeled images, our model-agnostic approach adapts to various generative architectures, including Diffusion models, GANs, and Autoregressive models. We show that the scene intrinsic maps produced by our method compare well with, and in some cases surpass those generated by leading supervised techniques.
Authors: Ayush Sarkar, Hanlin Mai, Amitabh Mahapatra, Svetlana Lazebnik, D.A. Forsyth, Anand Bhattad
Generative models can produce impressively realistic images. This paper demonstrates that generated images have geometric features different from those of real images. We build a set of collections of generated images, prequalified to fool simple, signal-based classifiers into believing they are real. We then show that prequalified generated images can be identified reliably by classifiers that only look at geometric properties. We use three such classifiers. All three classifiers are denied access to image pixels, and look only at derived geometric features. The first classifier looks at the perspective field of the image, the second looks at lines detected in the image, and the third looks at relations between detected objects and shadows. Our procedure detects generated images more reliably than SOTA local signal based detectors, for images from a number of distinct generators. Saliency maps suggest that the classifiers can identify geometric problems reliably. We conclude that current generators cannot reliably reproduce geometric properties of real images.
Authors: Carolina Cuesta-Lazaro, Siddharth Mishra-Sharma
We introduce a diffusion-based generative model to describe the distribution of galaxies in our Universe directly as a collection of points in 3-D space (coordinates) optionally with associated attributes (e.g., velocities and masses), without resorting to binning or voxelization. The custom diffusion model can be used both for emulation, reproducing essential summary statistics of the galaxy distribution, as well as inference, by computing the conditional likelihood of a galaxy field. We demonstrate a first application to massive dark matter haloes in the Quijote simulation suite. This approach can be extended to enable a comprehensive analysis of cosmological data, circumventing limitations inherent to summary statistic -- as well as neural simulation-based inference methods.
Authors: Hali Huang, Daniel Muthukrishna, Prajna Nair, Zimi Zhang, Michael Fausnaugh, Torsha Majumder, Ryan J. Foley, George R. Ricker
Astronomical transients, such as supernovae and other rare stellar explosions, have been instrumental in some of the most significant discoveries in astronomy. New astronomical sky surveys will soon record unprecedented numbers of transients as sparsely and irregularly sampled multivariate time series. To improve our understanding of the physical mechanisms of transients and their progenitor systems, early-time measurements are necessary. Prioritizing the follow-up of transients based on their age along with their class is crucial for new surveys. To meet this demand, we present the first method of predicting the age of transients in real-time from multi-wavelength time-series observations. We build a Bayesian probabilistic recurrent neural network. Our method can accurately predict the age of a transient with robust uncertainties as soon as it is initially triggered by a survey telescope. This work will be essential for the advancement of our understanding of the numerous young transients being detected by ongoing and upcoming astronomical surveys.
Authors: Dang Nguyen, Chacha Chen, He He, Chenhao Tan
When pneumonia is not found on a chest X-ray, should the report describe this negative observation or omit it? We argue that this question cannot be answered from the X-ray alone and requires a pragmatic perspective, which captures the communicative goal that radiology reports serve between radiologists and patients. However, the standard image-to-text formulation for radiology report generation fails to incorporate such pragmatic intents. Following this pragmatic perspective, we demonstrate that the indication, which describes why a patient comes for an X-ray, drives the mentions of negative observations and introduce indications as additional input to report generation. With respect to the output, we develop a framework to identify uninferable information from the image as a source of model hallucinations, and limit them by cleaning groundtruth reports. Finally, we use indications and cleaned groundtruth reports to develop pragmatic models, and show that they outperform existing methods not only in new pragmatics-inspired metrics (+4.3 Negative F1) but also in standard metrics (+6.3 Positive F1 and +11.0 BLEU-2).
Authors: Ryan Liu, Abhijith Gandrakota, Jennifer Ngadiuba, Maria Spiropulu, Jean-Roch Vlimant
Model-agnostic anomaly detection is one of the promising approaches in the search for new beyond the standard model physics. In this paper, we present Set-VAE, a particle-based variational autoencoder (VAE) anomaly detection algorithm. We demonstrate a 2x signal efficiency gain compared with traditional subjettiness-based jet selection. Furthermore, with an eye to the future deployment to trigger systems, we propose the CLIP-VAE, which reduces the inference-time cost of anomaly detection by using the KL-divergence loss as the anomaly score, resulting in a 2x acceleration in latency and reducing the caching requirement.
Authors: Olivia Macmillan-Scott, Mirco Musolesi
The concept of rationality is central to the field of artificial intelligence. Whether we are seeking to simulate human reasoning, or the goal is to achieve bounded optimality, we generally seek to make artificial agents as rational as possible. Despite the centrality of the concept within AI, there is no unified definition of what constitutes a rational agent. This article provides a survey of rationality and irrationality in artificial intelligence, and sets out the open questions in this area. The understanding of rationality in other fields has influenced its conception within artificial intelligence, in particular work in economics, philosophy and psychology. Focusing on the behaviour of artificial agents, we consider irrational behaviours that can prove to be optimal in certain scenarios. Some methods have been developed to deal with irrational agents, both in terms of identification and interaction, however work in this area remains limited. Methods that have up to now been developed for other purposes, namely adversarial scenarios, may be adapted to suit interactions with artificial agents. We further discuss the interplay between human and artificial agents, and the role that rationality plays within this interaction; many questions remain in this area, relating to potentially irrational behaviour of both humans and artificial agents.
Authors: Yuqi Wang, Aarzu Gupta, David Carpenter, Trey Mullikin, Zachary J. Reitman, Scott Floyd, John Kirkpatrick, Joseph K. Salama, Paul W. Sperduto, Jian-Guo Liu, Mustafa R. Bashir, Kyle J. Lafata
TodevelopanovelUncertaintyQuantification (UQ) framework to estimate the uncertainty of patient survival models in the absence of ground truth, we developed and evaluated our approach based on a dataset of 1383 patients treated with stereotactic radiosurgery (SRS) for brain metastases between January 2015 and December 2020. Our motivating hypothesis is that a time-to-event prediction of a test patient on inference is more certain given a higher feature-space-similarity to patients in the training set. Therefore, the uncertainty for a particular patient-of-interest is represented by the concordance index between a patient similarity rank and a prediction similarity rank. Model uncertainty was defined as the increased percentage of the max uncertainty-constrained-AUC compared to the model AUC. We evaluated our method on multiple clinically-relevant endpoints, including time to intracranial progression (ICP), progression-free survival (PFS) after SRS, overall survival (OS), and time to ICP and/or death (ICPD), on a variety of both statistical and non-statistical models, including CoxPH, conditional survival forest (CSF), and neural multi-task linear regression (NMTLR). Our results show that all models had the lowest uncertainty on ICP (2.21%) and the highest uncertainty (17.28%) on ICPD. OS models demonstrated high variation in uncertainty performance, where NMTLR had the lowest uncertainty(1.96%)and CSF had the highest uncertainty (14.29%). In conclusion, our method can estimate the uncertainty of individual patient survival modeling results. As expected, our data empirically demonstrate that as model uncertainty measured via our technique increases, the similarity between a feature-space and its predicted outcome decreases.
Authors: Konstantin Klemmer, Esther Rolf, Caleb Robinson, Lester Mackey, Marc Rußwurm
Geographic location is essential for modeling tasks in fields ranging from ecology to epidemiology to the Earth system sciences. However, extracting relevant and meaningful characteristics of a location can be challenging, often entailing expensive data fusion or data distillation from global imagery datasets. To address this challenge, we introduce Satellite Contrastive Location-Image Pretraining (SatCLIP), a global, general-purpose geographic location encoder that learns an implicit representation of locations from openly available satellite imagery. Trained location encoders provide vector embeddings summarizing the characteristics of any given location for convenient usage in diverse downstream tasks. We show that SatCLIP embeddings, pretrained on globally sampled multi-spectral Sentinel-2 satellite data, can be used in various predictive tasks that depend on location information but not necessarily satellite imagery, including temperature prediction, animal recognition in imagery, and population density estimation. Across tasks, SatCLIP embeddings consistently outperform embeddings from existing pretrained location encoders, ranging from models trained on natural images to models trained on semantic context. SatCLIP embeddings also help to improve geographic generalization. This demonstrates the potential of general-purpose location encoders and opens the door to learning meaningful representations of our planet from the vast, varied, and largely untapped modalities of geospatial data.
Authors: Daniel Bairamian, Philippe Marcotte, Joshua Romoff, Gabriel Robert, Derek Nowrouzezahrai
Recent advances in Competitive Self-Play (CSP) have achieved, or even surpassed, human level performance in complex game environments such as Dota 2 and StarCraft II using Distributed Multi-Agent Reinforcement Learning (MARL). One core component of these methods relies on creating a pool of learning agents -- consisting of the Main Agent, past versions of this agent, and Exploiter Agents -- where Exploiter Agents learn counter-strategies to the Main Agents. A key drawback of these approaches is the large computational cost and physical time that is required to train the system, making them impractical to deploy in highly iterative real-life settings such as video game productions. In this paper, we propose the Minimax Exploiter, a game theoretic approach to exploiting Main Agents that leverages knowledge of its opponents, leading to significant increases in data efficiency. We validate our approach in a diversity of settings, including simple turn based games, the arcade learning environment, and For Honor, a modern video game. The Minimax Exploiter consistently outperforms strong baselines, demonstrating improved stability and data efficiency, leading to a robust CSP-MARL method that is both flexible and easy to deploy.
Authors: Rumman Ahmed Prodhan, Sumya Akter, Tanmoy Sarkar Pias, Md. Akhtaruzzaman Adnan
The human brain is a complex organ, still completely undiscovered, that controls almost all the parts of the body. Apart from survival, the human brain stimulates emotions. Recent research indicates that brain signals can be very effective for emotion recognition. However, which parts of the brain exhibit most of the emotions is still under-explored. In this study, we empirically analyze the contribution of each part of the brain in exhibiting emotions. We use the DEAP dataset to find the most optimal electrode set which eventually leads to the effective brain part associated with emotions. We use Fast Fourier Transformation for effective feature extraction and a 1D-CNN with residual connection for classification. Though 32 electrodes from the DEAP dataset got an accuracy of 97.34%, only 12 electrodes (F7, P8, O1, F8, C4, T7, PO3, Fp1, Fp2, O2, P3, and Fz) achieve 95.81% accuracy. This study also shows that adding more than 10 electrodes does not improve performance significantly. Moreover, the frontal lobe is the most important for recognizing emotion.
Authors: Yixuan Luo, Mengye Ren, Sai Qian Zhang
Like masked language modeling (MLM) in natural language processing, masked image modeling (MIM) aims to extract valuable insights from image patches to enhance the feature extraction capabilities of the underlying deep neural network (DNN). Contrasted with other training paradigms like supervised learning and unsupervised contrastive learning, masked image modeling (MIM) pretraining typically demands significant computational resources in order to manage large training data batches (e.g., 4096). The significant memory and computation requirements pose a considerable challenge to its broad adoption. To mitigate this, we introduce a novel learning framework, termed~\textit{Block-Wise Masked Image Modeling} (BIM). This framework involves decomposing the MIM tasks into several sub-tasks with independent computation patterns, resulting in block-wise back-propagation operations instead of the traditional end-to-end approach. Our proposed BIM maintains superior performance compared to conventional MIM while greatly reducing peak memory consumption. Moreover, BIM naturally enables the concurrent training of numerous DNN backbones of varying depths. This leads to the creation of multiple trained DNN backbones, each tailored to different hardware platforms with distinct computing capabilities. This approach significantly reduces computational costs in comparison with training each DNN backbone individually. Our framework offers a promising solution for resource constrained training of MIM.
Authors: Dirk Tasche
We study the problem of class distribution estimation under dataset shift. On the training dataset, both features and class labels are observed while on the test dataset only the features can be observed. The task then is the estimation of the distribution of the class labels, i.e. the estimation of the class prior probabilities, in the test dataset. Assumptions of invariance between the training joint distribution of features and labels and the test distribution can considerably facilitate this task. We discuss the assumptions of covariate shift, factorizable joint shift, and sparse joint shift and their implications for class distribution estimation.
Authors: Lukas Wolf, Tiago Pimentel, Evelina Fedorenko, Ryan Cotterell, Alex Warstadt, Ethan Wilcox, Tamar Regev
Prosody -- the suprasegmental component of speech, including pitch, loudness, and tempo -- carries critical aspects of meaning. However, the relationship between the information conveyed by prosody vs. by the words themselves remains poorly understood. We use large language models (LLMs) to estimate how much information is redundant between prosody and the words themselves. Using a large spoken corpus of English audiobooks, we extract prosodic features aligned to individual words and test how well they can be predicted from LLM embeddings, compared to non-contextual word embeddings. We find a high degree of redundancy between the information carried by the words and prosodic information across several prosodic features, including intensity, duration, pauses, and pitch contours. Furthermore, a word's prosodic information is redundant with both the word itself and the context preceding as well as following it. Still, we observe that prosodic features can not be fully predicted from text, suggesting that prosody carries information above and beyond the words. Along with this paper, we release a general-purpose data processing pipeline for quantifying the relationship between linguistic information and extra-linguistic features.
Authors: Isaac Brant, Alexander Norcliffe, Pietro Liò
A Quantum Field Theory is defined by its interaction Hamiltonian, and linked to experimental data by the scattering matrix. The scattering matrix is calculated as a perturbative series, and represented succinctly as a first order differential equation in time. Neural Differential Equations (NDEs) learn the time derivative of a residual network's hidden state, and have proven efficacy in learning differential equations with physical constraints. Hence using an NDE to learn particle scattering matrices presents a possible experiment-theory phenomenological connection. In this paper, NDE models are used to learn $\phi^4$ theory, Scalar-Yukawa theory and Scalar Quantum Electrodynamics. A new NDE architecture is also introduced, the Fourier Neural Differential Equation (FNDE), which combines NDE integration and Fourier network convolution. The FNDE model demonstrates better generalisability than the non-integrated equivalent FNO model. It is also shown that by training on scattering data, the interaction Hamiltonian of a theory can be extracted from network parameters.
Authors: Mark Díaz, Sunipa Dev, Emily Reif, Remi Denton, Vinodkumar Prabhakaran
The unstructured nature of data used in foundation model development is a challenge to systematic analyses for making data use and documentation decisions. From a Responsible AI perspective, these decisions often rely upon understanding how people are represented in data. We propose a framework designed to guide analysis of human representation in unstructured data and identify downstream risks. We apply the framework in two toy examples using the Common Crawl web text corpus (C4) and LAION-400M. We also propose a set of hypothetical action steps in service of dataset use, development, and documentation.
Authors: Tuxun Lu, Aviva Prins
Crop management decision support systems are specialized tools for farmers that reduce the riskiness of revenue streams, especially valuable for use under the current climate changes that impact agricultural productivity. Unfortunately, small farmers in India, who could greatly benefit from these tools, do not have access to them. In this paper, we model an individual greenhouse as a Markov Decision Process (MDP) and adapt Li and Li (2019)'s Follow the Weighted Leader (FWL) online learning algorithm to offer crop planning advice. We successfully produce utility-preserving cropping pattern suggestions in simulations. When we compare against an offline planning algorithm, we achieve the same cumulative revenue with greatly reduced runtime.
Authors: Soheil Zibakhsh Shabgahi, Nojan Sheybani, Aiden Tabrizi, Farinaz Koushanfar
Traditional machine learning training is a static process that lacks real-time adaptability of hyperparameters. Popular tuning solutions during runtime involve checkpoints and schedulers. Adjusting hyper-parameters usually require the program to be restarted, wasting utilization and time, while placing unnecessary strain on memory and processors. We present LiveTune, a new framework allowing real-time parameter tuning during training through LiveVariables. Live Variables allow for a continuous training session by storing parameters on designated ports on the system, allowing them to be dynamically adjusted. Extensive evaluations of our framework show saving up to 60 seconds and 5.4 Kilojoules of energy per hyperparameter change.
Authors: Youssef Sultan, Jackson C. Rafter, Huyen T. Nguyen
Understanding whether a property is priced fairly hinders buyers and sellers since they usually do not have an objective viewpoint of the price distribution for the overall market of their interest. Drawing from data collected of all possible available properties for rent in Manhattan as of September 2023, this paper aims to strengthen our understanding of model residuals; specifically on machine learning models which generalize for a majority of the distribution of a well-proportioned dataset. Most models generally perceive deviations from predicted values as mere inaccuracies, however this paper proposes a different vantage point: when generalizing to at least 75\% of the data-set, the remaining deviations reveal significant insights. To harness these insights, we introduce the Price Anomaly Score (PAS), a metric capable of capturing boundaries between irregularly predicted prices. By combining relative pricing discrepancies with statistical significance, the Price Anomaly Score (PAS) offers a multifaceted view of rental valuations. This metric allows experts to identify overpriced or underpriced properties within a dataset by aggregating PAS values, then fine-tuning upper and lower boundaries to any threshold to set indicators of choice.
Authors: Vasileios Tsouvalas, Yuki Asano, Aaqib Saeed
Foundation Models (FMs) have revolutionized machine learning with their adaptability and high performance across tasks; yet, their integration into Federated Learning (FL) is challenging due to substantial communication overhead from their extensive parameterization. Current communication-efficient FL strategies, such as gradient compression, reduce bitrates to around $1$ bit-per-parameter (bpp). However, these approaches fail to harness the characteristics of FMs, with their large number of parameters still posing a challenge to communication efficiency, even at these bitrate regimes. In this work, we present DeltaMask, a novel method that efficiently fine-tunes FMs in FL at an ultra-low bitrate, well below 1 bpp. DeltaMask employs stochastic masking to detect highly effective subnetworks within FMs and leverage stochasticity and sparsity in client masks to compress updates into a compact grayscale image using probabilistic filters, deviating from traditional weight training approaches. Our comprehensive evaluations across various datasets and architectures demonstrate DeltaMask efficiently achieves bitrates as low as 0.09 bpp, enhancing communication efficiency while maintaining FMs performance, as measured on 8 datasets and 5 pre-trained models of various network architectures.
Authors: Sofia Serrano, Zander Brumbaugh, Noah A. Smith
Given the growing importance of AI literacy, we decided to write this tutorial to help narrow the gap between the discourse among those who study language models -- the core technology underlying ChatGPT and similar products -- and those who are intrigued and want to learn more about them. In short, we believe the perspective of researchers and educators can add some clarity to the public's understanding of the technologies beyond what's currently available, which tends to be either extremely technical or promotional material generated about products by their purveyors.
Our approach teases apart the concept of a language model from products built on them, from the behaviors attributed to or desired from those products, and from claims about similarity to human cognition. As a starting point, we (1) offer a scientific viewpoint that focuses on questions amenable to study through experimentation; (2) situate language models as they are today in the context of the research that led to their development; and (3) describe the boundaries of what is known about the models at this writing.
Authors: Xiaoge Zhang, Xiao-Lin Wang, Fenglei Fan, Yiu-Ming Cheung, Indranil Bose
In this paper, we develop a generic methodology to encode hierarchical causality structure among observed variables into a neural network in order to improve its predictive performance. The proposed methodology, called causality-informed neural network (CINN), leverages three coherent steps to systematically map the structural causal knowledge into the layer-to-layer design of neural network while strictly preserving the orientation of every causal relationship. In the first step, CINN discovers causal relationships from observational data via directed acyclic graph (DAG) learning, where causal discovery is recast as a continuous optimization problem to avoid the combinatorial nature. In the second step, the discovered hierarchical causality structure among observed variables is systematically encoded into neural network through a dedicated architecture and customized loss function. By categorizing variables in the causal DAG as root, intermediate, and leaf nodes, the hierarchical causal DAG is translated into CINN with a one-to-one correspondence between nodes in the causal DAG and units in the CINN while maintaining the relative order among these nodes. Regarding the loss function, both intermediate and leaf nodes in the DAG graph are treated as target outputs during CINN training so as to drive co-learning of causal relationships among different types of nodes. As multiple loss components emerge in CINN, we leverage the projection of conflicting gradients to mitigate gradient interference among the multiple learning tasks. Computational experiments across a broad spectrum of UCI data sets demonstrate substantial advantages of CINN in predictive performance over other state-of-the-art methods. In addition, an ablation study underscores the value of integrating structural and quantitative causal knowledge in enhancing the neural network's predictive performance incrementally.
