Authors: Minsi Ren, Bowen Gao, Bo Qiang, Yanyan Lan
Structure-based drug design (SBDD) stands at the forefront of drug discovery, emphasizing the creation of molecules that target specific binding pockets. Recent advances in this area have witnessed the adoption of deep generative models and geometric deep learning techniques, modeling SBDD as a conditional generation task where the target structure serves as context. Historically, evaluation of these models centered on docking scores, which quantitatively depict the predicted binding affinity between a molecule and its target pocket. Though state-of-the-art models purport that a majority of their generated ligands exceed the docking score of ground truth ligands in test sets, it begs the question: Do these scores align with real-world biological needs? In this paper, we introduce the delta score, a novel evaluation metric grounded in tangible pharmaceutical requisites. Our experiments reveal that molecules produced by current deep generative models significantly lag behind ground truth reference ligands when assessed with the delta score. This novel metric not only complements existing benchmarks but also provides a pivotal direction for subsequent research in the domain.
Authors: Xiaoqiong Xia, Chaoyu Zhu, Yuqi Shan, Fan Zhong, Lei Liu
Accurate and robust drug response prediction is of utmost importance in precision medicine. Although many models have been developed to utilize the representations of drugs and cancer cell lines for predicting cancer drug responses (CDR), their performances can be improved by addressing issues such as insufficient data modality, suboptimal fusion algorithms, and poor generalizability for novel drugs or cell lines. We introduce TransCDR, which uses transfer learning to learn drug representations and fuses multi-modality features of drugs and cell lines by a self-attention mechanism, to predict the IC50 values or sensitive states of drugs on cell lines. We are the first to systematically evaluate the generalization of the CDR prediction model to novel (i.e., never-before-seen) compound scaffolds and cell line clusters. TransCDR shows better generalizability than 8 state-of-the-art models. TransCDR outperforms its 5 variants that train drug encoders (i.e., RNN and AttentiveFP) from scratch under various scenarios. The most critical contributors among multiple drug notations and omics profiles are Extended Connectivity Fingerprint and genetic mutation. Additionally, the attention-based fusion module further enhances the predictive performance of TransCDR. TransCDR, trained on the GDSC dataset, demonstrates strong predictive performance on the external testing set CCLE. It is also utilized to predict missing CDRs on GDSC. Moreover, we investigate the biological mechanisms underlying drug response by classifying 7,675 patients from TCGA into drug-sensitive or drug-resistant groups, followed by a Gene Set Enrichment Analysis. TransCDR emerges as a potent tool with significant potential in drug response prediction. The source code and data can be accessed at https://github.com/XiaoqiongXia/TransCDR.
Authors: Stefan Bosse, Dirk Lehmhus
Detection and characterization of hidden defects, impurities, and damages in layered composites like Fibre laminates, e.g., Fibre Metal Laminates (FML), as well as in monolithic materials, e.g., aluminum die casting materials, is still a challenge. This work discusses methods and challenges in data-driven modeling of automated damage and defect detectors using X-ray single- and multi-projection (CT) images. Three main issues are identified: Data and feature variance, data feature labeling (for supervised machine learning), and the missing ground truth. It will be shown that only simulation of data can deliver a ground truth data set and accurate labeling. Noise has significant impact on the feature detection and will be discussed. Data-driven feature detectors are implemented with semantic pixel- or z-profile Convolutional Neural Networks and LSTM Auto-encoders. Data is measured with three different devices: A low-quality and low-cost (Low-Q), a mid- and a high-quality (micro-CT, Mid-/High-Q) device. The goals of this work are the training of robust and generalized feature detectors with synthetic data and the transition from High- and Mid-Q laboratory measuring technologies towards in-field usable technologies and methods.
Authors: Doyoung Kim, Susik Yoon, Dongmin Park, Youngjun Lee, Hwanjun Song, Jihwan Bang, Jae-Gil Lee
In real-world continual learning scenarios, tasks often exhibit intricate and unpredictable semantic shifts, posing challenges for fixed prompt management strategies. We identify the inadequacy of universal and specific prompting in handling these dynamic shifts. Universal prompting is ineffective for tasks with abrupt semantic changes, while specific prompting struggles with overfitting under mild semantic shifts. To overcome these limitations, we propose an adaptive prompting approach that tailors minimal yet sufficient prompts based on the task semantics. Our methodology, SemPrompt, incorporates a two-level semantic grouping process: macroscopic semantic assignment and microscopic semantic refinement. This process ensures optimal prompt utilization for varying task semantics, improving the efficiency and effectiveness of learning in real-world CL settings. Our experimental results demonstrate that SemPrompt consistently outperforms existing methods in adapting to diverse semantic shifts in tasks.
Authors: Nikolaos Ioannis Bountos, Maria Sdraka, Angelos Zavras, Ilektra Karasante, Andreas Karavias, Themistocles Herekakis, Angeliki Thanasou, Dimitrios Michail, Ioannis Papoutsis
Global floods, exacerbated by climate change, pose severe threats to human life, infrastructure, and the environment. This urgency is highlighted by recent catastrophic events in Pakistan and New Zealand, underlining the critical need for precise flood mapping for guiding restoration efforts, understanding vulnerabilities, and preparing for future events. While Synthetic Aperture Radar (SAR) offers day-and-night, all-weather imaging capabilities, harnessing it for deep learning is hindered by the absence of a large annotated dataset. To bridge this gap, we introduce Kuro Siwo, a meticulously curated multi-temporal dataset, spanning 32 flood events globally. Our dataset maps more than 63 billion m2 of land, with 12.1 billion of them being either a flooded area or a permanent water body. Kuro Siwo stands out for its unparalleled annotation quality to facilitate rapid flood mapping in a supervised setting. We also augment learning by including a large unlabeled set of SAR samples, aimed at self-supervised pretraining. We provide an extensive benchmark and strong baselines for a diverse set of flood events from Europe, America, Africa and Australia. Our benchmark demonstrates the quality of Kuro Siwo annotations, training models that can achieve $\approx$ 85% and $\approx$ 87% in F1-score for flooded areas and general water detection respectively. This work calls on the deep learning community to develop solution-driven algorithms for rapid flood mapping, with the potential to aid civil protection and humanitarian agencies amid climate change challenges. Our code and data will be made available at https://github.com/Orion-AI-Lab/KuroSiwo
Authors: Rohit Bharadwaj, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan
In this work, we address the challenging and emergent problem of novel object detection (NOD), focusing on the accurate detection of both known and novel object categories during inference. Traditional object detection algorithms are inherently closed-set, limiting their capability to handle NOD. We present a novel approach to transform existing closed-set detectors into open-set detectors. This transformation is achieved by leveraging the complementary strengths of pre-trained foundational models, specifically CLIP and SAM, through our cooperative mechanism. Furthermore, by integrating this mechanism with state-of-the-art open-set detectors such as GDINO, we establish new benchmarks in object detection performance. Our method achieves 17.42 mAP in novel object detection and 42.08 mAP for known objects on the challenging LVIS dataset. Adapting our approach to the COCO OVD split, we surpass the current state-of-the-art by a margin of 7.2 $ \text{AP}_{50} $ for novel classes. Our code is available at https://github.com/rohit901/cooperative-foundational-models .
Authors: Ling Chen, Zhishen Huang, Yong Long, Saiprasad Ravishankar
Traditional model-based image reconstruction (MBIR) methods combine forward and noise models with simple object priors. Recent application of deep learning methods for image reconstruction provides a successful data-driven approach to addressing the challenges when reconstructing images with undersampled measurements or various types of noise. In this work, we propose a hybrid supervised-unsupervised learning framework for X-ray computed tomography (CT) image reconstruction. The proposed learning formulation leverages both sparsity or unsupervised learning-based priors and neural network reconstructors to simulate a fixed-point iteration process. Each proposed trained block consists of a deterministic MBIR solver and a neural network. The information flows in parallel through these two reconstructors and is then optimally combined. Multiple such blocks are cascaded to form a reconstruction pipeline. We demonstrate the efficacy of this learned hybrid model for low-dose CT image reconstruction with limited training data, where we use the NIH AAPM Mayo Clinic Low Dose CT Grand Challenge dataset for training and testing. In our experiments, we study combinations of supervised deep network reconstructors and MBIR solver with learned sparse representation-based priors or analytical priors. Our results demonstrate the promising performance of the proposed framework compared to recent low-dose CT reconstruction methods.
Authors: Xuemei Li, Huirong Fu
Numerous studies have proved their effective strength in detecting Control Area Network (CAN) attacks. In the realm of understanding the human semantic space, transformer-based models have demonstrated remarkable effectiveness. Leveraging pre-trained transformers has become a common strategy in various language-related tasks, enabling these models to grasp human semantics more comprehensively. To delve into the adaptability evaluation on pre-trained models for CAN intrusion detection, we have developed two distinct models: CAN-SecureBERT and CAN-LLAMA2. Notably, our CAN-LLAMA2 model surpasses the state-of-the-art models by achieving an exceptional performance 0.999993 in terms of balanced accuracy, precision detection rate, F1 score, and a remarkably low false alarm rate of 3.10e-6. Impressively, the false alarm rate is 52 times smaller than that of the leading model, MTH-IDS (Multitiered Hybrid Intrusion Detection System). Our study underscores the promise of employing a Large Language Model as the foundational model, while incorporating adapters for other cybersecurity-related tasks and maintaining the model's inherent language-related capabilities.
Authors: Wei Jiang, Zhuang Xiong, Feng Liu, Nan Ye, Hongfu Sun
Supervised deep learning methods have shown promise in Magnetic Resonance Imaging (MRI) undersampling reconstruction, but their requirement for paired data limits their generalizability to the diverse MRI acquisition parameters. Recently, unsupervised controllable generative diffusion models have been applied to MRI undersampling reconstruction, without paired data or model retraining for different MRI acquisitions. However, diffusion models are generally slow in sampling and state-of-the-art acceleration techniques can lead to sub-optimal results when directly applied to the controllable generation process. This study introduces a new algorithm called Predictor-Projector-Noisor (PPN), which enhances and accelerates controllable generation of diffusion models for MRI undersampling reconstruction. Our results demonstrate that PPN produces high-fidelity MR images that conform to undersampled k-space measurements with significantly shorter reconstruction time than other controllable sampling methods. In addition, the unsupervised PPN accelerated diffusion models are adaptable to different MRI acquisition parameters, making them more practical for clinical use than supervised learning techniques.
Authors: Maëlys Solal (ARAMIS), Ravi Hassanaly (ARAMIS), Ninon Burgos (ARAMIS)
Unsupervised anomaly detection is a popular approach for the analysis of neuroimaging data as it allows to identify a wide variety of anomalies from unlabelled data. It relies on building a subject-specific model of healthy appearance to which a subject's image can be compared to detect anomalies. In the literature, it is common for anomaly detection to rely on analysing the residual image between the subject's image and its pseudo-healthy reconstruction. This approach however has limitations partly due to the pseudo-healthy reconstructions being imperfect and to the lack of natural thresholding mechanism. Our proposed method, inspired by Z-scores, leverages the healthy population variability to overcome these limitations. Our experiments conducted on FDG PET scans from the ADNI database demonstrate the effectiveness of our approach in accurately identifying Alzheimer's disease related anomalies.
Authors: Abdul Rahoof, Vivek Chaturvedi, Mahesh Raveendranatha Panicker, Muhammad Shafique
Accelerating compute intensive non-real-time beam-forming algorithms in ultrasound imaging using deep learning architectures has been gaining momentum in the recent past. Nonetheless, the complexity of the state-of-the-art deep learning techniques poses challenges for deployment on resource-constrained edge devices. In this work, we propose a novel vision transformer based tiny beamformer (Tiny-VBF), which works on the raw radio-frequency channel data acquired through single-angle plane wave insonification. The output of our Tiny-VBF provides fast envelope detection requiring very low frame rate, i.e. 0.34 GOPs/Frame for a frame size of 368 x 128 in comparison to the state-of-the-art deep learning models. It also exhibited an 8% increase in contrast and gains of 5% and 33% in axial and lateral resolution respectively when compared to Tiny-CNN on in-vitro dataset. Additionally, our model showed a 4.2% increase in contrast and gains of 4% and 20% in axial and lateral resolution respectively when compared against conventional Delay-and-Sum (DAS) beamformer. We further propose an accelerator architecture and implement our Tiny-VBF model on a Zynq UltraScale+ MPSoC ZCU104 FPGA using a hybrid quantization scheme with 50% less resource consumption compared to the floating-point implementation, while preserving the image quality.