Authors: Cansu Demirkiran, Guowei Yang, Darius Bunandar, Ajay Joshi
Photonic computing is a compelling avenue for performing highly efficient matrix multiplication, a crucial operation in Deep Neural Networks (DNNs). While this method has shown great success in DNN inference, meeting the high precision demands of DNN training proves challenging due to the precision limitations imposed by costly data converters and the analog noise inherent in photonic hardware. This paper proposes Mirage, a photonic DNN training accelerator that overcomes the precision challenges in photonic hardware using the Residue Number System (RNS). RNS is a numeral system based on modular arithmetic$\unicode{x2014}$allowing us to perform high-precision operations via multiple low-precision modular operations. In this work, we present a novel micro-architecture and dataflow for an RNS-based photonic tensor core performing modular arithmetic in the analog domain. By combining RNS and photonics, Mirage provides high energy efficiency without compromising precision and can successfully train state-of-the-art DNNs achieving accuracy comparable to FP32 training. Our study shows that on average across several DNNs when compared to systolic arrays, Mirage achieves more than $23.8\times$ faster training and $32.1\times$ lower EDP in an iso-energy scenario and consumes $42.8\times$ lower power with comparable or better EDP in an iso-area scenario.
Authors: Chengzhang Li, Zhenkang Peng, Ying Rong
With increasingly volatile market conditions and rapid product innovations, operational decision-making for large-scale systems entails solving thousands of problems with limited data. Data aggregation is proposed to combine the data across problems to improve the decisions obtained by solving those problems individually. We propose a novel cluster-based shrunken-SAA approach that can exploit the cluster structure among problems when implementing the data aggregation approaches. We prove that, as the number of problems grows, leveraging the known cluster structure among problems yields additional benefits over the data aggregation approaches that neglect such structure. When the cluster structure is unknown, we show that unveiling the cluster structure, even at the cost of a few data points, can be beneficial, especially when the distance between clusters of problems is substantial. Our proposed approach can be extended to general cost functions under mild conditions. When the number of problems gets large, the optimality gap of our proposed approach decreases exponentially in the distance between the clusters. We explore the performance of the proposed approach through the application of managing newsvendor systems via numerical experiments. We investigate the impacts of distance metrics between problem instances on the performance of the cluster-based Shrunken-SAA approach with synthetic data. We further validate our proposed approach with real data and highlight the advantages of cluster-based data aggregation, especially in the small-data large-scale regime, compared to the existing approaches.
Authors: Yuankai Luo, Lei Shi, Veronika Thost
Self-supervised learning (SSL) has great potential for molecular representation learning given the complexity of molecular graphs, the large amounts of unlabelled data available, the considerable cost of obtaining labels experimentally, and the hence often only small training datasets. The importance of the topic is reflected in the variety of paradigms and architectures that have been investigated recently. Yet the differences in performance seem often minor and are barely understood to date. In this paper, we study SSL based on persistent homology (PH), a mathematical tool for modeling topological features of data that persist across multiple scales. It has several unique features which particularly suit SSL, naturally offering: different views of the data, stability in terms of distance preservation, and the opportunity to flexibly incorporate domain knowledge. We (1) investigate an autoencoder, which shows the general representational power of PH, and (2) propose a contrastive loss that complements existing approaches. We rigorously evaluate our approach for molecular property prediction and demonstrate its particular features in improving the embedding space: after SSL, the representations are better and offer considerably more predictive power than the baselines over different probing tasks; our loss increases baseline performance, sometimes largely; and we often obtain substantial improvements over very small datasets, a common scenario in practice.
Authors: Haoyu He, Zizheng Pan, Jing Liu, Jianfei Cai, Bohan Zhuang
The paradigm of pre-training and fine-tuning has laid the foundation for deploying deep learning models. However, most fine-tuning methods are designed to meet a specific resource budget. Recently, considering diverse deployment scenarios with various resource budgets, stitchable neural network (SN-Net) is introduced to quickly obtain numerous new networks (stitches) from the pre-trained models (anchors) in a model family via model stitching. Although promising, SN-Net confronts new challenges when adapting it to new target domains, including huge memory and storage requirements and a long and sub-optimal multistage adaptation process. In this work, we present a novel framework, Efficient Stitchable Task Adaptation (ESTA), to efficiently produce a palette of fine-tuned models that adhere to diverse resource constraints. Specifically, we first tailor parameter-efficient fine-tuning to share low-rank updates among the stitches while maintaining independent bias terms. In this way, we largely reduce fine-tuning memory burdens and mitigate the interference among stitches that arises in task adaptation. Furthermore, we streamline a simple yet effective one-stage deployment pipeline, which estimates the important stitches to deploy with training-time gradient statistics. By assigning higher sampling probabilities to important stitches, we also get a boosted Pareto frontier. Extensive experiments on 25 downstream visual recognition tasks demonstrate that our ESTA is capable of generating stitches with smooth accuracy-efficiency trade-offs and surpasses the direct SN-Net adaptation by remarkable margins with significantly lower training time and fewer trainable parameters. Furthermore, we demonstrate the flexibility and scalability of our ESTA framework by stitching LLMs from LLaMA family, obtaining chatbot stitches of assorted sizes.
Authors: Kohei Morimoto, Yusuke Takase, Kosuke Mitarai, Keisuke Fujii
In this paper, we introduce the quantum adaptive distribution search (QuADS), a quantum continuous optimization algorithm that integrates Grover adaptive search (GAS) with the covariance matrix adaptation - evolution strategy (CMA-ES), a classical technique for continuous optimization. QuADS utilizes the quantum-based search capabilities of GAS and enhances them with the principles of CMA-ES for more efficient optimization. It employs a multivariate normal distribution for the initial state of the quantum search and repeatedly updates it throughout the optimization process. Our numerical experiments show that QuADS outperforms both GAS and CMA-ES. This is achieved through adaptive refinement of the initial state distribution rather than consistently using a uniform state, resulting in fewer oracle calls. This study presents an important step toward exploiting the potential of quantum computing for continuous optimization.
Authors: Yuchang Zhu, Jintang Li, Liang Chen, Zibin Zheng
Graph neural networks (GNNs) are being increasingly used in many high-stakes tasks, and as a result, there is growing attention on their fairness recently. GNNs have been shown to be unfair as they tend to make discriminatory decisions toward certain demographic groups, divided by sensitive attributes such as gender and race. While recent works have been devoted to improving their fairness performance, they often require accessible demographic information. This greatly limits their applicability in real-world scenarios due to legal restrictions. To address this problem, we present a demographic-agnostic method to learn fair GNNs via knowledge distillation, namely FairGKD. Our work is motivated by the empirical observation that training GNNs on partial data (i.e., only node attributes or topology data) can improve their fairness, albeit at the cost of utility. To make a balanced trade-off between fairness and utility performance, we employ a set of fairness experts (i.e., GNNs trained on different partial data) to construct the synthetic teacher, which distills fairer and informative knowledge to guide the learning of the GNN student. Experiments on several benchmark datasets demonstrate that FairGKD, which does not require access to demographic information, significantly improves the fairness of GNNs by a large margin while maintaining their utility.
Authors: Lujia Shen, Yuwen Pu, Shouling Ji, Changjiang Li, Xuhong Zhang, Chunpeng Ge, Ting Wang
Transformer-based models, such as BERT and GPT, have been widely adopted in natural language processing (NLP) due to their exceptional performance. However, recent studies show their vulnerability to textual adversarial attacks where the model's output can be misled by intentionally manipulating the text inputs. Despite various methods that have been proposed to enhance the model's robustness and mitigate this vulnerability, many require heavy consumption resources (e.g., adversarial training) or only provide limited protection (e.g., defensive dropout). In this paper, we propose a novel method called dynamic attention, tailored for the transformer architecture, to enhance the inherent robustness of the model itself against various adversarial attacks. Our method requires no downstream task knowledge and does not incur additional costs. The proposed dynamic attention consists of two modules: (I) attention rectification, which masks or weakens the attention value of the chosen tokens, and (ii) dynamic modeling, which dynamically builds the set of candidate tokens. Extensive experiments demonstrate that dynamic attention significantly mitigates the impact of adversarial attacks, improving up to 33\% better performance than previous methods against widely-used adversarial attacks. The model-level design of dynamic attention enables it to be easily combined with other defense methods (e.g., adversarial training) to further enhance the model's robustness. Furthermore, we demonstrate that dynamic attention preserves the state-of-the-art robustness space of the original model compared to other dynamic modeling methods.
Authors: Xiangyu Meng, Tao Song, Qing Yang, Huanhuan Dai, Lian Qiao, Hongzhen Ding, Long Hao, Xun Wang
Analyzing the genomic information from the Pan-Cancer database can help us understand cancer-related factors and contribute to the cancer diagnosis and prognosis. However, existing computational methods and deep learning methods can not effectively find the deep correlations between tens of thousands of genes, which leads to precision loss. In this paper, we proposed a novel pretrained model called Gene-MOE to learn the general feature representations of the Pan-Cancer dataset and transfer the pretrained weights to the downstream tasks. The Gene-MOE fully exploits the mixture of expert (MOE) layers to learn rich feature representations of high-dimensional genes. At the same time, we build a mixture of attention expert (MOAE) model to learn the deep semantic relationships within genetic features. Finally, we proposed a new self-supervised pretraining strategy including loss function design, data enhancement, and optimization strategy to train the Gene-MOE and further improve the performance for the downstream analysis. We carried out cancer classification and survival analysis experiments based on the Gene-MOE. According to the survival analysis results on 14 cancer types, using Gene-MOE outperformed state-of-the-art models on 12 cancer types. According to the classification results, the total accuracy of the classification model for 33 cancer classifications reached 95.2\%. Through detailed feature analysis, we found the Gene-MOE model can learn rich feature representations of high-dimensional genes.
Authors: Yuchen Zhong, Guangming Sheng, Tianzuo Qin, Minjie Wang, Quan Gan, Chuan Wu
Graph Neural Networks (GNNs) play a crucial role in various fields. However, most existing deep graph learning frameworks assume pre-stored static graphs and do not support training on graph streams. In contrast, many real-world graphs are dynamic and contain time domain information. We introduce GNNFlow, a distributed framework that enables efficient continuous temporal graph representation learning on dynamic graphs on multi-GPU machines. GNNFlow introduces an adaptive time-indexed block-based data structure that effectively balances memory usage with graph update and sampling operation efficiency. It features a hybrid GPU-CPU graph data placement for rapid GPU-based temporal neighborhood sampling and kernel optimizations for enhanced sampling processes. A dynamic GPU cache for node and edge features is developed to maximize cache hit rates through reuse and restoration strategies. GNNFlow supports distributed training across multiple machines with static scheduling to ensure load balance. We implement GNNFlow based on DGL and PyTorch. Our experimental results show that GNNFlow provides up to 21.1x faster continuous learning than existing systems.
Authors: Yan Kang, Tao Fan, Hanlin Gu, Lixin Fan, Qiang Yang
Foundation Models (FMs) such as GPT-4 encoded with vast knowledge and powerful emergent abilities have achieved remarkable success in various natural language processing and computer vision tasks. Grounding FMs by adapting them to domain-specific tasks or augmenting them with domain-specific knowledge enables us to exploit the full potential of FMs. However, grounding FMs faces several challenges, stemming primarily from constrained computing resources, data privacy, model heterogeneity, and model ownership. Federated Transfer Learning (FTL), the combination of federated learning and transfer learning, provides promising solutions to address these challenges. In recent years, the need for grounding FMs leveraging FTL, coined FTL-FM, has arisen strongly in both academia and industry. Motivated by the strong growth in FTL-FM research and the potential impact of FTL-FM on industrial applications, we propose an FTL-FM framework that formulates problems of grounding FMs in the federated learning setting, construct a detailed taxonomy based on the FTL-FM framework to categorize state-of-the-art FTL-FM works, and comprehensively overview FTL-FM works based on the proposed taxonomy. We also establish correspondences between FTL-FM and conventional phases of adapting FM so that FM practitioners can align their research works with FTL-FM. In addition, we overview advanced efficiency-improving and privacy-preserving techniques because efficiency and privacy are critical concerns in FTL-FM. Last, we discuss opportunities and future research directions of FTL-FM.
Authors: Shpresim Sadiku, Moritz Wagner, Sebastian Pokutta
Sparse adversarial attacks fool deep neural networks (DNNs) through minimal pixel perturbations, typically regularized by the $\ell_0$ norm. Recent efforts have replaced this norm with a structural sparsity regularizer, such as the nuclear group norm, to craft group-wise sparse adversarial attacks. The resulting perturbations are thus explainable and hold significant practical relevance, shedding light on an even greater vulnerability of DNNs than previously anticipated. However, crafting such attacks poses an optimization challenge, as it involves computing norms for groups of pixels within a non-convex objective. In this paper, we tackle this challenge by presenting an algorithm that simultaneously generates group-wise sparse attacks within semantically meaningful areas of an image. In each iteration, the core operation of our algorithm involves the optimization of a quasinorm adversarial loss. This optimization is achieved by employing the $1/2$-quasinorm proximal operator for some iterations, a method tailored for nonconvex programming. Subsequently, the algorithm transitions to a projected Nesterov's accelerated gradient descent with $2$-norm regularization applied to perturbation magnitudes. We rigorously evaluate the efficacy of our novel attack in both targeted and non-targeted attack scenarios, on CIFAR-10 and ImageNet datasets. When compared to state-of-the-art methods, our attack consistently results in a remarkable increase in group-wise sparsity, e.g., an increase of $48.12\%$ on CIFAR-10 and $40.78\%$ on ImageNet (average case, targeted attack), all while maintaining lower perturbation magnitudes. Notably, this performance is complemented by a significantly faster computation time and a $100\%$ attack success rate.
Authors: Abhishek Madaan, Tanya Chowdhury, Neha Rana, James Allan, Tanmoy Chakraborty
In this work, we explore various topics that fall under the umbrella of Uncertainty in post-hoc Explainable AI (XAI) methods. We in particular focus on the class of additive feature attribution explanation methods. We first describe our specifications of uncertainty and compare various statistical and recent methods to quantify the same. Next, for a particular instance, we study the relationship between a feature's attribution and its uncertainty and observe little correlation. As a result, we propose a modification in the distribution from which perturbations are sampled in LIME-based algorithms such that the important features have minimal uncertainty without an increase in computational cost. Next, while studying how the uncertainty in explanations varies across the feature space of a classifier, we observe that a fraction of instances show near-zero uncertainty. We coin the term "stable instances" for such instances and diagnose factors that make an instance stable. Next, we study how an XAI algorithm's uncertainty varies with the size and complexity of the underlying model. We observe that the more complex the model, the more inherent uncertainty is exhibited by it. As a result, we propose a measure to quantify the relative complexity of a blackbox classifier. This could be incorporated, for example, in LIME-based algorithms' sampling densities, to help different explanation algorithms achieve tighter confidence levels. Together, the above measures would have a strong impact on making XAI models relatively trustworthy for the end-user as well as aiding scientific discovery.
Authors: Zhenyu Tao, Wei Xu, Yongming Huang, Xiaoyun Wang, Xiaohu You
Digital twin, which enables emulation, evaluation, and optimization of physical entities through synchronized digital replicas, has gained increasingly attention as a promising technology for intricate wireless networks. For 6G, numerous innovative wireless technologies and network architectures have posed new challenges in establishing wireless network digital twins. To tackle these challenges, artificial intelligence (AI), particularly the flourishing generative AI, emerges as a potential solution. In this article, we discuss emerging prerequisites for wireless network digital twins considering the complicated network architecture, tremendous network scale, extensive coverage, and diversified application scenarios in the 6G era. We further explore the applications of generative AI, such as transformer and diffusion model, to empower the 6G digital twin from multiple perspectives including implementation, physical-digital synchronization, and slicing capability. Subsequently, we propose a hierarchical generative AI-enabled wireless network digital twin at both the message-level and policy-level, and provide a typical use case with numerical results to validate the effectiveness and efficiency. Finally, open research issues for wireless network digital twins in the 6G era are discussed.
Authors: Seongho Keum, Sanghyun Kim, Soojeong Lee, Juho Lee
Whole slide image (WSI) classification requires repetitive zoom-in and out for pathologists, as only small portions of the slide may be relevant to detecting cancer. Due to the lack of patch-level labels, multiple instance learning (MIL) is a common practice for training a WSI classifier. One of the challenges in MIL for WSIs is the weak supervision coming only from the slide-level labels, often resulting in severe overfitting. In response, researchers have considered adopting patch-level augmentation or applying mixup augmentation, but their applicability remains unverified. Our approach augments the training dataset by sampling a subset of patches in the WSI without significantly altering the underlying semantics of the original slides. Additionally, we introduce an efficient model (Slot-MIL) that organizes patches into a fixed number of slots, the abstract representation of patches, using an attention mechanism. We empirically demonstrate that the subsampling augmentation helps to make more informative slots by restricting the over-concentration of attention and to improve interpretability. Finally, we illustrate that combining our attention-based aggregation model with subsampling and mixup, which has shown limited compatibility in existing MIL methods, can enhance both generalization and calibration. Our proposed methods achieve the state-of-the-art performance across various benchmark datasets including class imbalance and distribution shifts.
Authors: Juan Pablo García Amboage, Eric Wulff, Maria Girone, Tomás F. Pena
Hyperparameter Optimization (HPO) of Deep Learning-based models tends to be a compute resource intensive process as it usually requires to train the target model with many different hyperparameter configurations. We show that integrating model performance prediction with early stopping methods holds great potential to speed up the HPO process of deep learning models. Moreover, we propose a novel algorithm called Swift-Hyperband that can use either classical or quantum support vector regression for performance prediction and benefit from distributed High Performance Computing environments. This algorithm is tested not only for the Machine-Learned Particle Flow model used in High Energy Physics, but also for a wider range of target models from domains such as computer vision and natural language processing. Swift-Hyperband is shown to find comparable (or better) hyperparameters as well as using less computational resources in all test cases.
Authors: Lorenzo Bianchi, Fabio Carrara, Nicola Messina, Claudio Gennaro, Fabrizio Falchi
Recent advancements in large vision-language models enabled visual object detection in open-vocabulary scenarios, where object classes are defined in free-text formats during inference. In this paper, we aim to probe the state-of-the-art methods for open-vocabulary object detection to determine to what extent they understand fine-grained properties of objects and their parts. To this end, we introduce an evaluation protocol based on dynamic vocabulary generation to test whether models detect, discern, and assign the correct fine-grained description to objects in the presence of hard-negative classes. We contribute with a benchmark suite of increasing difficulty and probing different properties like color, pattern, and material. We further enhance our investigation by evaluating several state-of-the-art open-vocabulary object detectors using the proposed protocol and find that most existing solutions, which shine in standard open-vocabulary benchmarks, struggle to accurately capture and distinguish finer object details. We conclude the paper by highlighting the limitations of current methodologies and exploring promising research directions to overcome the discovered drawbacks. Data and code are available at https://github.com/lorebianchi98/FG-OVD.
Authors: Sungbin Shin, Dongyeop Lee, Maksym Andriushchenko, Namhoon Lee
Training an overparameterized neural network can yield minimizers of the same level of training loss and yet different generalization capabilities. With evidence that indicates a correlation between sharpness of minima and their generalization errors, increasing efforts have been made to develop an optimization method to explicitly find flat minima as more generalizable solutions. This sharpness-aware minimization (SAM) strategy, however, has not been studied much yet as to how overparameterization can actually affect its behavior. In this work, we analyze SAM under varying degrees of overparameterization and present both empirical and theoretical results that suggest a critical influence of overparameterization on SAM. Specifically, we first use standard techniques in optimization to prove that SAM can achieve a linear convergence rate under overparameterization in a stochastic setting. We also show that the linearly stable minima found by SAM are indeed flatter and have more uniformly distributed Hessian moments compared to those of SGD. These results are corroborated with our experiments that reveal a consistent trend that the generalization improvement made by SAM continues to increase as the model becomes more overparameterized. We further present that sparsity can open up an avenue for effective overparameterization in practice.
Authors: Gaurav Pendharkar, A.Ancy Micheal, Jason Misquitta, Ranjeesh Kaippada
Tiger conservation necessitates the strategic deployment of multifaceted initiatives encompassing the preservation of ecological habitats, anti-poaching measures, and community involvement for sustainable growth in the tiger population. With the advent of artificial intelligence, tiger surveillance can be automated using object detection. In this paper, an accurate illumination invariant framework is proposed based on EnlightenGAN and YOLOv8 for tiger detection. The fine-tuned YOLOv8 model achieves a mAP score of 61% without illumination enhancement. The illumination enhancement improves the mAP by 0.7%. The approaches elevate the state-of-the-art performance on the ATRW dataset by approximately 6% to 7%.