Authors: Yiming Hu, Xiangxiang Chu, Bo Zhang
Neural Architecture Search (NAS) currently relies heavily on labeled data, which is both expensive and time-consuming to acquire. In this paper, we propose a novel NAS framework based on Masked Autoencoders (MAE) that eliminates the need for labeled data during the search process. By replacing the supervised learning objective with an image reconstruction task, our approach enables the robust discovery of network architectures without compromising performance and generalization ability. Additionally, we address the problem of performance collapse encountered in the widely-used Differentiable Architecture Search (DARTS) method in the unsupervised paradigm by introducing a multi-scale decoder. Through extensive experiments conducted on various search spaces and datasets, we demonstrate the effectiveness and robustness of the proposed method, providing empirical evidence of its superiority over baseline approaches.
Authors: Xiaoping Zheng, Bert Otten, Michiel F Reneman, Claudine JC Lamoth
Gait analysis holds significant importance in monitoring daily health, particularly among older adults. Advancements in sensor technology enable the capture of movement in real-life environments and generate big data. Machine learning, notably deep learning (DL), shows promise to use these big data in gait analysis. However, the inherent black-box nature of these models poses challenges for their clinical application. This study aims to enhance transparency in DL-based gait classification for aged-related gait patterns using Explainable Artificial Intelligence, such as SHAP.
A total of 244 subjects, comprising 129 adults and 115 older adults (age>65), were included. They performed a 3-minute walking task while accelerometers were affixed to the lumbar segment L3. DL models, convolutional neural network (CNN) and gated recurrent unit (GRU), were trained using 1-stride and 8-stride accelerations, respectively, to classify adult and older adult groups. SHAP was employed to explain the models' predictions.
CNN achieved a satisfactory performance with an accuracy of 81.4% and an AUC of 0.89, and GRU demonstrated promising results with an accuracy of 84.5% and an AUC of 0.94. SHAP analysis revealed that both CNN and GRU assigned higher SHAP values to the data from vertical and walking directions, particularly emphasizing data around heel contact, spanning from the terminal swing to loading response phases. Furthermore, SHAP values indicated that GRU did not treat every stride equally.
CNN accurately distinguished between adults and older adults based on the characteristics of a single stride's data. GRU achieved accurate classification by considering the relationships and subtle differences between strides. In both models, data around heel contact emerged as most critical, suggesting differences in acceleration and deceleration patterns during walking between different age groups.
Authors: Neelanjana Pal (Institute for Software Integrated Systems, Vanderbilt University,), Taylor T Johnson (Institute for Software Integrated Systems, Vanderbilt University)
Formally verifying audio classification systems is essential to ensure accurate signal classification across real-world applications like surveillance, automotive voice commands, and multimedia content management, preventing potential errors with serious consequences. Drawing from recent research, this study advances the utilization of star-set-based formal verification, extended through reachability analysis, tailored explicitly for Long Short-Term Memory architectures and their Convolutional variations within the audio classification domain. By conceptualizing the classification process as a sequence of set operations, the star set-based reachability approach streamlines the exploration of potential operational states attainable by the system. The paper serves as an encompassing case study, validating and verifying sequence audio classification analytics within real-world contexts. It accentuates the necessity for robustness verification to ensure precise and dependable predictions, particularly in light of the impact of noise on the accuracy of output classifications.
Authors: Jia-Hong Huang, Chao-Han Huck Yang, Pin-Yu Chen, Min-Hung Chen, Marcel Worring
The aim of video summarization is to shorten videos automatically while retaining the key information necessary to convey the overall story. Video summarization methods mainly rely on visual factors, such as visual consecutiveness and diversity, which may not be sufficient to fully understand the content of the video. There are other non-visual factors, such as interestingness, representativeness, and storyline consistency that should also be considered for generating high-quality video summaries. Current methods do not adequately take into account these non-visual factors, resulting in suboptimal performance. In this work, a new approach to video summarization is proposed based on insights gained from how humans create ground truth video summaries. The method utilizes a conditional modeling perspective and introduces multiple meaningful random variables and joint distributions to characterize the key components of video summarization. Helper distributions are employed to improve the training of the model. A conditional attention module is designed to mitigate potential performance degradation in the presence of multi-modal input. The proposed video summarization method incorporates the above innovative design choices that aim to narrow the gap between human-generated and machine-generated video summaries. Extensive experiments show that the proposed approach outperforms existing methods and achieves state-of-the-art performance on commonly used video summarization datasets.
Authors: Akira Sone, Naoki Yamamoto
Motivated by the great success of classical generative models in machine learning, enthusiastic exploration of their quantum version has recently started. To depart on this journey, it is important to develop a relevant metric to evaluate the quality of quantum generative models; in the classical case, one such examples is the inception score. In this paper, we propose the quantum inception score, which relates the quality to the classical capacity of the quantum channel that classifies a given dataset. We prove that, under this proposed measure, the quantum generative models provide better quality than their classical counterparts because of the presence of quantum coherence and entanglement. Finally, we harness the quantum fluctuation theorem to characterize the physical limitation of the quality of quantum generative models.
Authors: Hritik Gopal Shah, Behrouz Azimian, Anamitra Pal
Traditional smart meter measurements lack the granularity needed for real-time decision-making. To address this practical problem, we create a generative adversarial networks (GAN) model that enforces temporal consistency on its high-resolution outputs via hard inequality constraints using a convex optimization layer. A unique feature of our GAN model is that it is trained solely on slow timescale aggregated power information obtained from historical smart meter data. The results demonstrate that the model can successfully create minutely interval temporally-correlated instantaneous power injection profiles from 15-minute average power consumption information. This innovative approach, emphasizing inter-neuron constraints, offers a promising avenue for improved high-speed state estimation in distribution systems and enhances the applicability of data-driven solutions for monitoring such systems.
Authors: Wouter W. L. Nuijten, Vlado Menkovski
We propose a method for the classification of objects that are structured as random trees. Our aim is to model a distribution over the node label assignments in settings where the tree data structure is associated with node attributes (typically high dimensional embeddings). The tree topology is not predetermined and none of the label assignments are present during inference. Other methods that produce a distribution over node label assignment in trees (or more generally in graphs) either assume conditional independence of the label assignment, operate on a fixed graph topology, or require part of the node labels to be observed. Our method defines a Markov Network with the corresponding topology of the random tree and an associated Gibbs distribution. We parameterize the Gibbs distribution with a Graph Neural Network that operates on the random tree and the node embeddings. This allows us to estimate the likelihood of node assignments for a given random tree and use MCMC to sample from the distribution of node assignments.
We evaluate our method on the tasks of node classification in trees on the Stanford Sentiment Treebank dataset. Our method outperforms the baselines on this dataset, demonstrating its effectiveness for modeling joint distributions of node labels in random trees.
Authors: Tianyi Xie, Zeshun Zong, Yuxin Qiu, Xuan Li, Yutao Feng, Yin Yang, Chenfanfu Jiang
We introduce PhysGaussian, a new method that seamlessly integrates physically grounded Newtonian dynamics within 3D Gaussians to achieve high-quality novel motion synthesis. Employing a custom Material Point Method (MPM), our approach enriches 3D Gaussian kernels with physically meaningful kinematic deformation and mechanical stress attributes, all evolved in line with continuum mechanics principles. A defining characteristic of our method is the seamless integration between physical simulation and visual rendering: both components utilize the same 3D Gaussian kernels as their discrete representations. This negates the necessity for triangle/tetrahedron meshing, marching cubes, "cage meshes," or any other geometry embedding, highlighting the principle of "what you see is what you simulate (WS$^2$)." Our method demonstrates exceptional versatility across a wide variety of materials--including elastic entities, metals, non-Newtonian fluids, and granular materials--showcasing its strong capabilities in creating diverse visual content with novel viewpoints and movements. Our project page is at: https://xpandora.github.io/PhysGaussian/
Authors: Chenyang Gao, Yue Gu, Ivan Marsic
In supervised speech separation, permutation invariant training (PIT) is widely used to handle label ambiguity by selecting the best permutation to update the model. Despite its success, previous studies showed that PIT is plagued by excessive label assignment switching in adjacent epochs, impeding the model to learn better label assignments. To address this issue, we propose a novel training strategy, dynamic sample dropout (DSD), which considers previous best label assignments and evaluation metrics to exclude the samples that may negatively impact the learned label assignments during training. Additionally, we include layer-wise optimization (LO) to improve the performance by solving layer-decoupling. Our experiments showed that combining DSD and LO outperforms the baseline and solves excessive label assignment switching and layer-decoupling issues. The proposed DSD and LO approach is easy to implement, requires no extra training sets or steps, and shows generality to various speech separation tasks.
Authors: Csaba Toth, Harald Oberhauser, Zoltan Szabo
Tensor algebras give rise to one of the most powerful measures of similarity for sequences of arbitrary length called the signature kernel accompanied with attractive theoretical guarantees from stochastic analysis. Previous algorithms to compute the signature kernel scale quadratically in terms of the length and the number of the sequences. To mitigate this severe computational bottleneck, we develop a random Fourier feature-based acceleration of the signature kernel acting on the inherently non-Euclidean domain of sequences. We show uniform approximation guarantees for the proposed unbiased estimator of the signature kernel, while keeping its computation linear in the sequence length and number. In addition, combined with recent advances on tensor projections, we derive two even more scalable time series features with favourable concentration properties and computational complexity both in time and memory. Our empirical results show that the reduction in computational cost comes at a negligible price in terms of accuracy on moderate-sized datasets, and it enables one to scale to large datasets up to a million time series.
Authors: Trevor E. Pogue, Nicola Nicolici
We introduce a new algorithm called the Free-pipeline Fast Inner Product (FFIP) and its hardware architecture that improve an under-explored fast inner-product algorithm (FIP) proposed by Winograd in 1968. Unlike the unrelated Winograd minimal filtering algorithms for convolutional layers, FIP is applicable to all machine learning (ML) model layers that can mainly decompose to matrix multiplication, including fully-connected, convolutional, recurrent, and attention/transformer layers. We implement FIP for the first time in an ML accelerator then present our FFIP algorithm and generalized architecture which inherently improve FIP's clock frequency and, as a consequence, throughput for a similar hardware cost. Finally, we contribute ML-specific optimizations for the FIP and FFIP algorithms and architectures. We show that FFIP can be seamlessly incorporated into traditional fixed-point systolic array ML accelerators to achieve the same throughput with half the number of multiply-accumulate (MAC) units, or it can double the maximum systolic array size that can fit onto devices with a fixed hardware budget. Our FFIP implementation for non-sparse ML models with 8 to 16-bit fixed-point inputs achieves higher throughput and compute efficiency than the best-in-class prior solutions on the same type of compute platform.
Authors: Niyousha Rahimi, Mehran Mesbahi
This paper addresses the problem of designing a data-driven feedback controller for complex nonlinear dynamical systems in the presence of time-varying disturbances with unknown dynamics. Such disturbances are modeled as the "unknown" part of the system dynamics. The goal is to achieve finite-time regulation of system states through direct policy updates while also generating informative data that can subsequently be used for data-driven stabilization or system identification. First, we expand upon the notion of "regularizability" and characterize this system characteristic for a linear time-varying representation of the nonlinear system with locally-bounded higher-order terms. "Rapid-regularizability" then gauges the extent by which a system can be regulated in finite time, in contrast to its asymptotic behavior. We then propose the Data-Guided Regulation for Adaptive Nonlinear Control ( DG-RAN) algorithm, an online iterative synthesis procedure that utilizes discrete time-series data from a single trajectory for regulating system states and identifying disturbance dynamics. The effectiveness of our approach is demonstrated on a 6-DOF power descent guidance problem in the presence of adverse environmental disturbances.
Authors: Mark Horeni, Siddharth Joshi
Deploying Convolutional Neural Networks (CNNs) on edge platforms necessitates efficient hardware acceleration. Any unnecessary data movement in such accelerators can unacceptably degrade performance and efficiency. To address this, we develop a layer fusion technique targeting CNNs, that reduces off-chip data communication using a Genetic Algorithm (GA) applied to graph-based topological sort. Results show a 1.8$\times$ increase in energy efficiency and 1.9$\times$ improvement in energy-delay product (EDP) for MobileNet-v3 on a SIMBA-like mobile architecture. Our approach consistently improves workload performance, averaging 1.4$\times$ improvement to EDP for SIMBA and 1.12$\times$ for Eyeriss.