Authors: Yu Chen, Nivedita Bijlani, Samaneh Kouchaki, Payam Barnaghi
Machine learning enables extracting clinical insights from large temporal datasets. The applications of such machine learning models include identifying disease patterns and predicting patient outcomes. However, limited interpretability poses challenges for deploying advanced machine learning in digital healthcare. Understanding the meaning of latent states is crucial for interpreting machine learning models, assuming they capture underlying patterns. In this paper, we present a concise algorithm that allows for i) interpreting latent states using highly related input features; ii) interpreting predictions using subsets of input features via latent states; and iii) interpreting changes in latent states over time. The proposed algorithm is feasible for any model that is differentiable. We demonstrate that this approach enables the identification of a daytime behavioral pattern for predicting nocturnal behavior in a real-world healthcare dataset.
Authors: Lisheng Wu, Ke Chen
In goal-conditioned reinforcement learning (GCRL), sparse rewards present significant challenges, often obstructing efficient learning. Although multi-step GCRL can boost this efficiency, it can also lead to off-policy biases in target values. This paper dives deep into these biases, categorizing them into two distinct categories: "shooting" and "shifting". Recognizing that certain behavior policies can hasten policy refinement, we present solutions designed to capitalize on the positive aspects of these biases while minimizing their drawbacks, enabling the use of larger step sizes to speed up GCRL. An empirical study demonstrates that our approach ensures a resilient and robust improvement, even in ten-step learning scenarios, leading to superior learning efficiency and performance that generally surpass the baseline and several state-of-the-art multi-step GCRL benchmarks.
Authors: Daan Van Wesenbeeck, Aras Yurtman, Wannes Meert, Hendrik Blockeel
Time Series Motif Discovery (TSMD) refers to the task of identifying patterns that occur multiple times (possibly with minor variations) in a time series. All existing methods for TSMD have one or more of the following limitations: they only look for the two most similar occurrences of a pattern; they only look for patterns of a pre-specified, fixed length; they cannot handle variability along the time axis; and they only handle univariate time series. In this paper, we present a new method, LoCoMotif, that has none of these limitations. The method is motivated by a concrete use case from physiotherapy. We demonstrate the value of the proposed method on this use case. We also introduce a new quantitative evaluation metric for motif discovery, and benchmark data for comparing TSMD methods. LoCoMotif substantially outperforms the existing methods, on top of being more broadly applicable.
Authors: Kumar Kshitij Patel, Lingxiao Wang, Aadirupa Saha, Nati Sebro
We study the problems of distributed online and bandit convex optimization against an adaptive adversary. We aim to minimize the average regret on $M$ machines working in parallel over $T$ rounds with $R$ intermittent communications. Assuming the underlying cost functions are convex and can be generated adaptively, our results show that collaboration is not beneficial when the machines have access to the first-order gradient information at the queried points. This is in contrast to the case for stochastic functions, where each machine samples the cost functions from a fixed distribution. Furthermore, we delve into the more challenging setting of federated online optimization with bandit (zeroth-order) feedback, where the machines can only access values of the cost functions at the queried points. The key finding here is identifying the high-dimensional regime where collaboration is beneficial and may even lead to a linear speedup in the number of machines. We further illustrate our findings through federated adversarial linear bandits by developing novel distributed single and two-point feedback algorithms. Our work is the first attempt towards a systematic understanding of federated online optimization with limited feedback, and it attains tight regret bounds in the intermittent communication setting for both first and zeroth-order feedback. Our results thus bridge the gap between stochastic and adaptive settings in federated online optimization.
Authors: Rudra P.K. Poudel, Harit Pandya, Chao Zhang, Roberto Cipolla
Recent advances in deep reinforcement learning have showcased its potential in tackling complex tasks. However, experiments on visual control tasks have revealed that state-of-the-art reinforcement learning models struggle with out-of-distribution generalization. Conversely, expressing higher-level concepts and global contexts is relatively easy using language.
Building upon recent success of the large language models, our main objective is to improve the state abstraction technique in reinforcement learning by leveraging language for robust action selection. Specifically, we focus on learning language-grounded visual features to enhance the world model learning, a model-based reinforcement learning technique.
To enforce our hypothesis explicitly, we mask out the bounding boxes of a few objects in the image observation and provide the text prompt as descriptions for these masked objects. Subsequently, we predict the masked objects along with the surrounding regions as pixel reconstruction, similar to the transformer-based masked autoencoder approach.
Our proposed LanGWM: Language Grounded World Model achieves state-of-the-art performance in out-of-distribution test at the 100K interaction steps benchmarks of iGibson point navigation tasks. Furthermore, our proposed technique of explicit language-grounded visual representation learning has the potential to improve models for human-robot interaction because our extracted visual features are language grounded.
Authors: Andrea Marinoni, Pietro Lio', Alessandro Barp, Christian Jutten, Mark Girolami
Embedding graphs in continous spaces is a key factor in designing and developing algorithms for automatic information extraction to be applied in diverse tasks (e.g., learning, inferring, predicting). The reliability of graph embeddings directly depends on how much the geometry of the continuous space matches the graph structure. Manifolds are mathematical structure that can enable to incorporate in their topological spaces the graph characteristics, and in particular nodes distances. State-of-the-art of manifold-based graph embedding algorithms take advantage of the assumption that the projection on a tangential space of each point in the manifold (corresponding to a node in the graph) would locally resemble a Euclidean space. Although this condition helps in achieving efficient analytical solutions to the embedding problem, it does not represent an adequate set-up to work with modern real life graphs, that are characterized by weighted connections across nodes often computed over sparse datasets with missing records. In this work, we introduce a new class of manifold, named soft manifold, that can solve this situation. In particular, soft manifolds are mathematical structures with spherical symmetry where the tangent spaces to each point are hypocycloids whose shape is defined according to the velocity of information propagation across the data points. Using soft manifolds for graph embedding, we can provide continuous spaces to pursue any task in data analysis over complex datasets. Experimental results on reconstruction tasks on synthetic and real datasets show how the proposed approach enable more accurate and reliable characterization of graphs in continuous spaces with respect to the state-of-the-art.
Authors: Martin Wistuba, Prabhu Teja Sivaprasad, Lukas Balles, Giovanni Zappella
Recent work using pretrained transformers has shown impressive performance when fine-tuned with data from the downstream problem of interest. However, they struggle to retain that performance when the data characteristics changes. In this paper, we focus on continual learning, where a pre-trained transformer is updated to perform well on new data, while retaining its performance on data it was previously trained on. Earlier works have tackled this primarily through methods inspired from prompt tuning. We question this choice, and investigate the applicability of Low Rank Adaptation (LoRA) to continual learning. On a range of domain-incremental learning benchmarks, our LoRA-based solution, CoLoR, yields state-of-the-art performance, while still being as parameter efficient as the prompt tuning based methods.
Authors: Xiaoyue Mi, Fan Tang, Yepeng Weng, Danding Wang, Juan Cao, Sheng Tang, Peng Li, Yang Liu
Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i.e., accuracy on natural samples has reduced significantly. In this study, we reveal that natural accuracy degradation is highly related to the disruption of the natural sample topology in the representation space by quantitative and qualitative experiments. Based on this observation, we propose Topology-pReserving Adversarial traINing (TRAIN) to alleviate the problem by preserving the topology structure of natural samples from a standard model trained only on natural samples during adversarial training. As an additional regularization, our method can easily be combined with various popular adversarial training algorithms in a plug-and-play manner, taking advantage of both sides. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny ImageNet show that our proposed method achieves consistent and significant improvements over various strong baselines in most cases. Specifically, without additional data, our proposed method achieves up to 8.78% improvement in natural accuracy and 4.50% improvement in robust accuracy.
Authors: Xiaoyue Mi, Fan Tang, Zonghan Yang, Danding Wang, Juan Cao, Peng Li, Yang Liu
Despite the remarkable advances that have been made in continual learning, the adversarial vulnerability of such methods has not been fully discussed. We delve into the adversarial robustness of memory-based continual learning algorithms and observe limited robustness improvement by directly applying adversarial training techniques. Preliminary studies reveal the twin challenges for building adversarial robust continual learners: accelerated forgetting in continual learning and gradient obfuscation in adversarial robustness. In this study, we put forward a novel adversarial robust memory-based continual learner that adjusts data logits to mitigate the forgetting of pasts caused by adversarial samples. Furthermore, we devise a gradient-based data selection mechanism to overcome the gradient obfuscation caused by limited stored data. The proposed approach can widely integrate with existing memory-based continual learning as well as adversarial training algorithms in a plug-and-play way. Extensive experiments on Split-CIFAR10/100 and Split-Tiny-ImageNet demonstrate the effectiveness of our approach, achieving up to 8.13% higher accuracy for adversarial data.
Authors: Andrey Voynov, Amir Hertz, Moab Arar, Shlomi Fruchter, Daniel Cohen-Or
State-of-the-art diffusion models can generate highly realistic images based on various conditioning like text, segmentation, and depth. However, an essential aspect often overlooked is the specific camera geometry used during image capture. The influence of different optical systems on the final scene appearance is frequently overlooked. This study introduces a framework that intimately integrates a text-to-image diffusion model with the particular lens geometry used in image rendering. Our method is based on a per-pixel coordinate conditioning method, enabling the control over the rendering geometry. Notably, we demonstrate the manipulation of curvature properties, achieving diverse visual effects, such as fish-eye, panoramic views, and spherical texturing using a single diffusion model.
Authors: Xianlun Peng, Yang Tang, Fangfei Li, Yang Liu
In this paper, we present a reinforcement learning (RL) method for solving optimal false data injection attack problems in probabilistic Boolean control networks (PBCNs) where the attacker lacks knowledge of the system model. Specifically, we employ a Q-learning (QL) algorithm to address this problem. We then propose an improved QL algorithm that not only enhances learning efficiency but also obtains optimal attack strategies for large-scale PBCNs that the standard QL algorithm cannot handle. Finally, we verify the effectiveness of our proposed approach by considering two attacked PBCNs, including a 10-node network and a 28-node network.
Authors: Tong Xiao, Jingbo Zhu
Transformers have dominated empirical machine learning models of natural language processing. In this paper, we introduce basic concepts of Transformers and present key techniques that form the recent advances of these models. This includes a description of the standard Transformer architecture, a series of model refinements, and common applications. Given that Transformers and related deep learning techniques might be evolving in ways we have never seen, we cannot dive into all the model details or cover all the technical areas. Instead, we focus on just those concepts that are helpful for gaining a good understanding of Transformers and their variants. We also summarize the key ideas that impact this field, thereby yielding some insights into the strengths and limitations of these models.
Authors: Haiyan Wang
Feature selection is critical in machine learning to reduce dimensionality and improve model accuracy and efficiency. The exponential growth in feature space dimensionality for modern datasets directly results in ambiguous samples and redundant features, which can severely degrade classification accuracy. Quantum machine learning offers potential advantages for addressing this challenge. In this paper, we propose a novel method, quantum support vector machine feature selection (QSVMF), integrating quantum support vector machines with multi-objective genetic algorithm. QSVMF optimizes multiple simultaneous objectives: maximizing classification accuracy, minimizing selected features and quantum circuit costs, and reducing feature covariance. We apply QSVMF for feature selection on a breast cancer dataset, comparing the performance of QSVMF against classical approaches with the selected features. Experimental results show that QSVMF achieves superior performance. Furthermore, The Pareto front solutions of QSVMF enable analysis of accuracy versus feature set size trade-offs, identifying extremely sparse yet accurate feature subsets. We contextualize the biological relevance of the selected features in terms of known breast cancer biomarkers. This work highlights the potential of quantum-based feature selection to enhance machine learning efficiency and performance on complex real-world data.
Authors: Javier E. Santos, Yen Ting Lin
The aim of this short note is to show that Denoising Diffusion Probabilistic Model DDPM, a non-homogeneous discrete-time Markov process, can be represented by a time-homogeneous continuous-time Markov process observed at non-uniformly sampled discrete times. Surprisingly, this continuous-time Markov process is the well-known and well-studied Ornstein-Ohlenbeck (OU) process, which was developed in 1930's for studying Brownian particles in Harmonic potentials. We establish the formal equivalence between DDPM and the OU process using its analytical solution. We further demonstrate that the design problem of the noise scheduler for non-homogeneous DDPM is equivalent to designing observation times for the OU process. We present several heuristic designs for observation times based on principled quantities such as auto-variance and Fisher Information and connect them to ad hoc noise schedules for DDPM. Interestingly, we show that the Fisher-Information-motivated schedule corresponds exactly the cosine schedule, which was developed without any theoretical foundation but is the current state-of-the-art noise schedule.
Authors: Amr Gomaa, Bilal Mahdy, Niko Kleer, Antonio Krüger
Robotic-assisted surgical systems have demonstrated significant potential in enhancing surgical precision and minimizing human errors. However, existing systems lack the ability to accommodate the unique preferences and requirements of individual surgeons. Additionally, they primarily focus on general surgeries (e.g., laparoscopy) and are not suitable for highly precise microsurgeries, such as ophthalmic procedures. Thus, we propose a simulation-based image-guided approach for surgeon-centered autonomous agents that can adapt to the individual surgeon's skill level and preferred surgical techniques during ophthalmic cataract surgery. Our approach utilizes a simulated environment to train reinforcement and imitation learning agents guided by image data to perform all tasks of the incision phase of cataract surgery. By integrating the surgeon's actions and preferences into the training process with the surgeon-in-the-loop, our approach enables the robot to implicitly learn and adapt to the individual surgeon's unique approach through demonstrations. This results in a more intuitive and personalized surgical experience for the surgeon. Simultaneously, it ensures consistent performance for the autonomous robotic apprentice. We define and evaluate the effectiveness of our approach using our proposed metrics; and highlight the trade-off between a generic agent and a surgeon-centered adapted agent. Moreover, our approach has the potential to extend to other ophthalmic surgical procedures, opening the door to a new generation of surgeon-in-the-loop autonomous surgical robots. We provide an open-source simulation framework for future development and reproducibility.
Authors: Jia Li, Lijie Hu, Jingfeng Zhang, Tianhang Zheng, Hua Zhang, Di Wang
In this paper, we address the limitations of existing text-to-image diffusion models in generating demographically fair results when given human-related descriptions. These models often struggle to disentangle the target language context from sociocultural biases, resulting in biased image generation. To overcome this challenge, we propose Fair Mapping, a general, model-agnostic, and lightweight approach that modifies a pre-trained text-to-image model by controlling the prompt to achieve fair image generation. One key advantage of our approach is its high efficiency. The training process only requires updating a small number of parameters in an additional linear mapping network. This not only reduces the computational cost but also accelerates the optimization process. We first demonstrate the issue of bias in generated results caused by language biases in text-guided diffusion models. By developing a mapping network that projects language embeddings into an unbiased space, we enable the generation of relatively balanced demographic results based on a keyword specified in the prompt. With comprehensive experiments on face image generation, we show that our method significantly improves image generation performance when prompted with descriptions related to human faces. By effectively addressing the issue of bias, we produce more fair and diverse image outputs. This work contributes to the field of text-to-image generation by enhancing the ability to generate images that accurately reflect the intended demographic characteristics specified in the text.
Authors: Chi-Pin Huang, Kai-Po Chang, Chung-Ting Tsai, Yung-Hsuan Lai, Yu-Chiang Frank Wang
Concept erasure in text-to-image diffusion models aims to disable pre-trained diffusion models from generating images related to a target concept. To perform reliable concept erasure, the properties of robustness and locality are desirable. The former refrains the model from producing images associated with the target concept for any paraphrased or learned prompts, while the latter preserves the model ability in generating images for non-target concepts. In this paper, we propose Reliable Concept Erasing via Lightweight Erasers (Receler), which learns a lightweight Eraser to perform concept erasing and enhances locality and robustness with the proposed concept-localized regularization and adversarial prompt learning, respectively. Comprehensive quantitative and qualitative experiments with various concept prompts verify the superiority of Receler over the previous erasing methods on the above two desirable properties.
Authors: Tanmay Chavan, Shantanu Patankar, Aditya Kane, Omkar Gokhale, Geetanjali Kale, Raviraj Joshi
Contrastive learning has proven to be an effective method for pre-training models using weakly labeled data in the vision domain. Sentence transformers are the NLP counterparts to this architecture, and have been growing in popularity due to their rich and effective sentence representations. Having effective sentence representations is paramount in multiple tasks, such as information retrieval, retrieval augmented generation (RAG), and sentence comparison. Keeping in mind the deployability factor of transformers, evaluating the robustness of sentence transformers is of utmost importance. This work focuses on evaluating the robustness of the sentence encoders. We employ several adversarial attacks to evaluate its robustness. This system uses character-level attacks in the form of random character substitution, word-level attacks in the form of synonym replacement, and sentence-level attacks in the form of intra-sentence word order shuffling. The results of the experiments strongly undermine the robustness of sentence encoders. The models produce significantly different predictions as well as embeddings on perturbed datasets. The accuracy of the models can fall up to 15 percent on perturbed datasets as compared to unperturbed datasets. Furthermore, the experiments demonstrate that these embeddings does capture the semantic and syntactic structure (sentence order) of sentences. However, existing supervised classification strategies fail to leverage this information, and merely function as n-gram detectors.
Authors: Aymen Sadraoui (OPIS, CVN), Ségolène Martin (OPIS, CVN), Eliott Barbot (OPIS, CVN), Astrid Laurent-Bellue, Jean-Christophe Pesquet (OPIS, CVN), Catherine Guettier, Ismail Ben Ayed (ETS)
This paper presents a new approach for classifying 2D histopathology patches using few-shot learning. The method is designed to tackle a significant challenge in histopathology, which is the limited availability of labeled data. By applying a sliding window technique to histopathology slides, we illustrate the practical benefits of transductive learning (i.e., making joint predictions on patches) to achieve consistent and accurate classification. Our approach involves an optimization-based strategy that actively penalizes the prediction of a large number of distinct classes within each window. We conducted experiments on histopathological data to classify tissue classes in digital slides of liver cancer, specifically hepatocellular carcinoma. The initial results show the effectiveness of our method and its potential to enhance the process of automated cancer diagnosis and treatment, all while reducing the time and effort required for expert annotation.
Authors: Gergely Dániel Németh, Miguel Ángel Lozano, Novi Quadrianto, Nuria Oliver
Federated Learning (FL) has been proposed as a privacy-preserving solution for machine learning. However, recent works have shown that Federated Learning can leak private client data through membership attacks. In this paper, we show that the effectiveness of these attacks on the clients negatively correlates with the size of the client datasets and model complexity. Based on this finding, we propose model-agnostic Federated Learning as a privacy-enhancing solution because it enables the use of models of varying complexity in the clients. To this end, we present $\texttt{MaPP-FL}$, a novel privacy-aware FL approach that leverages model compression on the clients while keeping a full model on the server. We compare the performance of $\texttt{MaPP-FL}$ against state-of-the-art model-agnostic FL methods on the CIFAR-10, CIFAR-100, and FEMNIST vision datasets. Our experiments show the effectiveness of $\texttt{MaPP-FL}$ in preserving the clients' and the server's privacy while achieving competitive classification accuracies.
Authors: Yutong Wang, Clayton Scott
The notion of margin loss has been central to the development and analysis of algorithms for binary classification. To date, however, there remains no consensus as to the analogue of the margin loss for multiclass classification. In this work, we show that a broad range of multiclass loss functions, including many popular ones, can be expressed in the relative margin form, a generalization of the margin form of binary losses. The relative margin form is broadly useful for understanding and analyzing multiclass losses as shown by our prior work (Wang and Scott, 2020, 2021). To further demonstrate the utility of this way of expressing multiclass losses, we use it to extend the seminal result of Bartlett et al. (2006) on classification-calibration of binary margin losses to multiclass. We then analyze the class of Fenchel-Young losses, and expand the set of these losses that are known to be classification-calibrated.
Authors: Yong-Min Shin, Won-Yong Shin
Recent studies attempted to utilize multilayer perceptrons (MLPs) to solve semisupervised node classification on graphs, by training a student MLP by knowledge distillation from a teacher graph neural network (GNN). While previous studies have focused mostly on training the student MLP by matching the output probability distributions between the teacher and student models during distillation, it has not been systematically studied how to inject the structural information in an explicit and interpretable manner. Inspired by GNNs that separate feature transformation $T$ and propagation $\Pi$, we re-frame the distillation process as making the student MLP learn both $T$ and $\Pi$. Although this can be achieved by applying the inverse propagation $\Pi^{-1}$ before distillation from the teacher, it still comes with a high computational cost from large matrix multiplications during training. To solve this problem, we propose Propagate & Distill (P&D), which propagates the output of the teacher before distillation, which can be interpreted as an approximate process of the inverse propagation. We demonstrate that P&D can readily improve the performance of the student MLP.
High-dimensional imbalanced data poses a machine learning challenge. In the absence of sufficient or high-quality labels, unsupervised feature selection methods are crucial for the success of subsequent algorithms. Therefore, there is a growing need for unsupervised feature selection algorithms focused on imbalanced data. Thus, we propose a Marginal Laplacian Score (MLS) a modification of the well-known Laplacian Score (LS) to be better suited for imbalance data. We introduce an assumption that the minority class or anomalous appear more frequently in the margin of the features. Consequently, MLS aims to preserve the local structure of the data set's margin. As MLS is better suited for handling imbalanced data, we propose its integration into modern feature selection methods that utilize the Laplacian score. We integrate the MLS algorithm into the Differentiable Unsupervised Feature Selection (DUFS), resulting in DUFS-MLS. The proposed methods demonstrate robust and improved performance on synthetic and public data sets.
Authors: L. Jeff Hong, Yanxi Hou, Qingkai Zhang, Xiaowei Zhang
Stochastic simulation models, while effective in capturing the dynamics of complex systems, are often too slow to run for real-time decision-making. Metamodeling techniques are widely used to learn the relationship between a summary statistic of the outputs (e.g., the mean or quantile) and the inputs of the simulator, so that it can be used in real time. However, this methodology requires the knowledge of an appropriate summary statistic in advance, making it inflexible for many practical situations. In this paper, we propose a new metamodeling concept, called generative metamodeling, which aims to construct a "fast simulator of the simulator". This technique can generate random outputs substantially faster than the original simulation model, while retaining an approximately equal conditional distribution given the same inputs. Once constructed, a generative metamodel can instantaneously generate a large amount of random outputs as soon as the inputs are specified, thereby facilitating the immediate computation of any summary statistic for real-time decision-making. Furthermore, we propose a new algorithm -- quantile-regression-based generative metamodeling (QRGMM) -- and study its convergence and rate of convergence. Extensive numerical experiments are conducted to investigate the empirical performance of QRGMM, compare it with other state-of-the-art generative algorithms, and demonstrate its usefulness in practical real-time decision-making.
Authors: Farbin Fayza, Cansu Demirkiran, Hanning Chen, Che-Kai Liu, Avi Mohan, Hamza Errahmouni, Sanggeon Yun, Mohsen Imani, David Zhang, Darius Bunandar, Ajay Joshi
Over the past few years, silicon photonics-based computing has emerged as a promising alternative to CMOS-based computing for Deep Neural Networks (DNN). Unfortunately, the non-linear operations and the high-precision requirements of DNNs make it extremely challenging to design efficient silicon photonics-based systems for DNN inference and training. Hyperdimensional Computing (HDC) is an emerging, brain-inspired machine learning technique that enjoys several advantages over existing DNNs, including being lightweight, requiring low-precision operands, and being robust to noise introduced by the nonidealities in the hardware. For HDC, computing in-memory (CiM) approaches have been widely used, as CiM reduces the data transfer cost if the operands can fit into the memory. However, inefficient multi-bit operations, high write latency, and low endurance make CiM ill-suited for HDC. On the other hand, the existing electro-photonic DNN accelerators are inefficient for HDC because they are specifically optimized for matrix multiplication in DNNs and consume a lot of power with high-precision data converters.
In this paper, we argue that photonic computing and HDC complement each other better than photonic computing and DNNs, or CiM and HDC. We propose PhotoHDC, the first-ever electro-photonic accelerator for HDC training and inference, supporting the basic, record-based, and graph encoding schemes. Evaluating with popular datasets, we show that our accelerator can achieve two to five orders of magnitude lower EDP than the state-of-the-art electro-photonic DNN accelerators for implementing HDC training and inference. PhotoHDC also achieves four orders of magnitude lower energy-delay product than CiM-based accelerators for both HDC training and inference.
Authors: Maximilian Augustin, Yannic Neuhaus, Matthias Hein
While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how reliably these classifiers work in the wild. Furthermore, for safety-critical tasks the black-box nature of their decisions is problematic, and explanations or at least methods which make decisions plausible are needed urgently. In this paper, we address these problems by generating images that optimize a classifier-derived objective using a framework for guided image generation. We analyze the behavior and decisions of image classifiers by visual counterfactual explanations (VCEs), detection of systematic mistakes by analyzing images where classifiers maximally disagree, and visualization of neurons to verify potential spurious features. In this way, we validate existing observations, e.g. the shape bias of adversarially robust models, as well as novel failure modes, e.g. systematic errors of zero-shot CLIP classifiers, or identify harmful spurious features. Moreover, our VCEs outperform previous work while being more versatile.
Authors: Ainesh Bakshi, Vincent Cohen-Addad, Samuel B. Hopkins, Rajesh Jayaram, Silvio Lattanzi
Multi-dimensional Scaling (MDS) is a family of methods for embedding pair-wise dissimilarities between $n$ objects into low-dimensional space. MDS is widely used as a data visualization tool in the social and biological sciences, statistics, and machine learning. We study the Kamada-Kawai formulation of MDS: given a set of non-negative dissimilarities $\{d_{i,j}\}_{i , j \in [n]}$ over $n$ points, the goal is to find an embedding $\{x_1,\dots,x_n\} \subset \mathbb{R}^k$ that minimizes \[ \text{OPT} = \min_{x} \mathbb{E}_{i,j \in [n]} \left[ \left(1-\frac{\|x_i - x_j\|}{d_{i,j}}\right)^2 \right] \]
Despite its popularity, our theoretical understanding of MDS is extremely limited. Recently, Demaine, Hesterberg, Koehler, Lynch, and Urschel (arXiv:2109.11505) gave the first approximation algorithm with provable guarantees for Kamada-Kawai, which achieves an embedding with cost $\text{OPT} +\epsilon$ in $n^2 \cdot 2^{\tilde{\mathcal{O}}(k \Delta^4 / \epsilon^2)}$ time, where $\Delta$ is the aspect ratio of the input dissimilarities. In this work, we give the first approximation algorithm for MDS with quasi-polynomial dependency on $\Delta$: for target dimension $k$, we achieve a solution with cost $\mathcal{O}(\text{OPT}^{ \hspace{0.04in}1/k } \cdot \log(\Delta/\epsilon) )+ \epsilon$ in time $n^{ \mathcal{O}(1)} \cdot 2^{\tilde{\mathcal{O}}( k^2 (\log(\Delta)/\epsilon)^{k/2 + 1} ) }$.
Our approach is based on a novel analysis of a conditioning-based rounding scheme for the Sherali-Adams LP Hierarchy. Crucially, our analysis exploits the geometry of low-dimensional Euclidean space, allowing us to avoid an exponential dependence on the aspect ratio $\Delta$. We believe our geometry-aware treatment of the Sherali-Adams Hierarchy is an important step towards developing general-purpose techniques for efficient metric optimization algorithms.
Authors: Yingdong Hu, Fanqi Lin, Tong Zhang, Li Yi, Yang Gao
In this study, we are interested in imbuing robots with the capability of physically-grounded task planning. Recent advancements have shown that large language models (LLMs) possess extensive knowledge useful in robotic tasks, especially in reasoning and planning. However, LLMs are constrained by their lack of world grounding and dependence on external affordance models to perceive environmental information, which cannot jointly reason with LLMs. We argue that a task planner should be an inherently grounded, unified multimodal system. To this end, we introduce Robotic Vision-Language Planning (ViLa), a novel approach for long-horizon robotic planning that leverages vision-language models (VLMs) to generate a sequence of actionable steps. ViLa directly integrates perceptual data into its reasoning and planning process, enabling a profound understanding of commonsense knowledge in the visual world, including spatial layouts and object attributes. It also supports flexible multimodal goal specification and naturally incorporates visual feedback. Our extensive evaluation, conducted in both real-robot and simulated environments, demonstrates ViLa's superiority over existing LLM-based planners, highlighting its effectiveness in a wide array of open-world manipulation tasks.
Authors: Filippo Guerranti, Zinuo Yi, Anna Starovoit, Rafiq Kamel, Simon Geisler, Stephan Günnemann
Contrastive learning (CL) has emerged as a powerful framework for learning representations of images and text in a self-supervised manner while enhancing model robustness against adversarial attacks. More recently, researchers have extended the principles of contrastive learning to graph-structured data, giving birth to the field of graph contrastive learning (GCL). However, whether GCL methods can deliver the same advantages in adversarial robustness as their counterparts in the image and text domains remains an open question. In this paper, we introduce a comprehensive robustness evaluation protocol tailored to assess the robustness of GCL models. We subject these models to adaptive adversarial attacks targeting the graph structure, specifically in the evasion scenario. We evaluate node and graph classification tasks using diverse real-world datasets and attack strategies. With our work, we aim to offer insights into the robustness of GCL methods and hope to open avenues for potential future research directions.
Authors: Amin Rakhsha, Mete Kemertas, Mohammad Ghavamzadeh, Amir-massoud Farahmand
We propose and theoretically analyze an approach for planning with an approximate model in reinforcement learning that can reduce the adverse impact of model error. If the model is accurate enough, it accelerates the convergence to the true value function too. One of its key components is the MaxEnt Model Correction (MoCo) procedure that corrects the model's next-state distributions based on a Maximum Entropy density estimation formulation. Based on MoCo, we introduce the Model Correcting Value Iteration (MoCoVI) algorithm, and its sampled-based variant MoCoDyna. We show that MoCoVI and MoCoDyna's convergence can be much faster than the conventional model-free algorithms. Unlike traditional model-based algorithms, MoCoVI and MoCoDyna effectively utilize an approximate model and still converge to the correct value function.
Authors: Puja Trivedi, Ryan Rossi, David Arbour, Tong Yu, Franck Dernoncourt, Sungchul Kim, Nedim Lipka, Namyong Park, Nesreen K. Ahmed, Danai Koutra
Most real-world networks are noisy and incomplete samples from an unknown target distribution. Refining them by correcting corruptions or inferring unobserved regions typically improves downstream performance. Inspired by the impressive generative capabilities that have been used to correct corruptions in images, and the similarities between "in-painting" and filling in missing nodes and edges conditioned on the observed graph, we propose a novel graph generative framework, SGDM, which is based on subgraph diffusion. Our framework not only improves the scalability and fidelity of graph diffusion models, but also leverages the reverse process to perform novel, conditional generation tasks. In particular, through extensive empirical analysis and a set of novel metrics, we demonstrate that our proposed model effectively supports the following refinement tasks for partially observable networks: T1: denoising extraneous subgraphs, T2: expanding existing subgraphs and T3: performing "style" transfer by regenerating a particular subgraph to match the characteristics of a different node or subgraph.
Authors: Zhan Yu, Daniel W. C. Ho
This paper is concerned with functional learning by utilizing two-stage sampled distribution regression. We study a multi-penalty regularization algorithm for distribution regression under the framework of learning theory. The algorithm aims at regressing to real valued outputs from probability measures. The theoretical analysis on distribution regression is far from maturity and quite challenging, since only second stage samples are observable in practical setting. In the algorithm, to transform information from samples, we embed the distributions to a reproducing kernel Hilbert space $\mathcal{H}_K$ associated with Mercer kernel $K$ via mean embedding technique. The main contribution of the paper is to present a novel multi-penalty regularization algorithm to capture more features of distribution regression and derive optimal learning rates for the algorithm. The work also derives learning rates for distribution regression in the nonstandard setting $f_{\rho}\notin\mathcal{H}_K$, which is not explored in existing literature. Moreover, we propose a distribution regression-based distributed learning algorithm to face large-scale data or information challenge. The optimal learning rates are derived for the distributed learning algorithm. By providing new algorithms and showing their learning rates, we improve the existing work in different aspects in the literature.
Authors: Burhaneddin Yaman, Seyed Amir Hossein Hosseini, Mehmet Akçakaya
Deep learning (DL) has emerged as a powerful tool for accelerated MRI reconstruction, but often necessitates a database of fully-sampled measurements for training. Recent self-supervised and unsupervised learning approaches enable training without fully-sampled data. However, a database of undersampled measurements may not be available in many scenarios, especially for scans involving contrast or translational acquisitions in development. Moreover, recent studies show that database-trained models may not generalize well when the unseen measurements differ in terms of sampling pattern, acceleration rate, SNR, image contrast, and anatomy. Such challenges necessitate a new methodology to enable subject-specific DL MRI reconstruction without external training datasets, since it is clinically imperative to provide high-quality reconstructions that can be used to identify lesions/disease for \emph{every individual}. In this work, we propose a zero-shot self-supervised learning approach to perform subject-specific accelerated DL MRI reconstruction to tackle these issues. The proposed approach partitions the available measurements from a single scan into three disjoint sets. Two of these sets are used to enforce data consistency and define loss during training for self-supervision, while the last set serves to self-validate, establishing an early stopping criterion. In the presence of models pre-trained on a database with different image characteristics, we show that the proposed approach can be combined with transfer learning for faster convergence time and reduced computational complexity. The code is available at \url{https://github.com/byaman14/ZS-SSL}.
Authors: Bernard Koch, Tim Sainburg, Pablo Geraldo, Song Jiang, Yizhou Sun, Jacob Gates Foster
This review systematizes the emerging literature for causal inference using deep neural networks under the potential outcomes framework. It provides an intuitive introduction on how deep learning can be used to estimate/predict heterogeneous treatment effects and extend causal inference to settings where confounding is non-linear, time varying, or encoded in text, networks, and images. To maximize accessibility, we also introduce prerequisite concepts from causal inference and deep learning. The survey differs from other treatments of deep learning and causal inference in its sharp focus on observational causal estimation, its extended exposition of key algorithms, and its detailed tutorials for implementing, training, and selecting among deep estimators in Tensorflow 2 available at github.com/kochbj/Deep-Learning-for-Causal-Inference.
Authors: Tzvi Diskin, Yonina C. Eldar, Ami Wiesel
The Gauss Markov theorem states that the weighted least squares estimator is a linear minimum variance unbiased estimation (MVUE) in linear models. In this paper, we take a first step towards extending this result to non linear settings via deep learning with bias constraints. The classical approach to designing non-linear MVUEs is through maximum likelihood estimation (MLE) which often involves computationally challenging optimizations. On the other hand, deep learning methods allow for non-linear estimators with fixed computational complexity. Learning based estimators perform optimally on average with respect to their training set but may suffer from significant bias in other parameters. To avoid this, we propose to add a simple bias constraint to the loss function, resulting in an estimator we refer to as Bias Constrained Estimator (BCE). We prove that this yields asymptotic MVUEs that behave similarly to the classical MLEs and asymptotically attain the Cramer Rao bound. We demonstrate the advantages of our approach in the context of signal to noise ratio estimation as well as covariance estimation. A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance. Examples include distributed sensor networks and data augmentation in test-time. In such applications, we show that BCE leads to asymptotically consistent estimators.
Authors: Wenxi Wang, Yang Hu, Mohit Tiwari, Sarfraz Khurshid, Kenneth McMillan, Risto Miikkulainen
Propositional satisfiability (SAT) is an NP-complete problem that impacts many research fields, such as planning, verification, and security. Mainstream modern SAT solvers are based on the Conflict-Driven Clause Learning (CDCL) algorithm. Recent work aimed to enhance CDCL SAT solvers using Graph Neural Networks (GNNs). However, so far this approach either has not made solving more effective, or required substantial GPU resources for frequent online model inferences. Aiming to make GNN improvements practical, this paper proposes an approach called NeuroBack, which builds on two insights: (1) predicting phases (i.e., values) of variables appearing in the majority (or even all) of the satisfying assignments are essential for CDCL SAT solving, and (2) it is sufficient to query the neural model only once for the predictions before the SAT solving starts. Once trained, the offline model inference allows NeuroBack to execute exclusively on the CPU, removing its reliance on GPU resources. To train NeuroBack, a new dataset called DataBack containing 120,286 data samples is created. Finally, NeuroBack is implemented as an enhancement to a state-of-the-art SAT solver called Kissat. As a result, it allowed Kissat to solve 5.2% more problems on the recent SAT competition problem set, SATCOMP-2022. NeuroBack therefore shows how machine learning can be harnessed to improve SAT solving in an effective and practical manner.
Authors: Changho Shin, Winfred Li, Harit Vishwakarma, Nicholas Roberts, Frederic Sala
Weak supervision (WS) frameworks are a popular way to bypass hand-labeling large datasets for training data-hungry models. These approaches synthesize multiple noisy but cheaply-acquired estimates of labels into a set of high-quality pseudolabels for downstream training. However, the synthesis technique is specific to a particular kind of label, such as binary labels or sequences, and each new label type requires manually designing a new synthesis algorithm. Instead, we propose a universal technique that enables weak supervision over any label type while still offering desirable properties, including practical flexibility, computational efficiency, and theoretical guarantees. We apply this technique to important problems previously not tackled by WS frameworks including learning to rank, regression, and learning in hyperbolic space. Theoretically, our synthesis approach produces a consistent estimators for learning some challenging but important generalizations of the exponential family model. Experimentally, we validate our framework and show improvement over baselines in diverse settings including real-world learning-to-rank and regression problems along with learning on hyperbolic manifolds.
Authors: Elias Wirth, Sebastian Pokutta
The vanishing ideal of a set of points $X\subseteq \mathbb{R}^n$ is the set of polynomials that evaluate to $0$ over all points $\mathbf{x} \in X$ and admits an efficient representation by a finite set of polynomials called generators. To accommodate the noise in the data set, we introduce the pairwise conditional gradients approximate vanishing ideal algorithm (PCGAVI) that constructs a set of generators of the approximate vanishing ideal. The constructed generators capture polynomial structures in data and give rise to a feature map that can, for example, be used in combination with a linear classifier for supervised learning. In PCGAVI, we construct the set of generators by solving constrained convex optimization problems with the pairwise conditional gradients algorithm. Thus, PCGAVI not only constructs few but also sparse generators, making the corresponding feature transformation robust and compact. Furthermore, we derive several learning guarantees for PCGAVI that make the algorithm theoretically better motivated than related generator-constructing methods.
Authors: Jin-Ju Wang, Nicolas Dobigeon, Marie Chabert, Ding-Cheng Wang, Ting-Zhu Huang, Jie Huang
In the context of Earth observation, change detection boils down to comparing images acquired at different times by sensors of possibly different spatial and/or spectral resolutions or different modalities (e.g., optical or radar). Even when considering only optical images, this task has proven to be challenging as soon as the sensors differ by their spatial and/or spectral resolutions. This paper proposes a novel unsupervised change detection method dedicated to images acquired by such so-called heterogeneous optical sensors. It capitalizes on recent advances which formulate the change detection task into a robust fusion framework. Adopting this formulation, the work reported in this paper shows that any off-the-shelf network trained beforehand to fuse optical images of different spatial and/or spectral resolutions can be easily complemented with a network of the same architecture and embedded into an adversarial framework to perform change detection. A comparison with state-of-the-art change detection methods demonstrates the versatility and the effectiveness of the proposed approach.
Authors: Jevgenija Rudzusika, Buda Bajić, Thomas Koehler, Ozan Öktem
Deep learning based computed tomography (CT) reconstruction has demonstrated outstanding performance on simulated 2D low-dose CT data. This applies in particular to domain adapted neural networks, which incorporate a handcrafted physics model for CT imaging. Empirical evidence shows that employing such architectures reduces the demand for training data and improves upon generalisation. However, their training requires large computational resources that quickly become prohibitive in 3D helical CT, which is the most common acquisition geometry used for medical imaging. Furthermore, clinical data also comes with other challenges not accounted for in simulations, like errors in flux measurement, resolution mismatch and, most importantly, the absence of the real ground truth. The necessity to have a computationally feasible training combined with the need to address these issues has made it difficult to evaluate deep learning based reconstruction on clinical 3D helical CT. This paper modifies a domain adapted neural network architecture, the Learned Primal-Dual (LPD), so that it can be trained and applied to reconstruction in this setting. We achieve this by splitting the helical trajectory into sections and applying the unrolled LPD iterations to those sections sequentially. To the best of our knowledge, this work is the first to apply an unrolled deep learning architecture for reconstruction on full-sized clinical data, like those in the Low dose CT image and projection data set (LDCT). Moreover, training and testing is done on a single GPU card with 24GB of memory.