Authors: Hongming Zhang, Tongzheng Ren, Chenjun Xiao, Dale Schuurmans, Bo Dai
In real-world reinforcement learning problems, the state information is often only partially observable, which breaks the basic assumption in Markov decision processes, and thus, leads to inferior performances. Partially Observable Markov Decision Processes have been introduced to explicitly take the issue into account for learning, exploration, and planning, but presenting significant computational and statistical challenges. To address these difficulties, we exploit the representation view, which leads to a coherent design framework for a practically tractable reinforcement learning algorithm upon partial observations. We provide a theoretical analysis for justifying the statistical efficiency of the proposed algorithm. We also empirically demonstrate the proposed algorithm can surpass state-of-the-art performance with partial observations across various benchmarks, therefore, pushing reliable reinforcement learning towards more practical applications.
Authors: Tommaso Giovannelli, Oumaima Sohab, Luis Nunes Vicente
We are interested in assessing the use of neural networks as surrogate models to approximate and minimize objective functions in optimization problems. While neural networks are widely used for machine learning tasks such as classification and regression, their application in solving optimization problems has been limited. Our study begins by determining the best activation function for approximating the objective functions of popular nonlinear optimization test problems, and the evidence provided shows that~SiLU has the best performance. We then analyze the accuracy of function value, gradient, and Hessian approximations for such objective functions obtained through interpolation/regression models and neural networks. When compared to interpolation/regression models, neural networks can deliver competitive zero- and first-order approximations (at a high training cost) but underperform on second-order approximation. However, it is shown that combining a neural net activation function with the natural basis for quadratic interpolation/regression can waive the necessity of including cross terms in the natural basis, leading to models with fewer parameters to determine. Lastly, we provide evidence that the performance of a state-of-the-art derivative-free optimization algorithm can hardly be improved when the gradient of an objective function is approximated using any of the surrogate models considered, including neural networks.
Authors: Xiangjian Jiang, Yanyi Pu
Dynamic Graph Neural Networks (DGNNs) have emerged as the predominant approach for processing dynamic graph-structured data. However, the influence of temporal information on model performance and robustness remains insufficiently explored, particularly regarding how models address prediction tasks with different time granularities. In this paper, we explore the impact of time granularity when training DGNNs on dynamic graphs through extensive experiments. We examine graphs derived from various domains and compare three different DGNNs to the baseline model across four varied time granularities. We mainly consider the interplay between time granularities, model architectures, and negative sampling strategies to obtain general conclusions. Our results reveal that a sophisticated memory mechanism and proper time granularity are crucial for a DGNN to deliver competitive and robust performance in the dynamic link prediction task. We also discuss drawbacks in considered models and datasets and propose promising directions for future research on the time granularity of temporal graphs.
Authors: Bibek Poudel, Weizi Li
Human-driven vehicles can amplify naturally occurring perturbations in traffic, leading to congestion and consequently increased fuel consumption, higher collision risks, and reduced capacity utilization. While previous research has highlighted that a fraction of Robot Vehicles (RVs) can mitigate these issues, they often rely on simulations with simplistic, model-based Human-driven Vehicles (HVs) during car-following scenarios. Diverging from this trend, in this study, we analyze real-world human driving trajectories, extracting a wide range of acceleration behaviors during car-following. We then incorporate these behaviors in simulation where RVs from prior studies are employed to mitigate congestion, and evaluate their safety, efficiency, and stability. Further, we also introduce a reinforcement learning based RV that utilizes a congestion stage classifier neural network to optimize either "safety+stability" or "efficiency" in the presence of the diverse human driving behaviors. We evaluate the proposed RVs in two different mixed traffic control environments at various densities, configurations, and penetration rates and compare with the existing RVs.
Authors: Sayak Mukherjee, Ramij R. Hossain, Sheik M. Mohiuddin, Yuan Liu, Wei Du, Veronica Adetola, Rohit A. Jinsiwale, Qiuhua Huang, Tianzhixi Yin, Ankit Singhal
Improving system-level resiliency of networked microgrids is an important aspect with increased population of inverter-based resources (IBRs). This paper (1) presents resilient control design in presence of adversarial cyber-events, and proposes a novel federated reinforcement learning (Fed-RL) approach to tackle (a) model complexities, unknown dynamical behaviors of IBR devices, (b) privacy issues regarding data sharing in multi-party-owned networked grids, and (2) transfers learned controls from simulation to hardware-in-the-loop test-bed, thereby bridging the gap between simulation and real world. With these multi-prong objectives, first, we formulate a reinforcement learning (RL) training setup generating episodic trajectories with adversaries (attack signal) injected at the primary controllers of the grid forming (GFM) inverters where RL agents (or controllers) are being trained to mitigate the injected attacks. For networked microgrids, the horizontal Fed-RL method involving distinct independent environments is not appropriate, leading us to develop vertical variant Federated Soft Actor-Critic (FedSAC) algorithm to grasp the interconnected dynamics of networked microgrid. Next, utilizing OpenAI Gym interface, we built a custom simulation set-up in GridLAB-D/HELICS co-simulation platform, named Resilient RL Co-simulation (ResRLCoSIM), to train the RL agents with IEEE 123-bus benchmark test systems comprising 3 interconnected microgrids. Finally, the learned policies in simulation world are transferred to the real-time hardware-in-the-loop test-bed set-up developed using high-fidelity Hypersim platform. Experiments show that the simulator-trained RL controllers produce convincing results with the real-time test-bed set-up, validating the minimization of sim-to-real gap.
Authors: Jikai Jin, Vasilis Syrgkanis
This paper studies causal representation learning, the task of recovering high-level latent variables and their causal relationships from low-level data that we observe, assuming access to observations generated from multiple environments. While existing works are able to prove full identifiability of the underlying data generating process, they typically assume access to single-node, hard interventions which is rather unrealistic in practice. The main contribution of this paper is characterize a notion of identifiability which is provably the best one can achieve when hard interventions are not available. First, for linear causal models, we provide identifiability guarantee for data observed from general environments without assuming any similarities between them. While the causal graph is shown to be fully recovered, the latent variables are only identified up to an effect-domination ambiguity (EDA). We then propose an algorithm, LiNGCReL which is guaranteed to recover the ground-truth model up to EDA, and we demonstrate its effectiveness via numerical experiments. Moving on to general non-parametric causal models, we prove the same idenfifiability guarantee assuming access to groups of soft interventions. Finally, we provide counterparts of our identifiability results, indicating that EDA is basically inevitable in our setting.
Authors: Guanyu Zhang, Feng Li, Yanfei Kang
As the popularity of hierarchical point forecast reconciliation methods increases, there is a growing interest in probabilistic forecast reconciliation. Many studies have utilized machine learning or deep learning techniques to implement probabilistic forecasting reconciliation and have made notable progress. However, these methods treat the reconciliation step as a fixed and hard post-processing step, leading to a trade-off between accuracy and coherency. In this paper, we propose a new approach for probabilistic forecast reconciliation. Unlike existing approaches, our proposed approach fuses the prediction step and reconciliation step into a deep learning framework, making the reconciliation step more flexible and soft by introducing the Kullback-Leibler divergence regularization term into the loss function. The approach is evaluated using three hierarchical time series datasets, which shows the advantages of our approach over other probabilistic forecast reconciliation methods.
Authors: Armenak Petrosyan, Konstantin Pieper, Hoang Tran
We propose and analyze an efficient algorithm for solving the joint sparse recovery problem using a new regularization-based method, named orthogonally weighted $\ell_{2,1}$ ($\mathit{ow}\ell_{2,1}$), which is specifically designed to take into account the rank of the solution matrix. This method has applications in feature extraction, matrix column selection, and dictionary learning, and it is distinct from commonly used $\ell_{2,1}$ regularization and other existing regularization-based approaches because it can exploit the full rank of the row-sparse solution matrix, a key feature in many applications. We provide a proof of the method's rank-awareness, establish the existence of solutions to the proposed optimization problem, and develop an efficient algorithm for solving it, whose convergence is analyzed. We also present numerical experiments to illustrate the theory and demonstrate the effectiveness of our method on real-life problems.
Authors: Trang H. Tran, Lam M. Nguyen, Kyongmin Yeo, Nam Nguyen, Roman Vaculin
Foundation models have recently gained attention within the field of machine learning thanks to its efficiency in broad data processing. While researchers had attempted to extend this success to time series models, the main challenge is effectively extracting representations and transferring knowledge from pretraining datasets to the target finetuning dataset. To tackle this issue, we introduce a novel pretraining procedure that leverages supervised contrastive learning to distinguish features within each pretraining dataset. This pretraining phase enables a probabilistic similarity metric, which assesses the likelihood of a univariate sample being closely related to one of the pretraining datasets. Subsequently, using this similarity metric as a guide, we propose a fine-tuning procedure designed to enhance the accurate prediction of the target data by aligning it more closely with the learned dynamics of the pretraining datasets. Our experiments have shown promising results which demonstrate the efficacy of our approach.
Authors: Kyle A. Pearson, Eldar Noe, Daniel Zhao, Alphan Altinok, Alex Morgan
One of the main objectives of the Mars Exploration Program is to search for evidence of past or current life on the planet. To achieve this, Mars exploration has been focusing on regions that may have liquid or frozen water. A set of critical areas may have seen cycles of ice thawing in the relatively recent past in response to periodic changes in the obliquity of Mars. In this work, we use convolutional neural networks to detect surface regions containing "Brain Coral" terrain, a landform on Mars whose similarity in morphology and scale to sorted stone circles on Earth suggests that it may have formed as a consequence of freeze/thaw cycles. We use large images (~100-1000 megapixels) from the Mars Reconnaissance Orbiter to search for these landforms at resolutions close to a few tens of centimeters per pixel (~25--50 cm). Over 52,000 images (~28 TB) were searched (~5% of the Martian surface) where we found detections in over 200 images. To expedite the processing we leverage a classifier network (prior to segmentation) in the Fourier domain that can take advantage of JPEG compression by leveraging blocks of coefficients from a discrete cosine transform in lieu of decoding the entire image at the full spatial resolution. The hybrid pipeline approach maintains ~93% accuracy while cutting down on ~95% of the total processing time compared to running the segmentation network at the full resolution on every image. The timely processing of big data sets helps inform mission operations, geologic surveys to prioritize candidate landing sites, avoid hazardous areas, or map the spatial extent of certain terrain. The segmentation masks and source code are available on Github for the community to explore and build upon.
Authors: Jiming Yang, Yutong Zheng, Jiahong Zhou, Huiyu Li, Jun Yin
The ability to detect macroscopic changes is important for probing the behaviors of experimental many-body systems from the classical to the quantum realm. Although abrupt changes near phase boundaries can easily be detected, subtle macroscopic changes are much more difficult to detect as the changes can be obscured by noise. In this study, as a toy model for detecting subtle macroscopic changes in many-body systems, we try to differentiate scalar field samples at varying temperatures. We compare different methods for making such differentiations, from physics method, statistics method, to AI method. Our finding suggests that the AI method outperforms both the statistical method and the physics method in its sensitivity. Our result provides a proof-of-concept that AI can potentially detect macroscopic changes in many-body systems that elude physical measures.
Authors: Risto Miikkulainen, Olivier Francon, Daniel Young, Elliot Meyerson, Babak Hodjat
How areas of land are allocated for different uses, such as forests, urban, and agriculture, has a large effect on carbon balance, and therefore climate change. Based on available historical data on changes in land use and a simulation of carbon emissions/absorption, a surrogate model can be learned that makes it possible to evaluate the different options available to decision-makers efficiently. An evolutionary search process can then be used to discover effective land-use policies for specific locations. Such a system was built on the Project Resilience platform and evaluated with the Land-Use Harmonization dataset and the BLUE simulator. It generates Pareto fronts that trade off carbon impact and amount of change customized to different locations, thus providing a potentially useful tool for land-use planning.
Authors: Yadong Zhang, Pranav M Karve, Sankaran Mahadevan
We investigate the utility of graph neural networks (GNNs) as proxies of power grid operational decision-making algorithms (optimal power flow (OPF) and security-constrained unit commitment (SCUC)) to enable rigorous quantification of the operational risk. To conduct principled risk analysis, numerous Monte Carlo (MC) samples are drawn from the (foretasted) probability distributions of spatio-temporally correlated stochastic grid variables. The corresponding OPF and SCUC solutions, which are needed to quantify the risk, are generated using traditional OPF and SCUC solvers to generate data for training GNN model(s). The GNN model performance is evaluated in terms of the accuracy of predicting quantities of interests (QoIs) derived from the decision variables in OPF and SCUC. Specifically, we focus on thermal power generation and load shedding at system and individual zone level. We also perform reliability and risk quantification based on GNN predictions and compare with that obtained from OPF/SCUC solutions. Our results demonstrate that GNNs are capable of providing fast and accurate prediction of QoIs and thus can be good surrogate models for OPF and SCUC. The excellent accuracy of GNN-based reliability and risk assessment further suggests that GNN surrogate has the potential to be applied in real-time and hours-ahead risk quantification.