Authors: Krzysztof Kacprzyk, Zhaozhi Qian, Mihaela van der Schaar
Closed-form differential equations, including partial differential equations and higher-order ordinary differential equations, are one of the most important tools used by scientists to model and better understand natural phenomena. Discovering these equations directly from data is challenging because it requires modeling relationships between various derivatives that are not observed in the data (equation-data mismatch) and it involves searching across a huge space of possible equations. Current approaches make strong assumptions about the form of the equation and thus fail to discover many well-known systems. Moreover, many of them resolve the equation-data mismatch by estimating the derivatives, which makes them inadequate for noisy and infrequently sampled systems. To this end, we propose D-CIPHER, which is robust to measurement artifacts and can uncover a new and very general class of differential equations. We further design a novel optimization procedure, CoLLie, to help D-CIPHER search through this class efficiently. Finally, we demonstrate empirically that it can discover many well-known equations that are beyond the capabilities of current methods.
Authors: Zhichun Guo, Kehan Guo, Bozhao Nan, Yijun Tian, Roshni G. Iyer, Yihong Ma, Olaf Wiest, Xiangliang Zhang, Wei Wang, Chuxu Zhang, Nitesh V. Chawla
Molecular representation learning (MRL) is a key step to build the connection between machine learning and chemical science. In particular, it encodes molecules as numerical vectors preserving the molecular structures and features, on top of which the downstream tasks (e.g., property prediction) can be performed. Recently, MRL has achieved considerable progress, especially in methods based on deep molecular graph learning. In this survey, we systematically review these graph-based molecular representation techniques, especially the methods incorporating chemical domain knowledge. Specifically, we first introduce the features of 2D and 3D molecular graphs. Then we summarize and categorize MRL methods into three groups based on their input. Furthermore, we discuss some typical chemical applications supported by MRL. To facilitate studies in this fast-developing area, we also list the benchmarks and commonly used datasets in the paper. Finally, we share our thoughts on future research directions.
Authors: Bryce McLaughlin, Jann Spiess
When we use algorithms to produce risk assessments, we typically think of these predictions as providing helpful input to human decisions, such as when risk scores are presented to judges or doctors. But when a decision-maker obtains algorithmic assistance, they may not only react to the information. The decision-maker may view the input of the algorithm as recommending a default action, making it costly for them to deviate, such as when a judge is reluctant to overrule a high-risk assessment of a defendant or a doctor fears the consequences of deviating from recommended procedures. In this article, we propose a principal-agent model of joint human-machine decision-making. Within this model, we consider the effect and design of algorithmic recommendations when they affect choices not just by shifting beliefs, but also by altering preferences. We motivate this assumption from institutional factors, such as a desire to avoid audits, as well as from well-established models in behavioral science that predict loss aversion relative to a reference point, which here is set by the algorithm. We show that recommendation-dependent preferences create inefficiencies where the decision-maker is overly responsive to the recommendation. As a potential remedy, we discuss algorithms that strategically withhold recommendations, and show how they can improve the quality of final decisions.
Authors: Cedric Gerbelot, Emanuele Troiani, Francesca Mignacco, Florent Krzakala, Lenka Zdeborova
We prove closed-form equations for the exact high-dimensional asymptotics of a family of first order gradient-based methods, learning an estimator (e.g. M-estimator, shallow neural network, ...) from observations on Gaussian data with empirical risk minimization. This includes widely used algorithms such as stochastic gradient descent (SGD) or Nesterov acceleration. The obtained equations match those resulting from the discretization of dynamical mean-field theory (DMFT) equations from statistical physics when applied to gradient flow. Our proof method allows us to give an explicit description of how memory kernels build up in the effective dynamics, and to include non-separable update functions, allowing datasets with non-identity covariance matrices. Finally, we provide numerical implementations of the equations for SGD with generic extensive batch-size and with constant learning rates.
Authors: Jack Y. Araz, Michael Spannowsky
The Hamiltonian of an isolated quantum mechanical system determines its dynamics and physical behaviour. This study investigates the possibility of learning and utilising a system's Hamiltonian and its variational thermal state estimation for data analysis techniques. For this purpose, we employ the method of Quantum Hamiltonian-based models for the generative modelling of simulated Large Hadron Collider data and demonstrate the representability of such data as a mixed state. In a further step, we use the learned Hamiltonian for anomaly detection, showing that different sample types can form distinct dynamical behaviours once treated as a quantum many-body system. We exploit these characteristics to quantify the difference between sample types. Our findings show that the methodologies designed for field theory computations can be utilised in machine learning applications to employ theoretical approaches in data analysis techniques.
Authors: Haiyang Lin, Mingyu Yan, Xiaochun Ye, Dongrui Fan, Shirui Pan, Wenguang Chen, Yuan Xie
Graph neural networks (GNNs) have been demonstrated to be a powerful algorithmic model in broad application fields for their effectiveness in learning over graphs. To scale GNN training up for large-scale and ever-growing graphs, the most promising solution is distributed training which distributes the workload of training across multiple computing nodes. At present, the volume of related research on distributed GNN training is exceptionally vast, accompanied by an extraordinarily rapid pace of publication. Moreover, the approaches reported in these studies exhibit significant divergence. This situation poses a considerable challenge for newcomers, hindering their ability to grasp a comprehensive understanding of the workflows, computational patterns, communication strategies, and optimization techniques employed in distributed GNN training. As a result, there is a pressing need for a survey to provide correct recognition, analysis, and comparisons in this field. In this paper, we provide a comprehensive survey of distributed GNN training by investigating various optimization techniques used in distributed GNN training. First, distributed GNN training is classified into several categories according to their workflows. In addition, their computational patterns and communication patterns, as well as the optimization techniques proposed by recent work are introduced. Second, the software frameworks and hardware platforms of distributed GNN training are also introduced for a deeper understanding. Third, distributed GNN training is compared with distributed training of deep neural networks, emphasizing the uniqueness of distributed GNN training. Finally, interesting issues and opportunities in this field are discussed.
Authors: Hao Mei, Xiaoliang Lei, Longchao Da, Bin Shi, Hua Wei
This paper introduces a library for cross-simulator comparison of reinforcement learning models in traffic signal control tasks. This library is developed to implement recent state-of-the-art reinforcement learning models with extensible interfaces and unified cross-simulator evaluation metrics. It supports commonly-used simulators in traffic signal control tasks, including Simulation of Urban MObility(SUMO) and CityFlow, and multiple benchmark datasets for fair comparisons. We conducted experiments to validate our implementation of the models and to calibrate the simulators so that the experiments from one simulator could be referential to the other. Based on the validated models and calibrated environments, this paper compares and reports the performance of current state-of-the-art RL algorithms across different datasets and simulators. This is the first time that these methods have been compared fairly under the same datasets with different simulators.
Authors: Qingyao Sun (Cornell University), Kevin Murphy (Google DeepMind), Sayna Ebrahimi (Google Cloud AI Research), Alexander D'Amour (Google DeepMind)
Changes in the data distribution at test time can have deleterious effects on the performance of predictive models $p(y|x)$. We consider situations where there are additional meta-data labels (such as group labels), denoted by $z$, that can account for such changes in the distribution. In particular, we assume that the prior distribution $p(y, z)$, which models the dependence between the class label $y$ and the "nuisance" factors $z$, may change across domains, either due to a change in the correlation between these terms, or a change in one of their marginals. However, we assume that the generative model for features $p(x|y,z)$ is invariant across domains. We note that this corresponds to an expanded version of the widely used "label shift" assumption, where the labels now also include the nuisance factors $z$. Based on this observation, we propose a test-time label shift correction that adapts to changes in the joint distribution $p(y, z)$ using EM applied to unlabeled samples from the target domain distribution, $p_t(x)$. Importantly, we are able to avoid fitting a generative model $p(x|y, z)$, and merely need to reweight the outputs of a discriminative model $p_s(y, z|x)$ trained on the source distribution. We evaluate our method, which we call "Test-Time Label-Shift Adaptation" (TTLSA), on several standard image and text datasets, as well as the CheXpert chest X-ray dataset, and show that it improves performance over methods that target invariance to changes in the distribution, as well as baseline empirical risk minimization methods. Code for reproducing experiments is available at https://github.com/nalzok/test-time-label-shift .
Authors: Yikai Wang, Yanwei Fu, Xinwei Sun
A noisy training set usually leads to the degradation of the generalization and robustness of neural networks. In this paper, we propose a novel theoretically guaranteed clean sample selection framework for learning with noisy labels. Specifically, we first present a Scalable Penalized Regression (SPR) method, to model the linear relation between network features and one-hot labels. In SPR, the clean data are identified by the zero mean-shift parameters solved in the regression model. We theoretically show that SPR can recover clean data under some conditions. Under general scenarios, the conditions may be no longer satisfied; and some noisy data are falsely selected as clean data. To solve this problem, we propose a data-adaptive method for Scalable Penalized Regression with Knockoff filters (Knockoffs-SPR), which is provable to control the False-Selection-Rate (FSR) in the selected clean data. To improve the efficiency, we further present a split algorithm that divides the whole training set into small pieces that can be solved in parallel to make the framework scalable to large datasets. While Knockoffs-SPR can be regarded as a sample selection module for a standard supervised training pipeline, we further combine it with a semi-supervised algorithm to exploit the support of noisy data as unlabeled data. Experimental results on several benchmark datasets and real-world noisy datasets show the effectiveness of our framework and validate the theoretical results of Knockoffs-SPR. Our code and pre-trained models are available at https://github.com/Yikai-Wang/Knockoffs-SPR.
Authors: Kevin Lam, Christian Walder, Spiridon Penev, Richard Nock
Loss functions serve as the foundation of supervised learning and are often chosen prior to model development. To avoid potentially ad hoc choices of losses, statistical decision theory describes a desirable property for losses known as \emph{properness}, which asserts that Bayes' rule is optimal. Recent works have sought to \emph{learn losses} and models jointly. Existing methods do this by fitting an inverse canonical link function which monotonically maps $\mathbb{R}$ to $[0,1]$ to estimate probabilities for binary problems. In this paper, we extend monotonicity to maps between $\mathbb{R}^{C-1}$ and the projected probability simplex $\tilde{\Delta}^{C-1}$ by using monotonicity of gradients of convex functions. We present {\sc LegendreTron} as a novel and practical method that jointly learns \emph{proper canonical losses} and probabilities for multiclass problems. Tested on a benchmark of domains with up to 1,000 classes, our experimental results show that our method consistently outperforms the natural multiclass baseline under a $t$-test at 99% significance on all datasets with greater than 10 classes.
Authors: Muah Kim, Rick Fritschek, Rafael F. Schaefer
It is a known problem that deep-learning-based end-to-end (E2E) channel coding systems depend on a known and differentiable channel model, due to the learning process and based on the gradient-descent optimization methods. This places the challenge to approximate or generate the channel or its derivative from samples generated by pilot signaling in real-world scenarios. Currently, there are two prevalent methods to solve this problem. One is to generate the channel via a generative adversarial network (GAN), and the other is to, in essence, approximate the gradient via reinforcement learning methods. Other methods include using score-based methods, variational autoencoders, or mutual-information-based methods. In this paper, we focus on generative models and, in particular, on a new promising method called diffusion models, which have shown a higher quality of generation in image-based tasks. We will show that diffusion models can be used in wireless E2E scenarios and that they work as good as Wasserstein GANs while having a more stable training procedure and a better generalization ability in testing.
Authors: Tom Rainforth, Adam Foster, Desi R Ivanova, Freddie Bickford Smith
Bayesian experimental design (BED) provides a powerful and general framework for optimizing the design of experiments. However, its deployment often poses substantial computational challenges that can undermine its practical use. In this review, we outline how recent advances have transformed our ability to overcome these challenges and thus utilize BED effectively, before discussing some key areas for future development in the field.
Authors: Saqib Javed, Chengkun Li, Andrew Price, Yinlin Hu, Mathieu Salzmann
Edge applications, such as collaborative robotics and spacecraft rendezvous, demand efficient 6D object pose estimation on resource-constrained embedded platforms. Existing 6D pose estimation networks are often too large for such deployments, necessitating compression while maintaining reliable performance. To address this challenge, we introduce Modular Quantization-Aware Training (MQAT), an adaptive and mixed-precision quantization-aware training strategy that exploits the modular structure of modern 6D pose estimation architectures. MQAT guides a systematic gradated modular quantization sequence and determines module-specific bit precisions, leading to quantized models that outperform those produced by state-of-the-art uniform and mixed-precision quantization techniques. Our experiments showcase the generality of MQAT across datasets, architectures, and quantization algorithms. Remarkably, MQAT-trained quantized models achieve a significant accuracy boost (>7%) over the baseline full-precision network while reducing model size by a factor of 4x or more.
Authors: Zhongwen Zhang, Yuri Boykov
We propose "collision cross-entropy" as a robust alternative to Shannon's cross-entropy (CE) loss when class labels are represented by soft categorical distributions y. In general, soft labels can naturally represent ambiguous targets in classification. They are particularly relevant for self-labeled clustering methods, where latent pseudo-labels are jointly estimated with the model parameters and uncertainty is prevalent. In case of soft labels, Shannon's CE teaches the model predictions to reproduce the uncertainty in each training example, which inhibits the model's ability to learn and generalize from these examples. As an alternative loss, we propose the negative log of "collision probability" that maximizes the chance of equality between two random variables, predicted class and unknown true class. We show that it has the properties of a generalized CE. The proposed collision CE agrees with Shannon's CE for one-hot labels, but the training from soft labels differs. For example, unlike Shannon's CE, data points where y is a uniform distribution have zero contribution to the training. Collision CE significantly improves classification supervised by soft uncertain targets. Unlike Shannon's, collision CE is symmetric for y and network predictions, which is particularly relevant when both distributions are estimated in the context of self-labeled clustering. Focusing on discriminative deep clustering where self-labeling and entropy-based losses are dominant, we show that the use of collision CE improves the state-of-the-art. We also derive an efficient EM algorithm that significantly speeds up the pseudo-label estimation with collision CE.
Authors: Jingyi Hou, Zhen Dong, Jiayu Zhou, Zhijie Liu
Modern time series forecasting methods, such as Transformer and its variants, have shown strong ability in sequential data modeling. To achieve high performance, they usually rely on redundant or unexplainable structures to model complex relations between variables and tune the parameters with large-scale data. Many real-world data mining tasks, however, lack sufficient variables for relation reasoning, and therefore these methods may not properly handle such forecasting problems. With insufficient data, time series appear to be affected by many exogenous variables, and thus, the modeling becomes unstable and unpredictable. To tackle this critical issue, in this paper, we develop a novel algorithmic framework for inferring the intrinsic latent factors implied by the observable time series. The inferred factors are used to form multiple independent and predictable signal components that enable not only sparse relation reasoning for long-term efficiency but also reconstructing the future temporal data for accurate prediction. To achieve this, we introduce three characteristics, i.e., predictability, sufficiency, and identifiability, and model these characteristics via the powerful deep latent dynamics models to infer the predictable signal components. Empirical results on multiple real datasets show the efficiency of our method for different kinds of time series forecasting. The statistical analysis validates the predictability of the learned latent factors.
Authors: Wenhao Yuan, Xuehe Wang
Federated Learning (FL) has become an emerging norm for distributed model training, which enables multiple devices cooperatively to train a shared model utilizing their own datasets scheduled by a central server while keeping private data localized. However, during the training process, the non-independent-and-identically-distributed (Non-IID) data generated on heterogeneous clients and frequent communication across participants may significantly influence the training performance, slow down the convergent rate, and increase communication consumption. In this paper, we ameliorate the standard stochastic gradient descent approach by introducing the aggregated gradients at each local update epoch and propose an adaptive learning rate iterative algorithm that further takes the deviation between the local parameter and global parameter into account. The aforementioned adaptive learning rate design mechanism requires local information of all clients, which is challenging as there is no communication during the local update epochs. To obtain a decentralized adaptive learning rate for each client, we introduce the mean-field approach by utilizing two mean-field terms to estimate the average local parameters and gradients respectively without exchanging clients' local information with each other over time. Through theoretical analysis, we prove that our method can provide the convergence guarantee for model training and derive a convergent upper bound for the client drifting term. Extensive numerical results show that our proposed framework is superior to the state-of-the-art FL schemes in both model accuracy and convergent rate on real-world datasets with IID and Non-IID data distribution.
Authors: Changho Shin, Sonia Cromp, Dyah Adila, Frederic Sala
Weak supervision enables efficient development of training sets by reducing the need for ground truth labels. However, the techniques that make weak supervision attractive -- such as integrating any source of signal to estimate unknown labels -- also entail the danger that the produced pseudolabels are highly biased. Surprisingly, given everyday use and the potential for increased bias, weak supervision has not been studied from the point of view of fairness. We begin such a study, starting with the observation that even when a fair model can be built from a dataset with access to ground-truth labels, the corresponding dataset labeled via weak supervision can be arbitrarily unfair. To address this, we propose and empirically validate a model for source unfairness in weak supervision, then introduce a simple counterfactual fairness-based technique that can mitigate these biases. Theoretically, we show that it is possible for our approach to simultaneously improve both accuracy and fairness -- in contrast to standard fairness approaches that suffer from tradeoffs. Empirically, we show that our technique improves accuracy on weak supervision baselines by as much as 32\% while reducing demographic parity gap by 82.5\%. A simple extension of our method aimed at maximizing performance produces state-of-the-art performance in five out of ten datasets in the WRENCH benchmark.
Authors: Suhyun Kang, Duhun Hwang, Moonjung Eo, Taesup Kim, Wonjong Rhee
Model-agnostic meta-learning (MAML) is one of the most successful meta-learning algorithms. It has a bi-level optimization structure where the outer-loop process learns a shared initialization and the inner-loop process optimizes task-specific weights. Although MAML relies on the standard gradient descent in the inner-loop, recent studies have shown that controlling the inner-loop's gradient descent with a meta-learned preconditioner can be beneficial. Existing preconditioners, however, cannot simultaneously adapt in a task-specific and path-dependent way. Additionally, they do not satisfy the Riemannian metric condition, which can enable the steepest descent learning with preconditioned gradient. In this study, we propose Geometry-Adaptive Preconditioned gradient descent (GAP) that can overcome the limitations in MAML; GAP can efficiently meta-learn a preconditioner that is dependent on task-specific parameters, and its preconditioner can be shown to be a Riemannian metric. Thanks to the two properties, the geometry-adaptive preconditioner is effective for improving the inner-loop optimization. Experiment results show that GAP outperforms the state-of-the-art MAML family and preconditioned gradient descent-MAML (PGD-MAML) family in a variety of few-shot learning tasks. Code is available at: https://github.com/Suhyun777/CVPR23-GAP.
Authors: Marko Petković, Pablo Romero-Marimon, Vlado Menkovski, Sofia Calero
Efficiently predicting properties of porous crystalline materials has great potential to accelerate the high throughput screening process for developing new materials, as simulations carried out using first principles model are often computationally expensive. To effectively make use of Deep Learning methods to model these materials, we need to utilize the symmetries present in the crystals, which are defined by their space group. Existing methods for crystal property prediction either have symmetry constraints that are too restrictive or only incorporate symmetries between unit cells. In addition, these models do not explicitly model the porous structure of the crystal. In this paper, we develop a model which incorporates the symmetries of the unit cell of a crystal in its architecture and explicitly models the porous structure. We evaluate our model by predicting the heat of adsorption of CO$_2$ for different configurations of the mordenite zeolite. Our results confirm that our method performs better than existing methods for crystal property prediction and that the inclusion of pores results in a more efficient model.