Authors: Cheng Luo, Qin Li, Zhao Yan, Mengliang Rao, Yunbo Cao
A customer service platform system with a core text semantic similarity (STS) task faces two urgent challenges: Firstly, one platform system needs to adapt to different domains of customers, i.e., different domains adaptation (DDA). Secondly, it is difficult for the model of the platform system to distinguish sentence pairs that are literally close but semantically different, i.e., hard negative samples. In this paper, we propose an incorporation external keywords matrices model (IEKM) to address these challenges. The model uses external tools or dictionaries to construct external matrices and fuses them to the self-attention layers of the Transformer structure through gating units, thus enabling flexible corrections to the model results. We evaluate the method on multiple datasets and the results show that our method has improved performance on all datasets. To demonstrate that our method can effectively solve all the above challenges, we conduct a flexible correction experiment, which results in an increase in the F1 value from 56.61 to 73.53. Our code will be publicly available.
Authors: Sadia Kamal, Brenner Little, Jade Gullic, Trevor Harms, Kristin Olofsson, Arunkumar Bagavathi
Developing machine learning models to characterize political polarization on online social media presents significant challenges. These challenges mainly stem from various factors such as the lack of annotated data, presence of noise in social media datasets, and the sheer volume of data. The common research practice typically examines the biased structure of online user communities for a given topic or qualitatively measuring the impacts of polarized topics on social media. However, there is limited work focusing on analyzing polarization at the ground-level, specifically in the social media posts themselves. Such existing analysis heavily relies on annotated data, which often requires laborious human labeling, offers labels only to specific problems, and lacks the ability to determine the near-future bias state of a social media conversations. Understanding the degree of political orientation conveyed in social media posts is crucial for quantifying the bias of online user communities and investigating the spread of polarized content. In this work, we first introduce two heuristic methods that leverage on news media bias and post content to label social media posts. Next, we compare the efficacy and quality of heuristically labeled dataset with a randomly sampled human-annotated dataset. Additionally, we demonstrate that current machine learning models can exhibit improved performance in predicting political orientation of social media posts, employing both traditional supervised learning and few-shot learning setups. We conduct experiments using the proposed heuristic methods and machine learning approaches to predict the political orientation of posts collected from two social media forums with diverse political ideologies: Gab and Twitter.
Authors: Ke Xu, Yuanjie Zhu, Weizhi Zhang, Philip S. Yu
Graph Convolution Networks (GCNs) are widely considered state-of-the-art for collaborative filtering. Although several GCN-based methods have been proposed and achieved state-of-the-art performance in various tasks, they can be computationally expensive and time-consuming to train if too many layers are created. However, since the linear GCN model can be interpreted as a differential equation, it is possible to transfer it to an ODE problem. This inspired us to address the computational limitations of GCN-based models by designing a simple and efficient NODE-based model that can skip some GCN layers to reach the final state, thus avoiding the need to create many layers. In this work, we propose a Graph Neural Ordinary Differential Equation-based method for Collaborative Filtering (GODE-CF). This method estimates the final embedding by utilizing the information captured by one or two GCN layers. To validate our approach, we conducted experiments on multiple datasets. The results demonstrate that our model outperforms competitive baselines, including GCN-based models and other state-of-the-art CF methods. Notably, our proposed GODE-CF model has several advantages over traditional GCN-based models. It is simple, efficient, and has a fast training time, making it a practical choice for real-world situations.
Authors: Yanan Jian, Fuxun Yu, Simranjit Singh, Dimitrios Stamoulis
Aerial object detection is a challenging task, in which one major obstacle lies in the limitations of large-scale data collection and the long-tail distribution of certain classes. Synthetic data offers a promising solution, especially with recent advances in diffusion-based methods like stable diffusion (SD). However, the direct application of diffusion methods to aerial domains poses unique challenges: stable diffusion's optimization for rich ground-level semantics doesn't align with the sparse nature of aerial objects, and the extraction of post-synthesis object coordinates remains problematic. To address these challenges, we introduce a synthetic data augmentation framework tailored for aerial images. It encompasses sparse-to-dense region of interest (ROI) extraction to bridge the semantic gap, fine-tuning the diffusion model with low-rank adaptation (LORA) to circumvent exhaustive retraining, and finally, a Copy-Paste method to compose synthesized objects with backgrounds, providing a nuanced approach to aerial object detection through synthetic data.
Authors: Yunpeng Huang, Jingwei Xu, Zixu Jiang, Junyu Lai, Zenan Li, Yuan Yao, Taolue Chen, Lijuan Yang, Zhou Xin, Xiaoxing Ma
With the bomb ignited by ChatGPT, Transformer-based Large Language Models (LLMs) have paved a revolutionary path toward Artificial General Intelligence (AGI) and have been applied in diverse areas as knowledge bases, human interfaces, and dynamic agents. However, a prevailing limitation exists: many current LLMs, constrained by resources, are primarily pre-trained on shorter texts, rendering them less effective for longer-context prompts, commonly encountered in real-world settings. In this paper, we present a comprehensive survey focusing on the advancement of model architecture in Transformer-based LLMs to optimize long-context capabilities across all stages from pre-training to inference. We firstly delineate and analyze the problems of handling long-context input and output with the current Transformer-based models. Then, we mainly offer a holistic taxonomy to navigate the landscape of Transformer upgrades on architecture to solve these problems. Afterward, we provide the investigation on wildly used evaluation necessities tailored for long-context LLMs, including datasets, metrics, and baseline models, as well as some amazing optimization toolkits like libraries, systems, and compilers to augment LLMs' efficiency and efficacy across different stages. Finally, we further discuss the predominant challenges and potential avenues for future research in this domain. Additionally, we have established a repository where we curate relevant literature with real-time updates at https://github.com/Strivin0311/long-llms-learning.
Authors: Ngai Lam Ho, Kwan Hui Lim
Tour itinerary recommendation involves planning a sequence of relevant Point-of-Interest (POIs), which combines challenges from the fields of both Operations Research (OR) and Recommendation Systems (RS). As an OR problem, there is the need to maximize a certain utility (e.g., popularity of POIs in the tour) while adhering to some constraints (e.g., maximum time for the tour). As a RS problem, it is heavily related to problem or filtering or ranking a subset of POIs that are relevant to a user and recommending it as part of an itinerary. In this paper, we explore the use of language models for the task of tour itinerary recommendation and planning. This task has the unique requirement of recommending personalized POIs relevant to users and planning these POIs as an itinerary that satisfies various constraints. We discuss some approaches in this area, such as using word embedding techniques like Word2Vec and GloVe for learning POI embeddings and transformer-based techniques like BERT for generating
itineraries.
Authors: Shyam Venkatasubramanian, Ahmed Aloui, Vahid Tarokh
Despite their popularity across a wide range of domains, regression neural networks are prone to overfitting complex datasets. In this work, we propose a loss function termed Random Linear Projections (RLP) loss, which is empirically shown to mitigate overfitting. With RLP loss, the distance between sets of hyperplanes connecting fixed-size subsets of the neural network's feature-prediction pairs and feature-label pairs is minimized. The intuition behind this loss derives from the notion that if two functions share the same hyperplanes connecting all subsets of feature-label pairs, then these functions must necessarily be equivalent. Our empirical studies, conducted across benchmark datasets and representative synthetic examples, demonstrate the improvements of the proposed RLP loss over mean squared error (MSE). Specifically, neural networks trained with the RLP loss achieve better performance while requiring fewer data samples and are more robust to additive noise. We provide theoretical analysis supporting our empirical findings.
Authors: Shu Zheng, Tiandi Ye, Xiang Li, Ming Gao
Federated learning (FL) on heterogeneous data (non-IID data) has recently received great attention. Most existing methods focus on studying the convergence guarantees for the global objective. While these methods can guarantee the decrease of the global objective in each communication round, they fail to ensure risk decrease for each client. In this paper, to address the problem,we propose FedCOME, which introduces a consensus mechanism to enforce decreased risk for each client after each training round. In particular, we allow a slight adjustment to a client's gradient on the server side, which generates an acute angle between the corrected gradient and the original ones of other clients. We theoretically show that the consensus mechanism can guarantee the convergence of the global objective. To generalize the consensus mechanism to the partial participation FL scenario, we devise a novel client sampling strategy to select the most representative clients for the global data distribution. Training on these selected clients with the consensus mechanism could empirically lead to risk decrease for clients that are not selected. Finally, we conduct extensive experiments on four benchmark datasets to show the superiority of FedCOME against other state-of-the-art methods in terms of effectiveness, efficiency and fairness. For reproducibility, we make our source code publicly available at: \url{https://github.com/fedcome/fedcome}.
Authors: Shivam Aggarwal, Alessandro Pappalardo, Hans Jakob Damsgaard, Giuseppe Franco, Thomas B. Preußer, Michaela Blott, Tulika Mitra
Post-Training Quantization (PTQ) is a powerful technique for model compression, reducing the precision of neural networks without additional training overhead. Recent works have investigated adopting 8-bit floating-point quantization (FP8) in the context of PTQ for model inference. However, the exploration of floating-point formats smaller than 8 bits and their comparison with integer quantization remains relatively limited. In this work, we present minifloats, which are reduced-precision floating-point formats capable of further reducing the memory footprint, latency, and energy cost of a model while approaching full-precision model accuracy. Our work presents a novel PTQ design-space exploration, comparing minifloat and integer quantization schemes across a range of 3 to 8 bits for both weights and activations. We examine the applicability of various PTQ techniques to minifloats, including weight equalization, bias correction, SmoothQuant, gradient-based learned rounding, and the GPTQ method. Our experiments validate the effectiveness of low-precision minifloats when compared to their integer counterparts across a spectrum of accuracy-precision trade-offs on a set of reference deep learning vision workloads. Finally, we evaluate our results against an FPGA-based hardware cost model, showing that integer quantization often remains the Pareto-optimal option, given its relatively smaller hardware resource footprint.
Authors: Yinuo Ren, Feng Li, Yanfei Kang
Forecast combination integrates information from various sources by consolidating multiple forecast results from the target time series. Instead of the need to select a single optimal forecasting model, this paper introduces a deep learning ensemble forecasting model based on the Dirichlet process. Initially, the learning rate is sampled with three basis distributions as hyperparameters to convert the infinite mixture into a finite one. All checkpoints are collected to establish a deep learning sub-model pool, and weight adjustment and diversity strategies are developed during the combination process. The main advantage of this method is its ability to generate the required base learners through a single training process, utilizing the decaying strategy to tackle the challenge posed by the stochastic nature of gradient descent in determining the optimal learning rate. To ensure the method's generalizability and competitiveness, this paper conducts an empirical analysis using the weekly dataset from the M4 competition and explores sensitivity to the number of models to be combined. The results demonstrate that the ensemble model proposed offers substantial improvements in prediction accuracy and stability compared to a single benchmark model.
Authors: Yuhan Li, Zhixun Li, Peisong Wang, Jia Li, Xiangguo Sun, Hong Cheng, Jeffrey Xu Yu
Graph plays a significant role in representing and analyzing complex relationships in real-world applications such as citation networks, social networks, and biological data. Recently, Large Language Models (LLMs), which have achieved tremendous success in various domains, have also been leveraged in graph-related tasks to surpass traditional Graph Neural Networks (GNNs) based methods and yield state-of-the-art performance. In this survey, we first present a comprehensive review and analysis of existing methods that integrate LLMs with graphs. First of all, we propose a new taxonomy, which organizes existing methods into three categories based on the role (i.e., enhancer, predictor, and alignment component) played by LLMs in graph-related tasks. Then we systematically survey the representative methods along the three categories of the taxonomy. Finally, we discuss the remaining limitations of existing studies and highlight promising avenues for future research. The relevant papers are summarized and will be consistently updated at: https://github.com/yhLeeee/Awesome-LLMs-in-Graph-tasks.
Authors: Micha Livne, Zulfat Miftahutdinov, Elena Tutubalina, Maksim Kuznetsov, Daniil Polykovskiy, Annika Brundyn, Aastha Jhunjhunwala, Anthony Costa, Alex Aliper, Alex Zhavoronkov
Large Language Models (LLMs) have substantially driven scientific progress in various domains, and many papers have demonstrated their ability to tackle complex problems with creative solutions. Our paper introduces a new foundation model, nach0, capable of solving various chemical and biological tasks: biomedical question answering, named entity recognition, molecular generation, molecular synthesis, attributes prediction, and others. nach0 is a multi-domain and multi-task encoder-decoder LLM pre-trained on unlabeled text from scientific literature, patents, and molecule strings to incorporate a range of chemical and linguistic knowledge. We employed instruction tuning, where specific task-related instructions are utilized to fine-tune nach0 for the final set of tasks. To train nach0 effectively, we leverage the NeMo framework, enabling efficient parallel optimization of both base and large model versions. Extensive experiments demonstrate that our model outperforms state-of-the-art baselines on single-domain and cross-domain tasks. Furthermore, it can generate high-quality outputs in molecular and textual formats, showcasing its effectiveness in multi-domain setups.