Authors: Hakjin Lee, Minki Song, Jamyoung Koo, Junghoon Seo
The Detection Transformer (DETR) has emerged as a pivotal role in object detection tasks, setting new performance benchmarks due to its end-to-end design and scalability. Despite its advancements, the application of DETR in detecting rotated objects has demonstrated suboptimal performance relative to established oriented object detectors. Our analysis identifies a key limitation: the L1 cost used in Hungarian Matching leads to duplicate predictions due to the square-like problem in oriented object detection, thereby obstructing the training process of the detector. We introduce a Hausdorff distance-based cost for Hungarian matching, which more accurately quantifies the discrepancy between predictions and ground truths. Moreover, we note that a static denoising approach hampers the training of rotated DETR, particularly when the detector's predictions surpass the quality of noised ground truths. We propose an adaptive query denoising technique, employing Hungarian matching to selectively filter out superfluous noised queries that no longer contribute to model improvement. Our proposed modifications to DETR have resulted in superior performance, surpassing previous rotated DETR models and other alternatives. This is evidenced by our model's state-of-the-art achievements in benchmarks such as DOTA-v1.0/v1.5/v2.0, and DIOR-R.
Authors: Eilam Shapira, Reut Apel, Moshe Tennenholtz, Roi Reichart
Persuasion games have been fundamental in economics and AI research, and have significant practical applications. Recent works in this area have started to incorporate natural language, moving beyond the traditional stylized message setting. However, previous research has focused on on-policy prediction, where the train and test data have the same distribution, which is not representative of real-life scenarios. In this paper, we tackle the challenging problem of off-policy evaluation (OPE) in language-based persuasion games. To address the inherent difficulty of human data collection in this setup, we propose a novel approach which combines real and simulated human-bot interaction data. Our simulated data is created by an exogenous model assuming decision makers (DMs) start with a mixture of random and decision-theoretic based behaviors and improve over time. We present a deep learning training algorithm that effectively integrates real interaction and simulated data, substantially improving over models that train only with interaction data. Our results demonstrate the potential of real interaction and simulation mixtures as a cost-effective and scalable solution for OPE in language-based persuasion games. Our code and the large dataset we collected and generated are submitted as supplementary material and publicly available in our GitHub repository: https://github.com/eilamshapira/HumanChoicePrediction
Authors: Piyush Jha, Joseph Scott, Jaya Sriram Ganeshna, Mudit Singh, Vijay Ganesh
We present a novel tool BertRLFuzzer, a BERT and Reinforcement Learning (RL) based fuzzer aimed at finding security vulnerabilities for Web applications. BertRLFuzzer works as follows: given a set of seed inputs, the fuzzer performs grammar-adhering and attack-provoking mutation operations on them to generate candidate attack vectors. The key insight of BertRLFuzzer is the use of RL with a BERT model as an agent to guide the fuzzer to efficiently learn grammar-adhering and attack-provoking mutation operators. In order to establish the efficacy of BertRLFuzzer we compare it against a total of 13 black box and white box fuzzers over a benchmark of 9 victim websites with over 16K LOC. We observed a significant improvement relative to the nearest competing tool in terms of time to first attack (54% less), new vulnerabilities found (17 new vulnerabilities), and attack rate (4.4% more attack vectors generated).
Authors: Yu-Bang Zheng, Xi-Le Zhao, Junhua Zeng, Chao Li, Qibin Zhao, Heng-Chao Li, Ting-Zhu Huang
Tensor network (TN) representation is a powerful technique for computer vision and machine learning. TN structure search (TN-SS) aims to search for a customized structure to achieve a compact representation, which is a challenging NP-hard problem. Recent "sampling-evaluation-based" methods require sampling an extensive collection of structures and evaluating them one by one, resulting in prohibitively high computational costs. To address this issue, we propose a novel TN paradigm, named SVD-inspired TN decomposition (SVDinsTN), which allows us to efficiently solve the TN-SS problem from a regularized modeling perspective, eliminating the repeated structure evaluations. To be specific, by inserting a diagonal factor for each edge of the fully-connected TN, SVDinsTN allows us to calculate TN cores and diagonal factors simultaneously, with the factor sparsity revealing a compact TN structure. In theory, we prove a convergence guarantee for the proposed method. Experimental results demonstrate that the proposed method achieves approximately 100 to 1000 times acceleration compared to the state-of-the-art TN-SS methods while maintaining a comparable representation ability.
Authors: Yue Xu, Yong-Lu Li, Kaitong Cui, Ziyu Wang, Cewu Lu, Yu-Wing Tai, Chi-Keung Tang
Data-efficient learning has garnered significant attention, especially given the current trend of large multi-modal models. Recently, dataset distillation becomes an effective approach for data-efficiency; however, the distillation process itself can still be inefficient. In this work, we model the dataset distillation task within the context of information transport. By observing the substantial data redundancy inherent in the distillation, we argue to put more emphasis on the samples' utility for the distillation task. We introduce and validate a family of data utility estimators and optimal data selection methods to exploit the most valuable samples. This strategy significantly reduces the training costs and extends various existing distillation algorithms to larger and more diversified datasets, e.g., in some cases only 0.04% training data is sufficient for comparable distillation performance. Our method consistently enhances the distillation algorithms, even on much larger-scale and more heterogeneous datasets, e.g. ImageNet-1K and Kinetics-400. This paradigm opens up new avenues in the dynamics of distillation and paves the way for efficient dataset distillation. Our code is available on https://github.com/silicx/GoldFromOres .
Authors: Peiyao Xiao, Hao Ban, Kaiyi Ji
Multi-objective optimization (MOO) has become an influential framework in many machine learning problems with multiple objectives such as learning with multiple criteria and multi-task learning (MTL). In this paper, we propose a new direction-oriented multi-objective problem by regularizing the common descent direction within a neighborhood of a direction that optimizes a linear combination of objectives such as the average loss in MTL. This formulation includes GD and MGDA as special cases, enjoys the direction-oriented benefit as in CAGrad, and facilitates the design of stochastic algorithms. To solve this problem, we propose Stochastic Direction-oriented Multi-objective Gradient descent (SDMGrad) with simple SGD type of updates, and its variant SDMGrad-OS with an efficient objective sampling in the setting where the number of objectives is large. For a constant-level regularization parameter $\lambda$, we show that SDMGrad and SDMGrad-OS provably converge to a Pareto stationary point with improved complexities and milder assumptions. For an increasing $\lambda$, this convergent point reduces to a stationary point of the linear combination of objectives. We demonstrate the superior performance of the proposed methods in a series of tasks on multi-task supervised learning and reinforcement learning. Code is provided at https://github.com/ml-opt-lab/sdmgrad.
Authors: Fabian Akkerman, Julius Luy, Wouter van Heeswijk, Maximilian Schiffer
Large discrete action spaces (LDAS) remain a central challenge in reinforcement learning. Existing solution approaches can handle unstructured LDAS with up to a few million actions. However, many real-world applications in logistics, production, and transportation systems have combinatorial action spaces, whose size grows well beyond millions of actions, even on small instances. Fortunately, such action spaces exhibit structure, e.g., equally spaced discrete resource units. With this work, we focus on handling structured LDAS (SLDAS) with sizes that cannot be handled by current benchmarks: we propose Dynamic Neighborhood Construction (DNC), a novel exploitation paradigm for SLDAS. We present a scalable neighborhood exploration heuristic that utilizes this paradigm and efficiently explores the discrete neighborhood around the continuous proxy action in structured action spaces with up to $10^{73}$ actions. We demonstrate the performance of our method by benchmarking it against three state-of-the-art approaches designed for large discrete action spaces across two distinct environments. Our results show that DNC matches or outperforms state-of-the-art approaches while being computationally more efficient. Furthermore, our method scales to action spaces that so far remained computationally intractable for existing methodologies.
Authors: Sen Peng, Yufei Chen, Cong Wang, Xiaohua Jia
Diffusion models have rapidly become a vital part of deep generative architectures, given today's increasing demands. Obtaining large, high-performance diffusion models demands significant resources, highlighting their importance as intellectual property worth protecting. However, existing watermarking techniques for ownership verification are insufficient when applied to diffusion models. Very recent research in watermarking diffusion models either exposes watermarks during task generation, which harms the imperceptibility, or is developed for conditional diffusion models that require prompts to trigger the watermark. This paper introduces WDM, a novel watermarking solution for diffusion models without imprinting the watermark during task generation. It involves training a model to concurrently learn a Watermark Diffusion Process (WDP) for embedding watermarks alongside the standard diffusion process for task generation. We provide a detailed theoretical analysis of WDP training and sampling, relating it to a shifted Gaussian diffusion process via the same reverse noise. Extensive experiments are conducted to validate the effectiveness and robustness of our approach in various trigger and watermark data configurations.
Authors: Katherine Deck, Tobias Bischoff
Generated images of score-based models can suffer from errors in their spatial means, an effect, referred to as a color shift, which grows for larger images. This paper investigates a previously-introduced approach to mitigate color shifts in score-based diffusion models. We quantify the performance of a nonlinear bypass connection in the score network, designed to process the spatial mean of the input and to predict the mean of the score function. We show that this network architecture substantially improves the resulting quality of the generated images, and that this improvement is approximately independent of the size of the generated images. As a result, this modified architecture offers a simple solution for the color shift problem across image sizes. We additionally discuss the origin of color shifts in an idealized setting in order to motivate the approach.
Authors: Che-Jui Chang, Danrui Li, Deep Patel, Parth Goel, Honglu Zhou, Seonghyeon Moon, Samuel S. Sohn, Sejong Yoon, Vladimir Pavlovic, Mubbasir Kapadia
The study of complex human interactions and group activities has become a focal point in human-centric computer vision. However, progress in related tasks is often hindered by the challenges of obtaining large-scale labeled datasets from real-world scenarios. To address the limitation, we introduce M3Act, a synthetic data generator for multi-view multi-group multi-person human atomic actions and group activities. Powered by the Unity engine, M3Act features multiple semantic groups, highly diverse and photorealistic images, and a comprehensive set of annotations, which facilitates the learning of human-centered tasks across single-person, multi-person, and multi-group conditions. We demonstrate the advantages of M3Act across three core experiments using various input modalities. First, adding our synthetic data significantly improves the performance of MOTRv2 on DanceTrack, leading to a hop on the leaderboard from 10th to 2nd place. With M3Act, we achieve tracking results on par with MOTRv2*, which is trained with 62.5% more real-world data. Second, M3Act improves the benchmark performances on CAD2 by 5.59% and 7.43% on group activity and atomic action accuracy respectively. Moreover, M3Act opens new research for controllable 3D group activity generation. We define multiple metrics and propose a competitive baseline for the novel task.
Authors: Eric W. Bridgeford, Jaewon Chung, Brian Gilbert, Sambit Panda, Adam Li, Cencheng Shen, Alexandra Badea, Brian Caffo, Joshua T. Vogelstein
Causal inference studies whether the presence of a variable influences an observed outcome. As measured by quantities such as the "average treatment effect," this paradigm is employed across numerous biological fields, from vaccine and drug development to policy interventions. Unfortunately, the majority of these methods are often limited to univariate outcomes. Our work generalizes causal estimands to outcomes with any number of dimensions or any measurable space, and formulates traditional causal estimands for nominal variables as causal discrepancy tests. We propose a simple technique for adjusting universally consistent conditional independence tests and prove that these tests are universally consistent causal discrepancy tests. Numerical experiments illustrate that our method, Causal CDcorr, leads to improvements in both finite sample validity and power when compared to existing strategies. Our methods are all open source and available at github.com/ebridge2/cdcorr.
Authors: Shiliang Zuo
I study the problem of learning a Lipschitz function with corrupted binary signals. The learner tries to learn a $L$-Lipschitz function $f: [0,1]^d \rightarrow [0, L]$ that the adversary chooses. There is a total of $T$ rounds. In each round $t$, the adversary selects a context vector $x_t$ in the input space, and the learner makes a guess to the true function value $f(x_t)$ and receives a binary signal indicating whether the guess is high or low. In a total of $C$ rounds, the signal may be corrupted, though the value of $C$ is \emph{unknown} to the learner. The learner's goal is to incur a small cumulative loss. This work introduces the new algorithmic technique \emph{agnostic checking} as well as new analysis techniques. I design algorithms which: for the symmetric loss, the learner achieves regret $L\cdot O(C\log T)$ with $d = 1$ and $L\cdot O_d(C\log T + T^{(d-1)/d})$ with $d > 1$; for the pricing loss, the learner achieves regret $L\cdot \widetilde{O} (T^{d/(d+1)} + C\cdot T^{1/(d+1)})$.
Authors: Alessandro Zanardi, Andrea Censi, Margherita Atzei, Luigi Di Lillo, Emilio Frazzoli
Autonomous Vehicles (AVs) promise a range of societal advantages, including broader access to mobility, reduced road accidents, and enhanced transportation efficiency. However, evaluating the risks linked to AVs is complex due to limited historical data and the swift progression of technology. This paper presents a data-driven framework for assessing the risk of different AVs' behaviors in various operational design domains (ODDs), based on counterfactual simulations of "misbehaving" road users. We propose the notion of counterfactual safety margin, which represents the minimum deviation from nominal behavior that could cause a collision. This methodology not only pinpoints the most critical scenarios but also quantifies the (relative) risk's frequency and severity concerning AVs. Importantly, we show that our approach is applicable even when the AV's behavioral policy remains undisclosed, through worst- and best-case analyses, benefiting external entities like regulators and risk evaluators. Our experimental outcomes demonstrate the correlation between the safety margin, the quality of the driving policy, and the ODD, shedding light on the relative risks of different AV providers. Overall, this work contributes to the safety assessment of AVs and addresses legislative and insurance concerns surrounding this burgeoning technology.
Authors: Cesar F. Caiafa, Ramiro M. Irastorza
Inverse imaging problems that are ill-posed can be encountered across multiple domains of science and technology, ranging from medical diagnosis to astronomical studies. To reconstruct images from incomplete and distorted data, it is necessary to create algorithms that can take into account both, the physical mechanisms responsible for generating these measurements and the intrinsic characteristics of the images being analyzed. In this work, the sparse representation of images is reviewed, which is a realistic, compact and effective generative model for natural images inspired by the visual system of mammals. It enables us to address ill-posed linear inverse problems by training the model on a vast collection of images. Moreover, we extend the application of sparse coding to solve the non-linear and ill-posed problem in microwave tomography imaging, which could lead to a significant improvement of the state-of-the-arts algorithms.
Authors: Avery Ma, Yangchen Pan, Amir-massoud Farahmand
Stochastic gradient descent (SGD) and adaptive gradient methods, such as Adam and RMSProp, have been widely used in training deep neural networks. We empirically show that while the difference between the standard generalization performance of models trained using these methods is small, those trained using SGD exhibit far greater robustness under input perturbations. Notably, our investigation demonstrates the presence of irrelevant frequencies in natural datasets, where alterations do not affect models' generalization performance. However, models trained with adaptive methods show sensitivity to these changes, suggesting that their use of irrelevant frequencies can lead to solutions sensitive to perturbations. To better understand this difference, we study the learning dynamics of gradient descent (GD) and sign gradient descent (signGD) on a synthetic dataset that mirrors natural signals. With a three-dimensional input space, the models optimized with GD and signGD have standard risks close to zero but vary in their adversarial risks. Our result shows that linear models' robustness to $\ell_2$-norm bounded changes is inversely proportional to the model parameters' weight norm: a smaller weight norm implies better robustness. In the context of deep learning, our experiments show that SGD-trained neural networks have smaller Lipschitz constants, explaining the better robustness to input perturbations than those trained with adaptive gradient methods.
Authors: Niloufar Mehrabi, Sayed Pedram Haeri Boroujeni, Elnaz Pashaei
The Horse Herd Optimization Algorithm (HOA) is a new meta-heuristic algorithm based on the behaviors of horses at different ages. The HOA was introduced recently to solve complex and high-dimensional problems. This paper proposes a binary version of the Horse Herd Optimization Algorithm (BHOA) in order to solve discrete problems and select prominent feature subsets. Moreover, this study provides a novel hybrid feature selection framework based on the BHOA and a minimum Redundancy Maximum Relevance (MRMR) filter method. This hybrid feature selection, which is more computationally efficient, produces a beneficial subset of relevant and informative features. Since feature selection is a binary problem, we have applied a new Transfer Function (TF), called X-shape TF, which transforms continuous problems into binary search spaces. Furthermore, the Support Vector Machine (SVM) is utilized to examine the efficiency of the proposed method on ten microarray datasets, namely Lymphoma, Prostate, Brain-1, DLBCL, SRBCT, Leukemia, Ovarian, Colon, Lung, and MLL. In comparison to other state-of-the-art, such as the Gray Wolf (GW), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA), the proposed hybrid method (MRMR-BHOA) demonstrates superior performance in terms of accuracy and minimum selected features. Also, experimental results prove that the X-Shaped BHOA approach outperforms others methods.
Authors: Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Mengnan Du
Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications. Therefore, understanding and explaining these models is crucial for elucidating their behaviors, limitations, and social impacts. In this paper, we introduce a taxonomy of explainability techniques and provide a structured overview of methods for explaining Transformer-based language models. We categorize techniques based on the training paradigms of LLMs: traditional fine-tuning-based paradigm and prompting-based paradigm. For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge. We also discuss metrics for evaluating generated explanations, and discuss how explanations can be leveraged to debug models and improve performance. Lastly, we examine key challenges and emerging opportunities for explanation techniques in the era of LLMs in comparison to conventional machine learning models.
Authors: Hyunwoo Ryu, Jiwoo Kim, Hyunseok An, Junwoo Chang, Joohwan Seo, Taehan Kim, Yubin Kim, Chaewon Hwang, Jongeun Choi, Roberto Horowitz
Diffusion generative modeling has become a promising approach for learning robotic manipulation tasks from stochastic human demonstrations. In this paper, we present Diffusion-EDFs, a novel SE(3)-equivariant diffusion-based approach for visual robotic manipulation tasks. We show that our proposed method achieves remarkable data efficiency, requiring only 5 to 10 human demonstrations for effective end-to-end training in less than an hour. Furthermore, our benchmark experiments demonstrate that our approach has superior generalizability and robustness compared to state-of-the-art methods. Lastly, we validate our methods with real hardware experiments. Project Website: https://sites.google.com/view/diffusion-edfs/home
Authors: Andres Potapczynski, Marc Finzi, Geoff Pleiss, Andrew Gordon Wilson
Many areas of machine learning and science involve large linear algebra problems, such as eigendecompositions, solving linear systems, computing matrix exponentials, and trace estimation. The matrices involved often have Kronecker, convolutional, block diagonal, sum, or product structure. In this paper, we propose a simple but general framework for large-scale linear algebra problems in machine learning, named CoLA (Compositional Linear Algebra). By combining a linear operator abstraction with compositional dispatch rules, CoLA automatically constructs memory and runtime efficient numerical algorithms. Moreover, CoLA provides memory efficient automatic differentiation, low precision computation, and GPU acceleration in both JAX and PyTorch, while also accommodating new objects, operations, and rules in downstream packages via multiple dispatch. CoLA can accelerate many algebraic operations, while making it easy to prototype matrix structures and algorithms, providing an appealing drop-in tool for virtually any computational effort that requires linear algebra. We showcase its efficacy across a broad range of applications, including partial differential equations, Gaussian processes, equivariant model construction, and unsupervised learning.
Authors: Ajitesh Srivastava
Measuring distance or similarity between time-series data is a fundamental aspect of many applications including classification, clustering, and ensembling/alignment. Existing measures may fail to capture similarities among local trends (shapes) and may even produce misleading results. Our goal is to develop a measure that looks for similar trends occurring around similar times and is easily interpretable for researchers in applied domains. This is particularly useful for applications where time-series have a sequence of meaningful local trends that are ordered, such as in epidemics (a surge to an increase to a peak to a decrease). We propose a novel measure, DTW+S, which creates an interpretable "closeness-preserving" matrix representation of the time-series, where each column represents local trends, and then it applies Dynamic Time Warping to compute distances between these matrices. We present a theoretical analysis that supports the choice of this representation. We demonstrate the utility of DTW+S in several tasks. For the clustering of epidemic curves, we show that DTW+S is the only measure able to produce good clustering compared to the baselines. For ensemble building, we propose a combination of DTW+S and barycenter averaging that results in the best preservation of characteristics of the underlying trajectories. We also demonstrate that our approach results in better classification compared to Dynamic Time Warping for a class of datasets, particularly when local trends rather than scale play a decisive role.
Authors: Hao Mei, Junxian Li, Zhiming Liang, Guanjie Zheng, Bin Shi, Hua Wei
Traffic prediction is a crucial topic because of its broad scope of applications in the transportation domain. Recently, various studies have achieved promising results. However, most studies assume the prediction locations have complete or at least partial historical records and cannot be extended to non-historical recorded locations. In real-life scenarios, the deployment of sensors could be limited due to budget limitations and installation availability, which makes most current models not applicable. Though few pieces of literature tried to impute traffic states at the missing locations, these methods need the data simultaneously observed at the locations with sensors, making them not applicable to prediction tasks. Another drawback is the lack of measurement of uncertainty in prediction, making prior works unsuitable for risk-sensitive tasks or involving decision-making. To fill the gap, inspired by the previous inductive graph neural network, this work proposed an uncertainty-aware framework with the ability to 1) extend prediction to missing locations with no historical records and significantly extend spatial coverage of prediction locations while reducing deployment of sensors and 2) generate probabilistic prediction with uncertainty quantification to help the management of risk and decision making in the down-stream tasks. Through extensive experiments on real-life datasets, the result shows our method achieved promising results on prediction tasks, and the uncertainty quantification gives consistent results which highly correlated with the locations with and without historical data. We also show that our model could help support sensor deployment tasks in the transportation field to achieve higher accuracy with a limited sensor deployment budget.
Authors: Xiaohui Chen, Yinkai Wang, Yuanqi Du, Soha Hassoun, Li-Ping Liu
Self-supervised training methods for transformers have demonstrated remarkable performance across various domains. Previous transformer-based models, such as masked autoencoders (MAE), typically utilize a single normalization layer for both the [CLS] symbol and the tokens. We propose in this paper a simple modification that employs separate normalization layers for the tokens and the [CLS] symbol to better capture their distinct characteristics and enhance downstream task performance. Our method aims to alleviate the potential negative effects of using the same normalization statistics for both token types, which may not be optimally aligned with their individual roles. We empirically show that by utilizing a separate normalization layer, the [CLS] embeddings can better encode the global contextual information and are distributed more uniformly in its anisotropic space. When replacing the conventional normalization layer with the two separate layers, we observe an average 2.7% performance improvement over the image, natural language, and graph domains.
Authors: Tianxiang Zhao, Wenchao Yu, Suhang Wang, Lu Wang, Xiang Zhang, Yuncong Chen, Yanchi Liu, Wei Cheng, Haifeng Chen
Imitation learning, which learns agent policy by mimicking expert demonstration, has shown promising results in many applications such as medical treatment regimes and self-driving vehicles. However, it remains a difficult task to interpret control policies learned by the agent. Difficulties mainly come from two aspects: 1) agents in imitation learning are usually implemented as deep neural networks, which are black-box models and lack interpretability; 2) the latent causal mechanism behind agents' decisions may vary along the trajectory, rather than staying static throughout time steps. To increase transparency and offer better interpretability of the neural agent, we propose to expose its captured knowledge in the form of a directed acyclic causal graph, with nodes being action and state variables and edges denoting the causal relations behind predictions. Furthermore, we design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. Concretely, we conduct causal discovery from the perspective of Granger causality and propose a self-explainable imitation learning framework, {\method}. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner. After the model is learned, we can obtain causal relations among states and action variables behind its decisions, exposing policies learned by it. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of the proposed {\method} in learning the dynamic causal graphs for understanding the decision-making of imitation learning meanwhile maintaining high prediction accuracy.
Authors: Sander Dalm, Marcel van Gerven, Nasir Ahmad
Backpropagation (BP) is the dominant and most successful method for training parameters of deep neural network models. However, BP relies on two computationally distinct phases, does not provide a satisfactory explanation of biological learning, and can be challenging to apply for training of networks with discontinuities or noisy node dynamics. By comparison, node perturbation (NP) proposes learning by the injection of noise into the network activations, and subsequent measurement of the induced loss change. NP relies on two forward (inference) passes, does not make use of network derivatives, and has been proposed as a model for learning in biological systems. However, standard NP is highly data inefficient and unstable due to its unguided noise-based search process. In this work, we investigate different formulations of NP and relate it to the concept of directional derivatives as well as combining it with a decorrelating mechanism for layer-wise inputs. We find that a closer alignment with directional derivatives together with input decorrelation at every layer significantly enhances performance of NP learning, making its performance on the train set competitive with BP and allowing its application to noisy systems in which the noise process itself is inaccessible.
Authors: Yikai Liu, Ming Chen, Guang Lin
Coarse-grained (CG) models play a crucial role in the study of protein structures, protein thermodynamic properties, and protein conformation dynamics. Due to the information loss in the coarse-graining process, backmapping from CG to all-atom configurations is essential in many protein design and drug discovery applications when detailed atomic representations are needed for in-depth studies. Despite recent progress in data-driven backmapping approaches, devising a backmapping method that can be universally applied across various CG models and proteins remains unresolved. In this work, we propose BackDiff, a new generative model designed to achieve generalization and reliability in the protein backmapping problem. BackDiff leverages the conditional score-based diffusion model with geometric representations. Since different CG models can contain different coarse-grained sites which include selected atoms (CG atoms) and simple CG auxiliary functions of atomistic coordinates (CG auxiliary variables), we design a self-supervised training framework to adapt to different CG atoms, and constrain the diffusion sampling paths with arbitrary CG auxiliary variables as conditions. Our method facilitates end-to-end training and allows efficient sampling across different proteins and diverse CG models without the need for retraining. Comprehensive experiments over multiple popular CG models demonstrate BackDiff's superior performance to existing state-of-the-art approaches, and generalization and flexibility that these approaches cannot achieve. A pretrained BackDiff model can offer a convenient yet reliable plug-and-play solution for protein researchers, enabling them to investigate further from their own CG models.
Authors: Albert Garde, Esben Kran, Fazl Barez
As large language models (LLMs) become more capable, there is an urgent need for interpretable and transparent tools. Current methods are difficult to implement, and accessible tools to analyze model internals are lacking. To bridge this gap, we present DeepDecipher - an API and interface for probing neurons in transformer models' MLP layers. DeepDecipher makes the outputs of advanced interpretability techniques for LLMs readily available. The easy-to-use interface also makes inspecting these complex models more intuitive. This paper outlines DeepDecipher's design and capabilities. We demonstrate how to analyze neurons, compare models, and gain insights into model behavior. For example, we contrast DeepDecipher's functionality with similar tools like Neuroscope and OpenAI's Neuron Explainer. DeepDecipher enables efficient, scalable analysis of LLMs. By granting access to state-of-the-art interpretability methods, DeepDecipher makes LLMs more transparent, trustworthy, and safe. Researchers, engineers, and developers can quickly diagnose issues, audit systems, and advance the field.
Authors: Mor Ventura, Eyal Ben-David, Anna Korhonen, Roi Reichart
Text-To-Image (TTI) models, such as DALL-E and StableDiffusion, have demonstrated remarkable prompt-based image generation capabilities. Multilingual encoders may have a substantial impact on the cultural agency of these models, as language is a conduit of culture. In this study, we explore the cultural perception embedded in TTI models by characterizing culture across three hierarchical tiers: cultural dimensions, cultural domains, and cultural concepts. Based on this ontology, we derive prompt templates to unlock the cultural knowledge in TTI models, and propose a comprehensive suite of evaluation techniques, including intrinsic evaluations using the CLIP space, extrinsic evaluations with a Visual-Question-Answer (VQA) model and human assessments, to evaluate the cultural content of TTI-generated images. To bolster our research, we introduce the CulText2I dataset, derived from four diverse TTI models and spanning ten languages. Our experiments provide insights regarding Do, What, Which and How research questions about the nature of cultural encoding in TTI models, paving the way for cross-cultural applications of these models.
Authors: Josh Collyer, Tim Watson, Iain Phillips
Being able to identify functions of interest in cross-architecture software is useful whether you are analysing for malware, securing the software supply chain or conducting vulnerability research. Cross-Architecture Binary Code Similarity Search has been explored in numerous studies and has used a wide range of different data sources to achieve its goals. The data sources typically used draw on common structures derived from binaries such as function control flow graphs or binary level call graphs, the output of the disassembly process or the outputs of a dynamic analysis approach. One data source which has received less attention is binary intermediate representations. Binary Intermediate representations possess two interesting properties: they are cross architecture by their very nature and encode the semantics of a function explicitly to support downstream usage. Within this paper we propose Function as a String Encoded Representation (FASER) which combines long document transformers with the use of intermediate representations to create a model capable of cross architecture function search without the need for manual feature engineering, pre-training or a dynamic analysis step. We compare our approach against a series of baseline approaches for two tasks; A general function search task and a targeted vulnerability search task. Our approach demonstrates strong performance across both tasks, performing better than all baseline approaches.
Authors: Alexander Robey, Eric Wong, Hamed Hassani, George J. Pappas
Despite efforts to align large language models (LLMs) with human values, widely-used LLMs such as GPT, Llama, Claude, and PaLM are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generating objectionable content. To address this vulnerability, we propose SmoothLLM, the first algorithm designed to mitigate jailbreaking attacks on LLMs. Based on our finding that adversarially-generated prompts are brittle to character-level changes, our defense first randomly perturbs multiple copies of a given input prompt, and then aggregates the corresponding predictions to detect adversarial inputs. SmoothLLM reduces the attack success rate on numerous popular LLMs to below one percentage point, avoids unnecessary conservatism, and admits provable guarantees on attack mitigation. Moreover, our defense uses exponentially fewer queries than existing attacks and is compatible with any LLM. Our code is publicly available at the following link: https://github.com/arobey1/smooth-llm.
Authors: Lucas Möller, Dmitry Nikolaev, Sebastian Padó
Despite the success of Siamese encoder models such as sentence transformers (ST), little is known about the aspects of inputs they pay attention to. A barrier is that their predictions cannot be attributed to individual features, as they compare two inputs rather than processing a single one. This paper derives a local attribution method for Siamese encoders by generalizing the principle of integrated gradients to models with multiple inputs. The solution takes the form of feature-pair attributions, and can be reduced to a token-token matrix for STs. Our method involves the introduction of integrated Jacobians and inherits the advantageous formal properties of integrated gradients: it accounts for the model's full computation graph and is guaranteed to converge to the actual prediction. A pilot study shows that in an ST few token-pairs can often explain large fractions of predictions, and it focuses on nouns and verbs. For accurate predictions, it however needs to attend to the majority of tokens and parts of speech.
Authors: Bingzhi Zhang, Peng Xu, Xiaohui Chen, Quntao Zhuang
Deep generative models are key-enabling technology to computer vision, text generation and large language models. Denoising diffusion probabilistic models (DDPMs) have recently gained much attention due to their ability to generate diverse and high-quality samples in many computer vision tasks, as well as to incorporate flexible model architectures and relatively simple training scheme. Quantum generative models, empowered by entanglement and superposition, have brought new insight to learning classical and quantum data. Inspired by the classical counterpart, we propose the quantum denoising diffusion probabilistic models (QuDDPM) to enable efficiently trainable generative learning of quantum data. QuDDPM adopts sufficient layers of circuits to guarantee expressivity, while introduces multiple intermediate training tasks as interpolation between the target distribution and noise to avoid barren plateau and guarantee efficient training. We provide bounds on the learning error and demonstrate QuDDPM's capability in learning correlated quantum noise model, quantum many-body phases and topological structure of quantum data. The results provide a paradigm for versatile and efficient quantum generative learning.
Authors: Shaofei Cai, Bowei Zhang, Zihao Wang, Xiaojian Ma, Anji Liu, Yitao Liang
We study the problem of building a controller that can follow open-ended instructions in open-world environments. We propose to follow reference videos as instructions, which offer expressive goal specifications while eliminating the need for expensive text-gameplay annotations. A new learning framework is derived to allow learning such instruction-following controllers from gameplay videos while producing a video instruction encoder that induces a structured goal space. We implement our agent GROOT in a simple yet effective encoder-decoder architecture based on causal transformers. We evaluate GROOT against open-world counterparts and human players on a proposed Minecraft SkillForge benchmark. The Elo ratings clearly show that GROOT is closing the human-machine gap as well as exhibiting a 70% winning rate over the best generalist agent baseline. Qualitative analysis of the induced goal space further demonstrates some interesting emergent properties, including the goal composition and complex gameplay behavior synthesis. The project page is available at https://craftjarvis-groot.github.io.
Authors: Zhengtao Gui, Haoyuan Li, Sijie Xu, Yu Chen
Time series forecasting represents a significant and challenging task across various fields. Recently, methods based on mode decomposition have dominated the forecasting of complex time series because of the advantages of capturing local characteristics and extracting intrinsic modes from data. Unfortunately, most models fail to capture the implied volatilities that contain significant information. To enhance the prediction of contemporary diverse and complex time series, we propose a novel time series forecasting paradigm that integrates decomposition with the capability to capture the underlying fluctuation information of the series. In our methodology, we implement the Variational Mode Decomposition algorithm to decompose the time series into K distinct sub-modes. Following this decomposition, we apply the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model to extract the volatility information in these sub-modes. Subsequently, both the numerical data and the volatility information for each sub-mode are harnessed to train a neural network. This network is adept at predicting the information of the sub-modes, and we aggregate the predictions of all sub-modes to generate the final output. By integrating econometric and artificial intelligence methods, and taking into account both the numerical and volatility information of the time series, our proposed framework demonstrates superior performance in time series forecasting, as evidenced by the significant decrease in MSE, RMSE, and MAPE in our comparative experimental results.
Authors: Wenqi Jiang, Marco Zeller, Roger Waleffe, Torsten Hoefler, Gustavo Alonso
A Retrieval-Augmented Language Model (RALM) augments a generative language model by retrieving context-specific knowledge from an external database. This strategy facilitates impressive text generation quality even with smaller models, thus reducing orders of magnitude of computational demands. However, RALMs introduce unique system design challenges due to (a) the diverse workload characteristics between LM inference and retrieval and (b) the various system requirements and bottlenecks for different RALM configurations such as model sizes, database sizes, and retrieval frequencies. We propose Chameleon, a heterogeneous accelerator system that integrates both LM and retrieval accelerators in a disaggregated architecture. The heterogeneity ensures efficient acceleration of both LM inference and retrieval, while the accelerator disaggregation enables the system to independently scale both types of accelerators to fulfill diverse RALM requirements. Our Chameleon prototype implements retrieval accelerators on FPGAs and assigns LM inference to GPUs, with a CPU server orchestrating these accelerators over the network. Compared to CPU-based and CPU-GPU vector search systems, Chameleon achieves up to 23.72x speedup and 26.2x energy efficiency. Evaluated on various RALMs, Chameleon exhibits up to 2.16x reduction in latency and 3.18x speedup in throughput compared to the hybrid CPU-GPU architecture. These promising results pave the way for bringing accelerator heterogeneity and disaggregation into future RALM systems.
Authors: Revan MacQueen, James R. Wright
Self-play is a technique for machine learning in multi-agent systems where a learning algorithm learns by interacting with copies of itself. Self-play is useful for generating large quantities of data for learning, but has the drawback that the agents the learner will face post-training may have dramatically different behavior than the learner came to expect by interacting with itself. For the special case of two-player constant-sum games, self-play that reaches Nash equilibrium is guaranteed to produce strategies that perform well against any post-training opponent; however, no such guarantee exists for multiplayer games. We show that in games that approximately decompose into a set of two-player constant-sum games (called constant-sum polymatrix games) where global $\epsilon$-Nash equilibria are boundedly far from Nash equilibria in each subgame (called subgame stability), any no-external-regret algorithm that learns by self-play will produce a strategy with bounded vulnerability. For the first time, our results identify a structural property of multiplayer games that enable performance guarantees for the strategies produced by a broad class of self-play algorithms. We demonstrate our findings through experiments on Leduc poker.
Authors: Kalle Kujanpää, Joni Pajarinen, Alexander Ilin
Solving complex planning problems has been a long-standing challenge in computer science. Learning-based subgoal search methods have shown promise in tackling these problems, but they often suffer from a lack of completeness guarantees, meaning that they may fail to find a solution even if one exists. In this paper, we propose an efficient approach to augment a subgoal search method to achieve completeness in discrete action spaces. Specifically, we augment the high-level search with low-level actions to execute a multi-level (hybrid) search, which we call complete subgoal search. This solution achieves the best of both worlds: the practical efficiency of high-level search and the completeness of low-level search. We apply the proposed search method to a recently proposed subgoal search algorithm and evaluate the algorithm trained on offline data on complex planning problems. We demonstrate that our complete subgoal search not only guarantees completeness but can even improve performance in terms of search expansions for instances that the high-level could solve without low-level augmentations. Our approach makes it possible to apply subgoal-level planning for systems where completeness is a critical requirement.
Authors: Daniel Kienzle, Julian Lorenz, Katja Ludwig, Rainer Lienhart
We present a novel method for precise 3D object localization in single images from a single calibrated camera using only 2D labels. No expensive 3D labels are needed. Thus, instead of using 3D labels, our model is trained with easy-to-annotate 2D labels along with the physical knowledge of the object's motion. Given this information, the model can infer the latent third dimension, even though it has never seen this information during training. Our method is evaluated on both synthetic and real-world datasets, and we are able to achieve a mean distance error of just 6 cm in our experiments on real data. The results indicate the method's potential as a step towards learning 3D object location estimation, where collecting 3D data for training is not feasible.
Authors: Tian Yu Liu, Matthew Trager, Alessandro Achille, Pramuditha Perera, Luca Zancato, Stefano Soatto
We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text. This strategy is prompt-free, does not require fine-tuning, and is applicable to any pre-trained autoregressive model. Moreover, unlike vector-based representations, distribution-based representations can also model asymmetric relations (e.g., direction of logical entailment, hypernym/hyponym relations) by using algebraic operations between likelihood functions. These ideas are grounded in distributional perspectives on semantics and are connected to standard constructions in automata theory, but to our knowledge they have not been applied to modern language models. We empirically show that the representations obtained from large models align well with human annotations, outperform other zero-shot and prompt-free methods on semantic similarity tasks, and can be used to solve more complex entailment and containment tasks that standard embeddings cannot handle. Finally, we extend our method to represent data from different modalities (e.g., image and text) using multimodal autoregressive models. Our code is available at: https://github.com/tianyu139/meaning-as-trajectories
Authors: Vibhas K. Vats, Sripad Joshi, David J. Crandall, Md. Alimoor Reza, Soon-heung Jung
Traditional multi-view stereo (MVS) methods rely heavily on photometric and geometric consistency constraints, but newer machine learning-based MVS methods check geometric consistency across multiple source views only as a post-processing step. In this paper, we present a novel approach that explicitly encourages geometric consistency of reference view depth maps across multiple source views at different scales during learning (see Fig. 1). We find that adding this geometric consistency loss significantly accelerates learning by explicitly penalizing geometrically inconsistent pixels, reducing the training iteration requirements to nearly half that of other MVS methods. Our extensive experiments show that our approach achieves a new state-of-the-art on the DTU and BlendedMVS datasets, and competitive results on the Tanks and Temples benchmark. To the best of our knowledge, GC-MVSNet is the first attempt to enforce multi-view, multi-scale geometric consistency during learning.
Authors: Abhinav Prakash Gahlot, Huseyin Tuna Erdinc, Rafael Orozco, Ziyi Yin, Felix J. Herrmann
As the global deployment of carbon capture and sequestration (CCS) technology intensifies in the fight against climate change, it becomes increasingly imperative to establish robust monitoring and detection mechanisms for potential underground CO2 leakage, particularly through pre-existing or induced faults in the storage reservoir's seals. While techniques such as history matching and time-lapse seismic monitoring of CO2 storage have been used successfully in tracking the evolution of CO2 plumes in the subsurface, these methods lack principled approaches to characterize uncertainties related to the CO2 plumes' behavior. Inclusion of systematic assessment of uncertainties is essential for risk mitigation for the following reasons: (i) CO2 plume-induced changes are small and seismic data is noisy; (ii) changes between regular and irregular (e.g., caused by leakage) flow patterns are small; and (iii) the reservoir properties that control the flow are strongly heterogeneous and typically only available as distributions. To arrive at a formulation capable of inferring flow patterns for regular and irregular flow from well and seismic data, the performance of conditional normalizing flow will be analyzed on a series of carefully designed numerical experiments. While the inferences presented are preliminary in the context of an early CO2 leakage detection system, the results do indicate that inferences with conditional normalizing flows can produce high-fidelity estimates for CO2 plumes with or without leakage. We are also confident that the inferred uncertainty is reasonable because it correlates well with the observed errors. This uncertainty stems from noise in the seismic data and from the lack of precise knowledge of the reservoir's fluid flow properties.