Authors: Daniel Petashvili, Matthew Rodda
Bouldering is a sport where athletes aim to climb up an obstacle using a set of defined holds called a route. Typically routes are assigned a grade to inform climbers of its difficulty and allow them to more easily track their progression. However, the variation in individual climbers technical and physical attributes and many nuances of an individual route make grading a difficult and often biased task. In this work, we apply classical and deep-learning modelling techniques to the 2016, 2017 and 2019 Moonboard datasets, achieving state of the art grade prediction performance with 0.87 MAE and 1.12 RMSE. We achieve this performance on a feature-set that does not require decomposing routes into individual moves, which is a method common in literature and introduces bias. We also demonstrate the generalization capability of this model between editions and introduce a novel vision-based method of grade prediction. While the generalization performance of these techniques is below human level performance currently, we propose these methods as a basis for future work. Such a tool could be implemented in pre-existing mobile applications and would allow climbers to better track their progress and assess new routes with reduced bias.
Authors: Liu Yang, Kangwook Lee, Robert Nowak, Dimitris Papailiopoulos
Transformers have demonstrated effectiveness in \emph{in-context solving} data-fitting problems from various (latent) models, as reported by Garg et al. However, the absence of an inherent iterative structure in the transformer architecture presents a challenge in emulating the iterative algorithms, which are commonly employed in traditional machine learning methods. To address this, we propose the utilization of \emph{looped} transformer architecture and its associated training methodology, with the aim of incorporating iterative characteristics into the transformer architectures. Experimental results suggest that the looped transformer achieves performance comparable to the standard transformer in solving various data-fitting problems, while utilizing less than 10\% of the parameter count.
Authors: Alessandro Castelnovo, Nicole Inverardi, Gabriele Nanino, Ilaria Giuseppina Penco, Daniele Regoli
In the recent years, the raise in the usage and efficiency of Artificial Intelligence and, more in general, of Automated Decision-Making systems has brought with it an increasing and welcome awareness of the risks associated with such systems. One of such risks is that of perpetuating or even amplifying bias and unjust disparities present in the data from which many of these systems learn to adjust and optimise their decisions. This awareness has on one side encouraged several scientific communities to come up with more and more appropriate ways and methods to assess, quantify, and possibly mitigate such biases and disparities. On the other hand, it has prompted more and more layers of society, including policy makers, to call for ``fair'' algorithms. We believe that while a lot of excellent and multidisciplinary research is currently being conducted, what is still fundamentally missing is the awareness that having ``fair'' algorithms is per s\'e a nearly meaningless requirement, that needs to be complemented with a lot of additional societal choices to become actionable. Namely, there is a hiatus between what the society is demanding from Automated Decision-Making systems, and what this demand actually means in real-world scenarios. In this work, we outline the key features of such a hiatus, and pinpoint a list of fundamental ambiguities and attention points that we as a society must address in order to give a concrete meaning to the increasing demand of fairness in Automated Decision-Making systems.
Authors: Eugene Berta (SIERRA), Francis Bach (SIERRA), Michael Jordan (SIERRA)
Calibration of machine learning classifiers is necessary to obtain reliable and interpretable predictions, bridging the gap between model confidence and actual probabilities. One prominent technique, isotonic regression (IR), aims at calibrating binary classifiers by minimizing the cross entropy on a calibration set via monotone transformations. IR acts as an adaptive binning procedure, which allows achieving a calibration error of zero, but leaves open the issue of the effect on performance. In this paper, we first prove that IR preserves the convex hull of the ROC curve -- an essential performance metric for binary classifiers. This ensures that a classifier is calibrated while controlling for overfitting of the calibration set. We then present a novel generalization of isotonic regression to accommodate classifiers with K classes. Our method constructs a multidimensional adaptive binning scheme on the probability simplex, again achieving a multi-class calibration error equal to zero. We regularize this algorithm by imposing a form of monotony that preserves the K-dimensional ROC surface of the classifier. We show empirically that this general monotony criterion is effective in striking a balance between reducing cross entropy loss and avoiding overfitting of the calibration set.
Authors: Nisanur Alici, Kayode Inadagbo, Murat Isik
This research delves into sophisticated neural network frameworks like Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory Networks (LSTMs), and Deep Belief Networks (DBNs) for improved analysis of ECG signals via Field Programmable Gate Arrays (FPGAs). The MIT-BIH Arrhythmia Database serves as the foundation for training and evaluating our models, with added Gaussian noise to heighten the algorithms' resilience. The developed architectures incorporate various layers for specific processing and categorization functions, employing strategies such as the EarlyStopping callback and Dropout layer to prevent overfitting. Additionally, this paper details the creation of a tailored Tensor Compute Unit (TCU) accelerator for the PYNQ Z1 platform. It provides a thorough methodology for implementing FPGA-based machine learning, encompassing the configuration of the Tensil toolchain in Docker, selection of architectures, PS-PL configuration, and the compilation and deployment of models. By evaluating performance indicators like latency and throughput, we showcase the efficacy of FPGAs in advanced biomedical computing. This study ultimately serves as a comprehensive guide to optimizing neural network operations on FPGAs across various fields.
Authors: Aria Ahmadi, David R. Walton, Tim Atherton, Cagatay Dikici
We introduce a novel motion estimation method, MaskFlow, that is capable of estimating accurate motion fields, even in very challenging cases with small objects, large displacements and drastic appearance changes. In addition to lower-level features, that are used in other Deep Neural Network (DNN)-based motion estimation methods, MaskFlow draws from object-level features and segmentations. These features and segmentations are used to approximate the objects' translation motion field. We propose a novel and effective way of incorporating the incomplete translation motion field into a subsequent motion estimation network for refinement and completion. We also produced a new challenging synthetic dataset with motion field ground truth, and also provide extra ground truth for the object-instance matchings and corresponding segmentation masks. We demonstrate that MaskFlow outperforms state of the art methods when evaluated on our new challenging dataset, whilst still producing comparable results on the popular FlyingThings3D benchmark dataset.
Authors: Yifan Wang, Yi Gong, Yuan Zeng
Recent advances in Neural radiance fields (NeRF) have enabled high-fidelity scene reconstruction for novel view synthesis. However, NeRF requires hundreds of network evaluations per pixel to approximate a volume rendering integral, making it slow to train. Caching NeRFs into explicit data structures can effectively enhance rendering speed but at the cost of higher memory usage. To address these issues, we present Hyb-NeRF, a novel neural radiance field with a multi-resolution hybrid encoding that achieves efficient neural modeling and fast rendering, which also allows for high-quality novel view synthesis. The key idea of Hyb-NeRF is to represent the scene using different encoding strategies from coarse-to-fine resolution levels. Hyb-NeRF exploits memory-efficiency learnable positional features at coarse resolutions and the fast optimization speed and local details of hash-based feature grids at fine resolutions. In addition, to further boost performance, we embed cone tracing-based features in our learnable positional encoding that eliminates encoding ambiguity and reduces aliasing artifacts. Extensive experiments on both synthetic and real-world datasets show that Hyb-NeRF achieves faster rendering speed with better rending quality and even a lower memory footprint in comparison to previous state-of-the-art methods.
Authors: Hugo Schnoering, Michalis Vazirgiannis
This research delves into the intricacies of Bitcoin, a decentralized peer-to-peer network, and its associated blockchain, which records all transactions since its inception. While this ensures integrity and transparency, the transparent nature of Bitcoin potentially compromises users' privacy rights. To address this concern, users have adopted CoinJoin, a method that amalgamates multiple transaction intents into a single, larger transaction to bolster transactional privacy. This process complicates individual transaction tracing and disrupts many established blockchain analysis heuristics. Despite its significance, limited research has been conducted on identifying CoinJoin transactions. Particularly noteworthy are varied CoinJoin implementations such as JoinMarket, Wasabi, and Whirlpool, each presenting distinct challenges due to their unique transaction structures. This study delves deeply into the open-source implementations of these protocols, aiming to develop refined heuristics for identifying their transactions on the blockchain. Our exhaustive analysis covers transactions up to block 760,000, offering a comprehensive insight into CoinJoin transactions and their implications for Bitcoin blockchain analysis.
Authors: Florian Felten, El-Ghazali Talbi, Grégoire Danoy
Multi-objective reinforcement learning (MORL) extends traditional RL by seeking policies making different compromises among conflicting objectives. The recent surge of interest in MORL has led to diverse studies and solving methods, often drawing from existing knowledge in multi-objective optimization based on decomposition (MOO/D). Yet, a clear categorization based on both RL and MOO/D is lacking in the existing literature. Consequently, MORL researchers face difficulties when trying to classify contributions within a broader context due to the absence of a standardized taxonomy. To tackle such an issue, this paper introduces Multi-Objective Reinforcement Learning based on Decomposition (MORL/D), a novel methodology bridging RL and MOO literature. A comprehensive taxonomy for MORL/D is presented, providing a structured foundation for categorizing existing and potential MORL works. The introduced taxonomy is then used to scrutinize MORL research, enhancing clarity and conciseness through well-defined categorization. Moreover, a flexible framework derived from the taxonomy is introduced. This framework accommodates diverse instantiations using tools from both RL and MOO/D. Implementation across various configurations demonstrates its versatility, assessed against benchmark problems. Results indicate MORL/D instantiations achieve comparable performance with significantly greater versatility than current state-of-the-art approaches. By presenting the taxonomy and framework, this paper offers a comprehensive perspective and a unified vocabulary for MORL. This not only facilitates the identification of algorithmic contributions but also lays the groundwork for novel research avenues in MORL, contributing to the continued advancement of this field.
Authors: Marina Knittel, Max Springer, John Dickerson, MohammadTaghi Hajiaghayi
Research in fair machine learning, and particularly clustering, has been crucial in recent years given the many ethical controversies that modern intelligent systems have posed. Ahmadian et al. [2020] established the study of fairness in \textit{hierarchical} clustering, a stronger, more structured variant of its well-known flat counterpart, though their proposed algorithm that optimizes for Dasgupta's [2016] famous cost function was highly theoretical. Knittel et al. [2023] then proposed the first practical fair approximation for cost, however they were unable to break the polynomial-approximate barrier they posed as a hurdle of interest. We break this barrier, proposing the first truly polylogarithmic-approximate low-cost fair hierarchical clustering, thus greatly bridging the gap between the best fair and vanilla hierarchical clustering approximations.
Authors: Jiankai Tang, Kegang Wang, Hongming Hu, Xiyuxing Zhang, Peiyu Wang, Xin Liu, Yuntao Wang
This study concentrates on evaluating the efficacy of Large Language Models (LLMs) in healthcare, with a specific focus on their application in personal anomalous health monitoring. Our research primarily investigates the capabilities of LLMs in interpreting and analyzing physiological data obtained from FDA-approved devices. We conducted an extensive analysis using anomalous physiological data gathered in a simulated low-air-pressure plateau environment. This allowed us to assess the precision and reliability of LLMs in understanding and evaluating users' health status with notable specificity. Our findings reveal that LLMs exhibit exceptional performance in determining medical indicators, including a Mean Absolute Error (MAE) of less than 1 beat per minute for heart rate and less than 1% for oxygen saturation (SpO2). Furthermore, the Mean Absolute Percentage Error (MAPE) for these evaluations remained below 1%, with the overall accuracy of health assessments surpassing 85%. In image analysis tasks, such as interpreting photoplethysmography (PPG) data, our specially adapted GPT models demonstrated remarkable proficiency, achieving less than 1 bpm error in cycle count and 7.28 MAE for heart rate estimation. This study highlights LLMs' dual role as health data analysis tools and pivotal elements in advanced AI health assistants, offering personalized health insights and recommendations within the future health assistant framework.
Authors: Zhang Zhang, Ruyi Tao, Jiang Zhang
The rapid increase in the parameters of deep learning models has led to significant costs, challenging computational efficiency and model interpretability. In this paper, we introduce a novel and straightforward neural network pruning framework that incorporates the Gumbel-Softmax technique. This framework enables the simultaneous optimization of a network's weights and topology in an end-to-end process using stochastic gradient descent. Empirical results demonstrate its exceptional compression capability, maintaining high accuracy on the MNIST dataset with only 0.15\% of the original network parameters. Moreover, our framework enhances neural network interpretability, not only by allowing easy extraction of feature importance directly from the pruned network but also by enabling visualization of feature symmetry and the pathways of information propagation from features to outcomes. Although the pruning strategy is learned through deep learning, it is surprisingly intuitive and understandable, focusing on selecting key representative features and exploiting data patterns to achieve extreme sparse pruning. We believe our method opens a promising new avenue for deep learning pruning and the creation of interpretable machine learning systems.