Authors: Burcu Ozek, Zhenyuan Lu, Srinivasan Radhakrishnan, Sagar Kamarthi
Improper pain management can lead to severe physical or mental consequences, including suffering, and an increased risk of opioid dependency. Assessing the presence and severity of pain is imperative to prevent such outcomes and determine the appropriate intervention. However, the evaluation of pain intensity is challenging because different individuals experience pain differently. To overcome this, researchers have employed machine learning models to evaluate pain intensity objectively. However, these efforts have primarily focused on point estimation of pain, disregarding the inherent uncertainty and variability present in the data and model. Consequently, the point estimates provide only partial information for clinical decision-making. This study presents a neural network-based method for objective pain interval estimation, incorporating uncertainty quantification. This work explores three algorithms: the bootstrap method, lower and upper bound estimation (LossL) optimized by genetic algorithm, and modified lower and upper bound estimation (LossS) optimized by gradient descent algorithm. Our empirical results reveal that LossS outperforms the other two by providing a narrower prediction interval. As LossS outperforms, we assessed its performance in three different scenarios for pain assessment: (1) a generalized approach (single model for the entire population), (2) a personalized approach (separate model for each individual), and (3) a hybrid approach (separate model for each cluster of individuals). Our findings demonstrate the hybrid approach's superior performance, with notable practicality in clinical contexts. It has the potential to be a valuable tool for clinicians, enabling objective pain intensity assessment while taking uncertainty into account. This capability is crucial in facilitating effective pain management and reducing the risks associated with improper treatment.
Authors: Naoki Sato, Hideaki Iiduka
The graduated optimization approach is a heuristic method for finding globally optimal solutions for nonconvex functions and has been theoretically analyzed in several studies. This paper defines a new family of nonconvex functions for graduated optimization, discusses their sufficient conditions, and provides a convergence analysis of the graduated optimization algorithm for them. It shows that stochastic gradient descent (SGD) with mini-batch stochastic gradients has the effect of smoothing the function, the degree of which is determined by the learning rate and batch size. This finding provides theoretical insights on why large batch sizes fall into sharp local minima, why decaying learning rates and increasing batch sizes are superior to fixed learning rates and batch sizes, and what the optimal learning rate scheduling is. To the best of our knowledge, this is the first paper to provide a theoretical explanation for these aspects. Moreover, a new graduated optimization framework that uses a decaying learning rate and increasing batch size is analyzed and experimental results of image classification that support our theoretical findings are reported.
Authors: Marcello Carioni, Subhadip Mukherjee, Hong Ye Tan, Junqi Tang
Unsupervised deep learning approaches have recently become one of the crucial research areas in imaging owing to their ability to learn expressive and powerful reconstruction operators even when paired high-quality training data is scarcely available. In this chapter, we review theoretically principled unsupervised learning schemes for solving imaging inverse problems, with a particular focus on methods rooted in optimal transport and convex analysis. We begin by reviewing the optimal transport-based unsupervised approaches such as the cycle-consistency-based models and learned adversarial regularization methods, which have clear probabilistic interpretations. Subsequently, we give an overview of a recent line of works on provably convergent learned optimization algorithms applied to accelerate the solution of imaging inverse problems, alongside their dedicated unsupervised training schemes. We also survey a number of provably convergent plug-and-play algorithms (based on gradient-step deep denoisers), which are among the most important and widely applied unsupervised approaches for imaging problems. At the end of this survey, we provide an overview of a few related unsupervised learning frameworks that complement our focused schemes. Together with a detailed survey, we provide an overview of the key mathematical results that underlie the methods reviewed in the chapter to keep our discussion self-contained.
Authors: Fredy Vides, Idelfonso B. R. Nogueira, Lendy Banegas, Evelyn Flores
The investigation reported in this document focuses on identifying systems with symmetries using equivariant autoregressive reservoir computers. General results in structured matrix approximation theory are presented, exploring a two-fold approach. Firstly, a comprehensive examination of generic symmetry-preserving nonlinear time delay embedding is conducted. This involves analyzing time series data sampled from an equivariant system under study. Secondly, sparse least-squares methods are applied to discern approximate representations of the output coupling matrices. These matrices play a pivotal role in determining the nonlinear autoregressive representation of an equivariant system. The structural characteristics of these matrices are dictated by the set of symmetries inherent in the system. The document outlines prototypical algorithms derived from the described techniques, offering insight into their practical applications. Emphasis is placed on their effectiveness in the identification and predictive simulation of equivariant nonlinear systems, regardless of whether such systems exhibit chaotic behavior.
Authors: Vukasin Bozic, Danilo Dordevic, Daniele Coppola, Joseph Thommes, Sidak Pal Singh
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: Leonardo D. González, Victor M. Zavala
Bayesian optimization (BO) has proven to be an effective paradigm for the global optimization of expensive-to-sample systems. One of the main advantages of BO is its use of Gaussian processes (GPs) to characterize model uncertainty which can be leveraged to guide the learning and search process. However, BO typically treats systems as black-boxes and this limits the ability to exploit structural knowledge (e.g., physics and sparse interconnections). Composite functions of the form $f(x, y(x))$, wherein GP modeling is shifted from the performance function $f$ to an intermediate function $y$, offer an avenue for exploiting structural knowledge. However, the use of composite functions in a BO framework is complicated by the need to generate a probability density for $f$ from the Gaussian density of $y$ calculated by the GP (e.g., when $f$ is nonlinear it is not possible to obtain a closed-form expression). Previous work has handled this issue using sampling techniques; these are easy to implement and flexible but are computationally intensive. In this work, we introduce a new paradigm which allows for the efficient use of composite functions in BO; this uses adaptive linearizations of $f$ to obtain closed-form expressions for the statistical moments of the composite function. We show that this simple approach (which we call BOIS) enables the exploitation of structural knowledge, such as that arising in interconnected systems as well as systems that embed multiple GP models and combinations of physics and GP models. Using a chemical process optimization case study, we benchmark the effectiveness of BOIS against standard BO and sampling approaches. Our results indicate that BOIS achieves performance gains and accurately captures the statistics of composite functions.
Authors: Georg Wölflein, Dyke Ferber, Asier Rabasco Meneghetti, Omar S. M. El Nahhas, Daniel Truhn, Zunamys I. Carrero, David J. Harrison, Ognjen Arandjelović, Jakob N. Kather
Deep learning is revolutionising pathology, offering novel opportunities in disease prognosis and personalised treatment. Historically, stain normalisation has been a crucial preprocessing step in computational pathology pipelines, and persists into the deep learning era. Yet, with the emergence of feature extractors trained using self-supervised learning (SSL) on diverse pathology datasets, we call this practice into question. In an empirical evaluation of publicly available feature extractors, we find that omitting stain normalisation and image augmentations does not compromise downstream performance, while incurring substantial savings in memory and compute. Further, we show that the top-performing feature extractors are remarkably robust to variations in stain and augmentations like rotation in their latent space. Contrary to previous patch-level benchmarking studies, our approach emphasises clinical relevance by focusing on slide-level prediction tasks in a weakly supervised setting with external validation cohorts. This work represents the most comprehensive robustness evaluation of public pathology SSL feature extractors to date, involving more than 6,000 training runs across nine tasks, five datasets, three downstream architectures, and various preprocessing setups. Our findings stand to streamline digital pathology workflows by minimising preprocessing needs and informing the selection of feature extractors.
Authors: Yuanhui Huang, Wenzhao Zheng, Borui Zhang, Jie Zhou, Jiwen Lu
3D occupancy prediction is an important task for the robustness of vision-centric autonomous driving, which aims to predict whether each point is occupied in the surrounding 3D space. Existing methods usually require 3D occupancy labels to produce meaningful results. However, it is very laborious to annotate the occupancy status of each voxel. In this paper, we propose SelfOcc to explore a self-supervised way to learn 3D occupancy using only video sequences. We first transform the images into the 3D space (e.g., bird's eye view) to obtain 3D representation of the scene. We directly impose constraints on the 3D representations by treating them as signed distance fields. We can then render 2D images of previous and future frames as self-supervision signals to learn the 3D representations. We propose an MVS-embedded strategy to directly optimize the SDF-induced weights with multiple depth proposals. Our SelfOcc outperforms the previous best method SceneRF by 58.7% using a single frame as input on SemanticKITTI and is the first self-supervised work that produces reasonable 3D occupancy for surround cameras on nuScenes. SelfOcc produces high-quality depth and achieves state-of-the-art results on novel depth synthesis, monocular depth estimation, and surround-view depth estimation on the SemanticKITTI, KITTI-2015, and nuScenes, respectively. Code: https://github.com/huang-yh/SelfOcc.
Authors: Jie Fu, Qingqing Ye, Haibo Hu, Zhili Chen, Lulu Wang, Kuncan Wang, Xun Ran
Machine learning models are known to memorize private data to reduce their training loss, which can be inadvertently exploited by privacy attacks such as model inversion and membership inference. To protect against these attacks, differential privacy (DP) has become the de facto standard for privacy-preserving machine learning, particularly those popular training algorithms using stochastic gradient descent, such as DPSGD. Nonetheless, DPSGD still suffers from severe utility loss due to its slow convergence. This is partially caused by the random sampling, which brings bias and variance to the gradient, and partially by the Gaussian noise, which leads to fluctuation of gradient updates.
Our key idea to address these issues is to apply selective updates to the model training, while discarding those useless or even harmful updates. Motivated by this, this paper proposes DPSUR, a Differentially Private training framework based on Selective Updates and Release, where the gradient from each iteration is evaluated based on a validation test, and only those updates leading to convergence are applied to the model. As such, DPSUR ensures the training in the right direction and thus can achieve faster convergence than DPSGD. The main challenges lie in two aspects -- privacy concerns arising from gradient evaluation, and gradient selection strategy for model update. To address the challenges, DPSUR introduces a clipping strategy for update randomization and a threshold mechanism for gradient selection. Experiments conducted on MNIST, FMNIST, CIFAR-10, and IMDB datasets show that DPSUR significantly outperforms previous works in terms of convergence speed and model utility.
Authors: Niklas Smedemark-Margulies, Yunus Bicer, Elifnur Sunger, Tales Imbiriba, Eugene Tunik, Deniz Erdogmus, Mathew Yarossi, Robin Walters
We study the task of gesture recognition from electromyography (EMG), with the goal of enabling expressive human-computer interaction at high accuracy, while minimizing the time required for new subjects to provide calibration data. To fulfill these goals, we define combination gestures consisting of a direction component and a modifier component. New subjects only demonstrate the single component gestures and we seek to extrapolate from these to all possible single or combination gestures. We extrapolate to unseen combination gestures by combining the feature vectors of real single gestures to produce synthetic training data. This strategy allows us to provide a large and flexible gesture vocabulary, while not requiring new subjects to demonstrate combinatorially many example gestures. We pre-train an encoder and a combination operator using self-supervision, so that we can produce useful synthetic training data for unseen test subjects. To evaluate the proposed method, we collect a real-world EMG dataset, and measure the effect of augmented supervision against two baselines: a partially-supervised model trained with only single gesture data from the unseen subject, and a fully-supervised model trained with real single and real combination gesture data from the unseen subject. We find that the proposed method provides a dramatic improvement over the partially-supervised model, and achieves a useful classification accuracy that in some cases approaches the performance of the fully-supervised model.
Authors: Yixin Tang, Yicong Lin, Navdeep S. Sahni
This paper investigates an approach to both speed up business decision-making and lower the cost of learning through experimentation by factorizing business policies and employing fractional factorial experimental designs for their evaluation. We illustrate how this method integrates with advances in the estimation of heterogeneous treatment effects, elaborating on its advantages and foundational assumptions. We empirically demonstrate the implementation and benefits of our approach and assess its validity in evaluating consumer promotion policies at DoorDash, which is one of the largest delivery platforms in the US. Our approach discovers a policy with 5% incremental profit at 67% lower implementation cost.
Authors: Ben Pikus, Will LeVine, Tony Chen, Sean Hendryx
Foundation models, specifically Large Language Models (LLM's), have lately gained wide-spread attention and adoption. Reinforcement Learning with Human Feedback (RLHF) involves training a reward model to capture desired behaviors, which is then used to align an LLM. These reward models are additionally used at inference-time to estimate how well LLM responses adhere to those desired behaviors. However, there is little work measuring how robust these reward models are to distribution shifts. In this work, we evaluate how reward model performance - measured via accuracy and calibration (i.e. alignment between accuracy and confidence) - is affected by distribution shift. We show novel calibration patterns and accuracy drops due to OOD prompts and responses, and that the reward model is more sensitive to shifts in responses than prompts. Additionally, we adapt an OOD detection technique commonly used in classification to the reward model setting in order to detect these distribution shifts in prompts and responses.
Authors: Samuel Burbulla
Physics-informed neural networks (PINNs) effectively embed physical principles into machine learning, but often struggle with complex or alternating geometries. We propose a novel method for integrating geometric transformations within PINNs to robustly accommodate geometric variations. Our method incorporates a diffeomorphism as a mapping of a reference domain and adapts the derivative computation of the physics-informed loss function. This generalizes the applicability of PINNs not only to smoothly deformed domains, but also to lower-dimensional manifolds and allows for direct shape optimization while training the network. We demonstrate the effectivity of our approach on several problems: (i) Eikonal equation on Archimedean spiral, (ii) Poisson problem on surface manifold, (iii) Incompressible Stokes flow in deformed tube, and (iv) Shape optimization with Laplace operator. Through these examples, we demonstrate the enhanced flexibility over traditional PINNs, especially under geometric variations. The proposed framework presents an outlook for training deep neural operators over parametrized geometries, paving the way for advanced modeling with PDEs on complex geometries in science and engineering.
Authors: Chengyang Zhang, Yong Zhang, Qitan Shao, Bo Li, Yisheng Lv, Xinglin Piao, Baocai Yin
Traffic prediction is one of the most significant foundations in Intelligent Transportation Systems (ITS). Traditional traffic prediction methods rely only on historical traffic data to predict traffic trends and face two main challenges. 1) insensitivity to unusual events. 2) poor performance in long-term prediction. In this work, we explore how generative models combined with text describing the traffic system can be applied for traffic generation and name the task Text-to-Traffic Generation (TTG). The key challenge of the TTG task is how to associate text with the spatial structure of the road network and traffic data for generating traffic situations. To this end, we propose ChatTraffic, the first diffusion model for text-to-traffic generation. To guarantee the consistency between synthetic and real data, we augment a diffusion model with the Graph Convolutional Network (GCN) to extract spatial correlations of traffic data. In addition, we construct a large dataset containing text-traffic pairs for the TTG task. We benchmarked our model qualitatively and quantitatively on the released dataset. The experimental results indicate that ChatTraffic can generate realistic traffic situations from the text. Our code and dataset are available at https://github.com/ChyaZhang/ChatTraffic.
Authors: Zhihao Kong, Amirhossein Mollaali, Christian Moya, Na Lu, Guang Lin
Deep Operator Network (DeepONet) is a neural network framework for learning nonlinear operators such as those from ordinary differential equations (ODEs) describing complex systems. Multiple-input deep neural operators (MIONet) extended DeepONet to allow multiple input functions in different Banach spaces. MIONet offers flexibility in training dataset grid spacing, without constraints on output location. However, it requires offline inputs and cannot handle varying sequence lengths in testing datasets, limiting its real-time application in dynamic complex systems. This work redesigns MIONet, integrating Long Short Term Memory (LSTM) to learn neural operators from time-dependent data. This approach overcomes data discretization constraints and harnesses LSTM's capability with variable-length, real-time data. Factors affecting learning performance, like algorithm extrapolation ability are presented. The framework is enhanced with uncertainty quantification through a novel Bayesian method, sampling from MIONet parameter distributions. Consequently, we develop the B-LSTM-MIONet, incorporating LSTM's temporal strengths with Bayesian robustness, resulting in a more precise and reliable model for noisy datasets.
Authors: Prodromos Kolyvakis, Aristidis Likas
Unimodality, pivotal in statistical analysis, offers insights into dataset structures and drives sophisticated analytical procedures. While unimodality's confirmation is straightforward for one-dimensional data using methods like Silverman's approach and Hartigans' dip statistic, its generalization to higher dimensions remains challenging. By extrapolating one-dimensional unimodality principles to multi-dimensional spaces through linear random projections and leveraging point-to-point distancing, our method, rooted in $\alpha$-unimodality assumptions, presents a novel multivariate unimodality test named mud-pod. Both theoretical and empirical studies confirm the efficacy of our method in unimodality assessment of multidimensional datasets as well as in estimating the number of clusters.
Authors: Qiqi Su, Christos Kloukinas, Artur d'Avila Garcez
Multivariate time series have many applications, from healthcare and meteorology to life science. Although deep learning models have shown excellent predictive performance for time series, they have been criticised for being "black-boxes" or non-interpretable. This paper proposes a novel modular neural network model for multivariate time series prediction that is interpretable by construction. A recurrent neural network learns the temporal dependencies in the data while an attention-based feature selection component selects the most relevant features and suppresses redundant features used in the learning of the temporal dependencies. A modular deep network is trained from the selected features independently to show the users how features influence outcomes, making the model interpretable. Experimental results show that this approach can outperform state-of-the-art interpretable Neural Additive Models (NAM) and variations thereof in both regression and classification of time series tasks, achieving a predictive performance that is comparable to the top non-interpretable methods for time series, LSTM and XGBoost.
Authors: Daniel Barley, Holger Fröning
The rise of Deep Neural Networks (DNNs) has led to an increase in model size and complexity, straining the memory capacity of GPUs. Sparsity in DNNs, characterized as structural or ephemeral, has gained attention as a solution. This work focuses on ephemeral sparsity, aiming to reduce memory consumption during training. It emphasizes the significance of activations, an often overlooked component, and their role in memory usage. This work employs structured pruning in Block Sparse Compressed Row (BSR) format in combination with a magnitude-based criterion to efficiently prune activations. We furthermore introduce efficient block-sparse operators for GPUs and showcase their effectiveness, as well as the superior compression offered by block sparsity. We report the effectiveness of activation pruning by evaluating training speed, accuracy, and memory usage of large-scale neural architectures on the example of ResMLP on image classification tasks. As a result, we observe a memory reduction of up to 32% while maintaining accuracy. Ultimately, our approach aims to democratize large-scale model training, reduce GPU requirements, and address ecological concerns.
Authors: Tianshu Wen, Kookjin Lee, Youngsoo Choi
We present a new data-driven reduced-order modeling approach to efficiently solve parametrized partial differential equations (PDEs) for many-query problems. This work is inspired by the concept of implicit neural representation (INR), which models physics signals in a continuous manner and independent of spatial/temporal discretization. The proposed framework encodes PDE and utilizes a parametrized neural ODE (PNODE) to learn latent dynamics characterized by multiple PDE parameters. PNODE can be inferred by a hypernetwork to reduce the potential difficulties in learning PNODE due to a complex multilayer perceptron (MLP). The framework uses an INR to decode the latent dynamics and reconstruct accurate PDE solutions. Further, a physics-informed loss is also introduced to correct the prediction of unseen parameter instances. Incorporating the physics-informed loss also enables the model to be fine-tuned in an unsupervised manner on unseen PDE parameters. A numerical experiment is performed on a two-dimensional Burgers equation with a large variation of PDE parameters. We evaluate the proposed method at a large Reynolds number and obtain up to speedup of O(10^3) and ~1% relative error to the ground truth values.
Authors: Minbiao Han, Kumar Kshitij Patel, Han Shao, Lingxiao Wang
Federated learning is a machine learning protocol that enables a large population of agents to collaborate over multiple rounds to produce a single consensus model. There are several federated learning applications where agents may choose to defect permanently$-$essentially withdrawing from the collaboration$-$if they are content with their instantaneous model in that round. This work demonstrates the detrimental impact of such defections on the final model's robustness and ability to generalize. We also show that current federated optimization algorithms fail to disincentivize these harmful defections. We introduce a novel optimization algorithm with theoretical guarantees to prevent defections while ensuring asymptotic convergence to an effective solution for all participating agents. We also provide numerical experiments to corroborate our findings and demonstrate the effectiveness of our algorithm.