Authors: Simon Arridge, Andreas Hauptmann, Yury Korolev
Solving inverse problems requires knowledge of the forward operator, but accurate models can be computationally expensive and hence cheaper variants are desired that do not compromise reconstruction quality. This chapter reviews reconstruction methods in inverse problems with learned forward operators that follow two different paradigms. The first one is completely agnostic to the forward operator and learns its restriction to the subspace spanned by the training data. The framework of regularisation by projection is then used to find a reconstruction. The second one uses a simplified model of the physics of the measurement process and only relies on the training data to learn a model correction. We present the theory of these two approaches and compare them numerically. A common theme emerges: both methods require, or at least benefit from, training data not only for the forward operator, but also for its adjoint.
Authors: Yifei Xiong, Xiliang Yang, Sanguo Zhang, Zhijian He
Sequential neural posterior estimation (SNPE) techniques have been recently proposed for dealing with simulation-based models with intractable likelihoods. Unlike approximate Bayesian computation, SNPE techniques learn the posterior from sequential simulation using neural network-based conditional density estimators. This paper reclaims SNPE-B proposed by Lueckmann et al. (2017), which suffers from inefficiency and slow inference due to inefficient utilization of simulated data and high variance of parameter updates. To address these issues, we firstly introduce a concentrated loss function based on an adaptive calibration kernel that reweights the simulated data appropriately to improve the data efficiency. Moreover, we provide a theoretical analysis of the variance of associated Monte Carlo estimators. Based on this analysis, we then propose several variance reduction techniques to further accelerate the process of learning. Numerical experiments demonstrate that our method outperforms the original method together with other existing competitors on certain tasks.
Authors: David Oniani, Yanshan Wang
Large Language Models (LLMs) have proven effective at In-Context Learning (ICL), an ability that allows them to create predictors from labeled examples. Few studies have explored the interplay between ICL and specific properties of functions it attempts to approximate. In our study, we use a formal framework to explore ICL and propose a new task of approximating functions with varying number of minima. We implement a method that allows for producing functions with given inputs as minima. We find that increasing the number of minima degrades ICL performance. At the same time, our evaluation shows that ICL outperforms 2-layer Neural Network (2NN) model. Furthermore, ICL learns faster than 2NN in all settings. We validate the findings through a set of few-shot experiments across various hyperparameter configurations.
Authors: Daesoo Lee, Sara Malacarne, Erlend Aune
We present a novel time series anomaly detection method that achieves excellent detection accuracy while offering a superior level of explainability. Our proposed method, TimeVQVAE-AD, leverages masked generative modeling adapted from the cutting-edge time series generation method known as TimeVQVAE. The prior model is trained on the discrete latent space of a time-frequency domain. Notably, the dimensional semantics of the time-frequency domain are preserved in the latent space, enabling us to compute anomaly scores across different frequency bands, which provides a better insight into the detected anomalies. Additionally, the generative nature of the prior model allows for sampling likely normal states for detected anomalies, enhancing the explainability of the detected anomalies through counterfactuals. Our experimental evaluation on the UCR Time Series Anomaly archive demonstrates that TimeVQVAE-AD significantly surpasses the existing methods in terms of detection accuracy and explainability.
Authors: Francisco J. Martinez-Murcia, Juan M. Górriz, Javier Ramírez, Andrés Ortiz
Spatial and intensity normalization are nowadays a prerequisite for neuroimaging analysis. Influenced by voxel-wise and other univariate comparisons, where these corrections are key, they are commonly applied to any type of analysis and imaging modalities. Nuclear imaging modalities such as PET-FDG or FP-CIT SPECT, a common modality used in Parkinson's Disease diagnosis, are especially dependent on intensity normalization. However, these steps are computationally expensive and furthermore, they may introduce deformations in the images, altering the information contained in them. Convolutional Neural Networks (CNNs), for their part, introduce position invariance to pattern recognition, and have been proven to classify objects regardless of their orientation, size, angle, etc. Therefore, a question arises: how well can CNNs account for spatial and intensity differences when analysing nuclear brain imaging? Are spatial and intensity normalization still needed? To answer this question, we have trained four different CNN models based on well-established architectures, using or not different spatial and intensity normalization preprocessing. The results show that a sufficiently complex model such as our three-dimensional version of the ALEXNET can effectively account for spatial differences, achieving a diagnosis accuracy of 94.1% with an area under the ROC curve of 0.984. The visualization of the differences via saliency maps shows that these models are correctly finding patterns that match those found in the literature, without the need of applying any complex spatial normalization procedure. However, the intensity normalization -- and its type -- is revealed as very influential in the results and accuracy of the trained model, and therefore must be well accounted.
Authors: Shikha Baghel, Shreyas Ramoji, Somil Jain, Pratik Roy Chowdhuri, Prachi Singh, Deepu Vijayasenan, Sriram Ganapathy
In multi-lingual societies, where multiple languages are spoken in a small geographic vicinity, informal conversations often involve mix of languages. Existing speech technologies may be inefficient in extracting information from such conversations, where the speech data is rich in diversity with multiple languages and speakers. The DISPLACE (DIarization of SPeaker and LAnguage in Conversational Environments) challenge constitutes an open-call for evaluating and bench-marking the speaker and language diarization technologies on this challenging condition. The challenge entailed two tracks: Track-1 focused on speaker diarization (SD) in multilingual situations while, Track-2 addressed the language diarization (LD) in a multi-speaker scenario. Both the tracks were evaluated using the same underlying audio data. To facilitate this evaluation, a real-world dataset featuring multilingual, multi-speaker conversational far-field speech was recorded and distributed. Furthermore, a baseline system was made available for both SD and LD task which mimicked the state-of-art in these tasks. The challenge garnered a total of $42$ world-wide registrations and received a total of $19$ combined submissions for Track-1 and Track-2. This paper describes the challenge, details of the datasets, tasks, and the baseline system. Additionally, the paper provides a concise overview of the submitted systems in both tracks, with an emphasis given to the top performing systems. The paper also presents insights and future perspectives for SD and LD tasks, focusing on the key challenges that the systems need to overcome before wide-spread commercial deployment on such conversations.
Authors: Maria Bånkestad, Jens Sjölund, Jalil Taghia, Thomas B. Schöon
We present elliptical processes, a family of non-parametric probabilistic models that subsume Gaussian processes and Student's t processes. This generalization includes a range of new heavy-tailed behaviors while retaining computational tractability. Elliptical processes are based on a representation of elliptical distributions as a continuous mixture of Gaussian distributions. We parameterize this mixture distribution as a spline normalizing flow, which we train using variational inference. The proposed form of the variational posterior enables a sparse variational elliptical process applicable to large-scale problems. We highlight advantages compared to Gaussian processes through regression and classification experiments. Elliptical processes can supersede Gaussian processes in several settings, including cases where the likelihood is non-Gaussian or when accurate tail modeling is essential.
Authors: Lennert De Smet, Emanuele Sansone, Pedro Zuidberg Dos Martires
Categorical random variables can faithfully represent the discrete and uncertain aspects of data as part of a discrete latent variable model. Learning in such models necessitates taking gradients with respect to the parameters of the categorical probability distributions, which is often intractable due to their combinatorial nature. A popular technique to estimate these otherwise intractable gradients is the Log-Derivative trick. This trick forms the basis of the well-known REINFORCE gradient estimator and its many extensions. While the Log-Derivative trick allows us to differentiate through samples drawn from categorical distributions, it does not take into account the discrete nature of the distribution itself. Our first contribution addresses this shortcoming by introducing the CatLog-Derivative trick - a variation of the Log-Derivative trick tailored towards categorical distributions. Secondly, we use the CatLog-Derivative trick to introduce IndeCateR, a novel and unbiased gradient estimator for the important case of products of independent categorical distributions with provably lower variance than REINFORCE. Thirdly, we empirically show that IndeCateR can be efficiently implemented and that its gradient estimates have significantly lower bias and variance for the same number of samples compared to the state of the art.
Authors: Frederikke Isa Marin, Felix Teufel, Marc Horrender, Dennis Madsen, Dennis Pultz, Ole Winther, Wouter Boomsma
The genome sequence contains the blueprint for governing cellular processes. While the availability of genomes has vastly increased over the last decades, experimental annotation of the various functional, non-coding and regulatory elements encoded in the DNA sequence remains both expensive and challenging. This has sparked interest in unsupervised language modeling of genomic DNA, a paradigm that has seen great success for protein sequence data. Although various DNA language models have been proposed, evaluation tasks often differ between individual works, and might not fully recapitulate the fundamental challenges of genome annotation, including the length, scale and sparsity of the data. In this study, we introduce BEND, a Benchmark for DNA language models, featuring a collection of realistic and biologically meaningful downstream tasks defined on the human genome. We find that embeddings from current DNA LMs can approach performance of expert methods on some tasks, but only capture limited information about long-range features. BEND is available at https://github.com/frederikkemarin/BEND.
Authors: Robert Gorwa, Michael Veale
The AI development community is increasingly making use of hosting intermediaries such as Hugging Face provide easy access to user-uploaded models and training data. These model marketplaces lower technical deployment barriers for hundreds of thousands of users, yet can be used in numerous potentially harmful and illegal ways. In this article, we explain ways in which AI systems, which can both `contain' content and be open-ended tools, present one of the trickiest platform governance challenges seen to date. We provide case studies of several incidents across three illustrative platforms -- Hugging Face, GitHub and Civitai -- to examine how model marketplaces moderate models. Building on this analysis, we outline important (and yet nevertheless limited) practices that industry has been developing to respond to moderation demands: licensing, access and use restrictions, automated content moderation, and open policy development. While the policy challenge at hand is a considerable one, we conclude with some ideas as to how platforms could better mobilize resources to act as a careful, fair, and proportionate regulatory access point.
Authors: Dion Häfner, Johannes Gemmrich, Markus Jochum
Big data and large-scale machine learning have had a profound impact on science and engineering, particularly in fields focused on forecasting and prediction. Yet, it is still not clear how we can use the superior pattern matching abilities of machine learning models for scientific discovery. This is because the goals of machine learning and science are generally not aligned. In addition to being accurate, scientific theories must also be causally consistent with the underlying physical process and allow for human analysis, reasoning, and manipulation to advance the field. In this paper, we present a case study on discovering a new symbolic model for oceanic rogue waves from data using causal analysis, deep learning, parsimony-guided model selection, and symbolic regression. We train an artificial neural network on causal features from an extensive dataset of observations from wave buoys, while selecting for predictive performance and causal invariance. We apply symbolic regression to distill this black-box model into a mathematical equation that retains the neural network's predictive capabilities, while allowing for interpretation in the context of existing wave theory. The resulting model reproduces known behavior, generates well-calibrated probabilities, and achieves better predictive scores on unseen data than current theory. This showcases how machine learning can facilitate inductive scientific discovery, and paves the way for more accurate rogue wave forecasting.
Authors: Gauransh Sawhney, Daksh Dave, Adeel Ahmed, Jiechao Gao, Khalid Saleem
Unsupervised Domain Adaptation (UDA) methods facilitate knowledge transfer from a labeled source domain to an unlabeled target domain, navigating the obstacle of domain shift. While Convolutional Neural Networks (CNNs) are a staple in UDA, the rise of Vision Transformers (ViTs) provides new avenues for domain generalization. This paper presents an innovative method to bolster ViT performance in source-free target adaptation, beginning with an evaluation of how key, query, and value elements affect ViT outcomes. Experiments indicate that altering the key component has negligible effects on Transformer performance. Leveraging this discovery, we introduce Domain Representation Images (DRIs), feeding embeddings through the key element. DRIs act as domain-specific markers, effortlessly merging with the training regimen. To assess our method, we perform target adaptation tests on the Cross Instance DRI source-only (SO) control. We measure the efficacy of target adaptation with and without DRIs, against existing benchmarks like SHOT-B* and adaptations via CDTrans. Findings demonstrate that excluding DRIs offers limited gains over SHOT-B*, while their inclusion in the key segment boosts average precision promoting superior domain generalization. This research underscores the vital role of DRIs in enhancing ViT efficiency in UDA scenarios, setting a precedent for further domain adaptation explorations.
Authors: Pradnya Rajendra Jadhav, Raviprasad Aduri
Schizophrenia is a complicated mental illness characterized by a broad spectrum of symptoms affecting cognition, behavior, and emotion. The task of identifying reliable biomarkers to classify Schizophrenia accurately continues to be a challenge in the field of psychiatry. We investigate the temporal patterns within the motor activity data as a potential key to enhancing the categorization of individuals with Schizophrenia, using the dataset having motor activity recordings of 22 Schizophrenia patients and 32 control subjects. The dataset contains per-minute motor activity measurements collected for an average of 12.7 days in a row for each participant. We dissect each day into segments (Twelve, Eight, six, four, three, and two parts) and evaluate their impact on classification. We employ sixteen statistical features within these temporal segments and train them on Seven machine learning models to get deeper insights. LightGBM model outperforms the other six models. Our results indicate that the temporal segmentation significantly improves the classification, with AUC-ROC = 0.93, F1 score = 0.84( LightGBM- without any segmentation) and AUC-ROC = 0.98, F1 score = 0.93( LightGBM- with segmentation). Distinguishing between diurnal and nocturnal segments amplifies the differences between Schizophrenia patients and controls. However, further subdivisions into smaller time segments do not affect the AUC- ROC significantly. Morning, afternoon, evening, and night partitioning gives similar classification performance to day-night partitioning. These findings are valuable as they indicate that extensive temporal classification beyond distinguishing between day and night does not yield substantial results, offering an efficient approach for further classification, early diagnosis, and monitoring of Schizophrenia.
Authors: Petru Manescu, Joseph Geradts, Delmiro Fernandez-Reyes
Hypoxia occurs when tumour cells outgrow their blood supply, leading to regions of low oxygen levels within the tumour. Calculating hypoxia levels can be an important step in understanding the biology of tumours, their clinical progression and response to treatment. This study demonstrates a novel application of deep learning to evaluate hypoxia in the context of breast cancer histomorphology. More precisely, we show that Weakly Supervised Deep Learning (WSDL) models can accurately detect hypoxia associated features in routine Hematoxylin and Eosin (H&E) whole slide images (WSI). We trained and evaluated a deep Multiple Instance Learning model on tiles from WSI H&E tissue from breast cancer primary sites (n=240) obtaining on average an AUC of 0.87 on a left-out test set. We also showed significant differences between features of hypoxic and normoxic tissue regions as distinguished by the WSDL models. Such DL hypoxia H&E WSI detection models could potentially be extended to other tumour types and easily integrated into the pathology workflow without requiring additional costly assays.
Authors: Mauro Comi, Yijiong Lin, Alex Church, Alessio Tonioni, Laurence Aitchison, Nathan F. Lepora
Humans rely on their visual and tactile senses to develop a comprehensive 3D understanding of their physical environment. Recently, there has been a growing interest in exploring and manipulating objects using data-driven approaches that utilise high-resolution vision-based tactile sensors. However, 3D shape reconstruction using tactile sensing has lagged behind visual shape reconstruction because of limitations in existing techniques, including the inability to generalise over unseen shapes, the absence of real-world testing, and limited expressive capacity imposed by discrete representations. To address these challenges, we propose TouchSDF, a Deep Learning approach for tactile 3D shape reconstruction that leverages the rich information provided by a vision-based tactile sensor and the expressivity of the implicit neural representation DeepSDF. Our technique consists of two components: (1) a Convolutional Neural Network that maps tactile images into local meshes representing the surface at the touch location, and (2) an implicit neural function that predicts a signed distance function to extract the desired 3D shape. This combination allows TouchSDF to reconstruct smooth and continuous 3D shapes from tactile inputs in simulation and real-world settings, opening up research avenues for robust 3D-aware representations and improved multimodal perception in robotics. Code and supplementary material are available at: https://touchsdf.github.io/
Authors: Nikola Zlatanov
In this paper, I present a completely new type of upper and lower bounds on the right-tail probabilities of continuous random variables with unbounded support and with semi-bounded support from the left. The presented upper and lower right-tail bounds depend only on the probability density function (PDF), its first derivative, and two parameters that are used for tightening the bounds. These tail bounds hold under certain conditions that depend on the PDF, its first and second derivatives, and the two parameters. The new tail bounds are shown to be tight for a wide range of continuous random variables via numerical examples.
Authors: Keshav P. Keval, Vivek S. Borkar
In this paper, we propose a reinforcement learning algorithm to solve a multi-agent Markov decision process (MMDP). The goal, inspired by Blackwell's Approachability Theorem, is to lower the time average cost of each agent to below a pre-specified agent-specific bound. For the MMDP, we assume the state dynamics to be controlled by the joint actions of agents, but the per-stage costs to only depend on the individual agent's actions. We combine the Q-learning algorithm for a weighted combination of the costs of each agent, obtained by a gossip algorithm with the Metropolis-Hastings or Multiplicative Weights formalisms to modulate the averaging matrix of the gossip. We use multiple timescales in our algorithm and prove that under mild conditions, it approximately achieves the desired bounds for each of the agents. We also demonstrate the empirical performance of this algorithm in the more general setting of MMDPs having jointly controlled per-stage costs.
Authors: William T. Redman, Dean Huang, Maria Fonoberova, Igor Mezić
Koopman operator theory, a data-driven dynamical systems framework, has found significant success in learning models from complex, real-world data sets, enabling state-of-the-art prediction and control. The greater interpretability and lower computational costs of these models, compared to traditional machine learning methodologies, make Koopman learning an especially appealing approach. Despite this, little work has been performed on endowing Koopman learning with the ability to learn from its own mistakes. To address this, we equip Koopman methods - developed for predicting non-stationary time-series - with an episodic memory mechanism, enabling global recall of (or attention to) periods in time where similar dynamics previously occurred. We find that a basic implementation of Koopman learning with episodic memory leads to significant improvements in prediction on synthetic and real-world data. Our framework has considerable potential for expansion, allowing for future advances, and opens exciting new directions for Koopman learning.
Authors: Boumediene Hamzi, Marcus Hutter, Houman Owhadi
Machine Learning (ML) and Algorithmic Information Theory (AIT) look at Complexity from different points of view. We explore the interface between AIT and Kernel Methods (that are prevalent in ML) by adopting an AIT perspective on the problem of learning kernels from data, in kernel ridge regression, through the method of Sparse Kernel Flows. In particular, by looking at the differences and commonalities between Minimal Description Length (MDL) and Regularization in Machine Learning (RML), we prove that the method of Sparse Kernel Flows is the natural approach to adopt to learn kernels from data. This paper shows that it is not necessary to use the statistical route to derive Sparse Kernel Flows and that one can directly work with code-lengths and complexities that are concepts that show up in AIT.
Authors: Juhyeon Kim, Hyungeun Lee, Seungwon Yu, Ung Hwang, Wooyul Jung, Miseon Park, Kijung Yoon
Multivariate time series is prevalent in many scientific and industrial domains. Modeling multivariate signals is challenging due to their long-range temporal dependencies and intricate interactions--both direct and indirect. To confront these complexities, we introduce a method of representing multivariate signals as nodes in a graph with edges indicating interdependency between them. Specifically, we leverage graph neural networks (GNN) and attention mechanisms to efficiently learn the underlying relationships within the time series data. Moreover, we suggest employing hierarchical signal decompositions running over the graphs to capture multiple spatial dependencies. The effectiveness of our proposed model is evaluated across various real-world benchmark datasets designed for long-term forecasting tasks. The results consistently showcase the superiority of our model, achieving an average 23\% reduction in mean squared error (MSE) compared to existing models.
Authors: Chuang Liu, Wenhang Yu, Kuang Gao, Xueqi Ma, Yibing Zhan, Jia Wu, Bo Du, Wenbin Hu
Graph pooling has been increasingly recognized as crucial for Graph Neural Networks (GNNs) to facilitate hierarchical graph representation learning. Existing graph pooling methods commonly consist of two stages: selecting top-ranked nodes and discarding the remaining to construct coarsened graph representations. However, this paper highlights two key issues with these methods: 1) The process of selecting nodes to discard frequently employs additional Graph Convolutional Networks or Multilayer Perceptrons, lacking a thorough evaluation of each node's impact on the final graph representation and subsequent prediction tasks. 2) Current graph pooling methods tend to directly discard the noise segment (dropped) of the graph without accounting for the latent information contained within these elements. To address the first issue, we introduce a novel Graph Explicit Pooling (GrePool) method, which selects nodes by explicitly leveraging the relationships between the nodes and final representation vectors crucial for classification. The second issue is addressed using an extended version of GrePool (i.e., GrePool+), which applies a uniform loss on the discarded nodes. This addition is designed to augment the training process and improve classification accuracy. Furthermore, we conduct comprehensive experiments across 12 widely used datasets to validate our proposed method's effectiveness, including the Open Graph Benchmark datasets. Our experimental results uniformly demonstrate that GrePool outperforms 14 baseline methods for most datasets. Likewise, implementing GrePool+ enhances GrePool's performance without incurring additional computational costs.
Authors: Prashant Khanduri, Chengyin Li, Rafi Ibn Sultan, Yao Qiang, Joerg Kliewer, Dongxiao Zhu
Recently, compositional optimization (CO) has gained popularity because of its applications in distributionally robust optimization (DRO) and many other machine learning problems. Large-scale and distributed availability of data demands the development of efficient federated learning (FL) algorithms for solving CO problems. Developing FL algorithms for CO is particularly challenging because of the compositional nature of the objective. Moreover, current state-of-the-art methods to solve such problems rely on large batch gradients (depending on the solution accuracy) not feasible for most practical settings. To address these challenges, in this work, we propose efficient FedAvg-type algorithms for solving non-convex CO in the FL setting. We first establish that vanilla FedAvg is not suitable to solve distributed CO problems because of the data heterogeneity in the compositional objective at each client which leads to the amplification of bias in the local compositional gradient estimates. To this end, we propose a novel FL framework FedDRO that utilizes the DRO problem structure to design a communication strategy that allows FedAvg to control the bias in the estimation of the compositional gradient. A key novelty of our work is to develop solution accuracy-independent algorithms that do not require large batch gradients (and function evaluations) for solving federated CO problems. We establish $\mathcal{O}(\epsilon^{-2})$ sample and $\mathcal{O}(\epsilon^{-3/2})$ communication complexity in the FL setting while achieving linear speedup with the number of clients. We corroborate our theoretical findings with empirical studies on large-scale DRO problems.
Authors: Maria Bånkestad, Keven M. Dorst, Göran Widmalm, Jerk Rönnols
Carbohydrates, vital components of biological systems, are well-known for their structural diversity. Nuclear Magnetic Resonance (NMR) spectroscopy plays a crucial role in understanding their intricate molecular arrangements and is essential in assessing and verifying the molecular structure of organic molecules. An important part of this process is to predict the NMR chemical shift from the molecular structure. This work introduces a novel approach that leverages E(3) equivariant graph neural networks to predict carbohydrate NMR spectra. Notably, our model achieves a substantial reduction in mean absolute error, up to threefold, compared to traditional models that rely solely on two-dimensional molecular structure. Even with limited data, the model excels, highlighting its robustness and generalization capabilities. The implications are far-reaching and go beyond an advanced understanding of carbohydrate structures and spectral interpretation. For example, it could accelerate research in pharmaceutical applications, biochemistry, and structural biology, offering a faster and more reliable analysis of molecular structures. Furthermore, our approach is a key step towards a new data-driven era in spectroscopy, potentially influencing spectroscopic techniques beyond NMR.
Authors: Sung-Yu Chen, Chi-Min Chang, Kuan-Jung Chiang, Chun-Shu Wei
Steady-state visual-evoked potential (SSVEP)-based brain-computer interfaces (BCIs) offer a non-invasive means of communication through high-speed speller systems. However, their efficiency heavily relies on individual training data obtained during time-consuming calibration sessions. To address the challenge of data insufficiency in SSVEP-based BCIs, we present SSVEP-DAN, the first dedicated neural network model designed for aligning SSVEP data across different domains, which can encompass various sessions, subjects, or devices. Our experimental results across multiple cross-domain scenarios demonstrate SSVEP-DAN's capability to transform existing source SSVEP data into supplementary calibration data, significantly enhancing SSVEP decoding accuracy in scenarios with limited calibration data. We envision SSVEP-DAN as a catalyst for practical SSVEP-based BCI applications with minimal calibration. The source codes in this work are available at: https://github.com/CECNL/SSVEP-DAN.
Authors: Jesus de la Fuente, Guillermo Serrano, Uxía Veleiro, Mikel Casals, Laura Vera, Marija Pizurica, Antonio Pineda-Lucena, Idoia Ochoa, Silve Vicent, Olivier Gevaert, Mikel Hernaez
Drug-target interaction (DTI) prediction is a challenging, albeit essential task in drug repurposing. Learning on graph models have drawn special attention as they can significantly reduce drug repurposing costs and time commitment. However, many current approaches require high-demanding additional information besides DTIs that complicates their evaluation process and usability. Additionally, structural differences in the learning architecture of current models hinder their fair benchmarking. In this work, we first perform an in-depth evaluation of current DTI datasets and prediction models through a robust benchmarking process, and show that DTI prediction methods based on transductive models lack generalization and lead to inflated performance when evaluated as previously done in the literature, hence not being suited for drug repurposing approaches. We then propose a novel biologically-driven strategy for negative edge subsampling and show through in vitro validation that newly discovered interactions are indeed true. We envision this work as the underpinning for future fair benchmarking and robust model design. All generated resources and tools are publicly available as a python package.
Authors: Dominique Nshimyimana, Vitor Fortes Rey, Paul Lukowic
Machine learning algorithms are improving rapidly, but annotating training data remains a bottleneck for many applications. In this paper, we show how real data can be used for self-supervised learning without any transformations by taking advantage of the symmetry present in the activities. Our approach involves contrastive matching of two different sensors (left and right wrist or leg-worn IMUs) to make representations of co-occurring sensor data more similar and those of non-co-occurring sensor data more different. We test our approach on the Opportunity and MM-Fit datasets. In MM-Fit we show significant improvement over the baseline supervised and self-supervised method SimCLR, while for Opportunity there is significant improvement over the supervised baseline and slight improvement when compared to SimCLR. Moreover, our method improves supervised baselines even when using only a small amount of the data for training. Future work should explore under which conditions our method is beneficial for human activity recognition systems and other related applications.
Authors: Zhe Chen
It has been over six years since the Transformer architecture was put forward. Surprisingly, the vanilla Transformer architecture is still widely used today. One reason is that the lack of deep understanding and comprehensive interpretation of the Transformer architecture makes it more challenging to improve the Transformer architecture. In this paper, we first interpret the Transformer architecture comprehensively in plain words based on our understanding and experiences. The interpretations are further proved and verified. These interpretations also cover the Extractor, a family of drop-in replacements for the multi-head self-attention in the Transformer architecture. Then, we propose an improvement on a type of the Extractor that outperforms the self-attention, without introducing additional trainable parameters. Experimental results demonstrate that the improved Extractor performs even better, showing a way to improve the Transformer architecture.
Authors: Georgios Albanis, Nikolaos Zioulis, Kostas Kolomvatsos
Capturing smooth motions from videos using markerless techniques typically involves complex processes such as temporal constraints, multiple stages with data-driven regression and optimization, and bundle solving over temporal windows. These processes can be inefficient and require tuning multiple objectives across stages. In contrast, BundleMoCap introduces a novel and efficient approach to this problem. It solves the motion capture task in a single stage, eliminating the need for temporal smoothness objectives while still delivering smooth motions. BundleMoCap outperforms the state-of-the-art without increasing complexity. The key concept behind BundleMoCap is manifold interpolation between latent keyframes. By relying on a local manifold smoothness assumption, we can efficiently solve a bundle of frames using a single code. Additionally, the method can be implemented as a sliding window optimization and requires only the first frame to be properly initialized, reducing the overall computational burden. BundleMoCap's strength lies in its ability to achieve high-quality motion capture results with simplicity and efficiency. More details can be found at https://moverseai.github.io/bundle/.
Authors: Xuan Zhao, Simone Fabbrizzi, Paula Reyero Lobo, Siamak Ghodsi, Klaus Broelemann, Steffen Staab, Gjergji Kasneci
The unequal representation of different groups in a sample population can lead to discrimination of minority groups when machine learning models make automated decisions. To address these issues, fairness-aware machine learning jointly optimizes two (or more) metrics aiming at predictive effectiveness and low unfairness. However, the inherent under-representation of minorities in the data makes the disparate treatment of subpopulations less noticeable and difficult to deal with during learning. In this paper, we propose a novel adversarial reweighting method to address such \emph{representation bias}. To balance the data distribution between the majority and the minority groups, our approach deemphasizes samples from the majority group. To minimize empirical risk, our method prefers samples from the majority group that are close to the minority group as evaluated by the Wasserstein distance. Our theoretical analysis shows the effectiveness of our adversarial reweighting approach. Experiments demonstrate that our approach mitigates bias without sacrificing classification accuracy, outperforming related state-of-the-art methods on image and tabular benchmark datasets.
Authors: Marco Anisetti, Claudio A. Ardagna, Nicola Bena, Ernesto Damiani, Paolo G. Panero
Modern applications are increasingly driven by Machine Learning (ML) models whose non-deterministic behavior is affecting the entire application life cycle from design to operation. The pervasive adoption of ML is urgently calling for approaches that guarantee a stable non-functional behavior of ML-based applications over time and across model changes. To this aim, non-functional properties of ML models, such as privacy, confidentiality, fairness, and explainability, must be monitored, verified, and maintained. This need is even more pressing when modern applications operate in the edge-cloud continuum, increasing their complexity and dynamicity. Existing approaches mostly focus on i) implementing classifier selection solutions according to the functional behavior of ML models, ii) finding new algorithmic solutions to this need, such as continuous re-training. In this paper, we propose a multi-model approach built on dynamic classifier selection, where multiple ML models showing similar non-functional properties are made available to the application and one model is selected over time according to (dynamic and unpredictable) contextual changes. Our solution goes beyond the state of the art by providing an architectural and methodological approach that continuously guarantees a stable non-functional behavior of ML-based applications, is applicable to different ML models, and is driven by non-functional properties assessed on the models themselves. It consists of a two-step process working during application operation, where model assessment verifies non-functional properties of ML models trained and selected at development time, and model substitution guarantees a continuous and stable support of non-functional properties. We experimentally evaluate our solution in a real-world scenario focusing on non-functional property fairness.
Authors: Paul Scemama, Ariel Kapusta
Bayesian deep learning and conformal prediction are two methods that have been used to convey uncertainty and increase safety in machine learning systems. We focus on combining Bayesian deep learning with split conformal prediction and how this combination effects out-of-distribution coverage; particularly in the case of multiclass image classification. We suggest that if the model is generally underconfident on the calibration set, then the resultant conformal sets may exhibit worse out-of-distribution coverage compared to simple predictive credible sets. Conversely, if the model is overconfident on the calibration set, the use of conformal prediction may improve out-of-distribution coverage. We evaluate prediction sets as a result of combining split conformal methods and neural networks trained with (i) stochastic gradient descent, (ii) deep ensembles, and (iii) mean-field variational inference. Our results suggest that combining Bayesian deep learning models with split conformal prediction can, in some cases, cause unintended consequences such as reducing out-of-distribution coverage.
Authors: Thibaud Leteno, Antoine Gourru, Charlotte Laclau, Rémi Emonet, Christophe Gravier
Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g. women vs. men) remains an open challenge. This paper presents a novel method for mitigating biases in neural text classification, agnostic to the model architecture. Considering the difficulty to distinguish fair from unfair information in a text encoder, we take inspiration from adversarial training to induce Wasserstein independence between representations learned to predict our target label and the ones learned to predict some sensitive attribute. Our approach provides two significant advantages. Firstly, it does not require annotations of sensitive attributes in both testing and training data. This is more suitable for real-life scenarios compared to existing methods that require annotations of sensitive attributes at train time. Second, our approach exhibits a comparable or better fairness-accuracy trade-off compared to existing methods.
Authors: Bhavya Mehta, Nirmit Deliwala, Madhav Chandane
Multimodal single-cell technologies enable the simultaneous collection of diverse data types from individual cells, enhancing our understanding of cellular states. However, the integration of these datatypes and modeling the interrelationships between modalities presents substantial computational and analytical challenges in disease biomarker detection and drug discovery. Established practices rely on isolated methodologies to investigate individual molecular aspects separately, often resulting in inaccurate analyses. To address these obstacles, distinct Machine Learning Techniques are leveraged, each of its own kind to model the co-variation of DNA to RNA, and finally to surface proteins in single cells during hematopoietic stem cell development, which simplifies understanding of underlying cellular mechanisms and immune responses. Experiments conducted on a curated subset of a 300,000-cell time course dataset, highlights the exceptional performance of Echo State Networks, boasting a remarkable state-of-the-art correlation score of 0.94 and 0.895 on Multi-omic and CiteSeq datasets. Beyond the confines of this study, these findings hold promise for advancing comprehension of cellular differentiation and function, leveraging the potential of Machine Learning.
Authors: Joseph Rance, Filip Svoboda
Federated Learning is an important emerging distributed training paradigm that keeps data private on clients. It is now well understood that by controlling only a small subset of FL clients, it is possible to introduce a backdoor to a federated learning model, in the presence of certain attributes. In this paper, we present a new type of attack that compromises the fairness of the trained model. Fairness is understood to be the attribute-level performance distribution of a trained model. It is particularly salient in domains where, for example, skewed accuracy discrimination between subpopulations could have disastrous consequences. We find that by employing a threat model similar to that of a backdoor attack, an attacker is able to influence the aggregated model to have an unfair performance distribution between any given set of attributes. Furthermore, we find that this attack is possible by controlling only a single client. While combating naturally induced unfairness in FL has previously been discussed in depth, its artificially induced kind has been neglected. We show that defending against attacks on fairness should be a critical consideration in any situation where unfairness in a trained model could benefit a user who participated in its training.
Authors: Minqi Jiang, Michael Dennis, Edward Grefenstette, Tim Rocktäschel
Unsupervised environment design (UED) is a form of automatic curriculum learning for training robust decision-making agents to zero-shot transfer into unseen environments. Such autocurricula have received much interest from the RL community. However, UED experiments, based on CPU rollouts and GPU model updates, have often required several weeks of training. This compute requirement is a major obstacle to rapid innovation for the field. This work introduces the minimax library for UED training on accelerated hardware. Using JAX to implement fully-tensorized environments and autocurriculum algorithms, minimax allows the entire training loop to be compiled for hardware acceleration. To provide a petri dish for rapid experimentation, minimax includes a tensorized grid-world based on MiniGrid, in addition to reusable abstractions for conducting autocurricula in procedurally-generated environments. With these components, minimax provides strong UED baselines, including new parallelized variants, which achieve over 120$\times$ speedups in wall time compared to previous implementations when training with equal batch sizes. The minimax library is available under the Apache 2.0 license at https://github.com/facebookresearch/minimax.
Authors: Jonathan Sadeghi, Nicholas A. Lord, John Redford, Romain Mueller
Autonomous driving (AD) systems are often built and tested in a modular fashion, where the performance of different modules is measured using task-specific metrics. These metrics should be chosen so as to capture the downstream impact of each module and the performance of the system as a whole. For example, high perception quality should enable prediction and planning to be performed safely. Even though this is true in general, we show here that it is possible to construct planner inputs that score very highly on various perception quality metrics but still lead to planning failures. In an analogy to adversarial attacks on image classifiers, we call such inputs \textbf{adversarial perception errors} and show they can be systematically constructed using a simple boundary-attack algorithm. We demonstrate the effectiveness of this algorithm by finding attacks for two different black-box planners in several urban and highway driving scenarios using the CARLA simulator. Finally, we analyse the properties of these attacks and show that they are isolated in the input space of the planner, and discuss their implications for AD system deployment and testing.
Authors: Xiaodong Cui, Ashish Mittal, Songtao Lu, Wei Zhang, George Saon, Brian Kingsbury
Soft random sampling (SRS) is a simple yet effective approach for efficient training of large-scale deep neural networks when dealing with massive data. SRS selects a subset uniformly at random with replacement from the full data set in each epoch. In this paper, we conduct a theoretical and empirical analysis of SRS. First, we analyze its sampling dynamics including data coverage and occupancy. Next, we investigate its convergence with non-convex objective functions and give the convergence rate. Finally, we provide its generalization performance. We empirically evaluate SRS for image recognition on CIFAR10 and automatic speech recognition on Librispeech and an in-house payload dataset to demonstrate its effectiveness. Compared to existing coreset-based data selection methods, SRS offers a better accuracy-efficiency trade-off. Especially on real-world industrial scale data sets, it is shown to be a powerful training strategy with significant speedup and competitive performance with almost no additional computing cost.
Authors: Kush Kothari, Bhavya Mehta, Reshmika Nambiar, Seema Shrawne
This survey paper presents a brief overview of recent research on graph data augmentation and few-shot learning. It covers various techniques for graph data augmentation, including node and edge perturbation, graph coarsening, and graph generation, as well as the latest developments in few-shot learning, such as meta-learning and model-agnostic meta-learning. The paper explores these areas in depth and delves into further sub classifications. Rule based approaches and learning based approaches are surveyed under graph augmentation techniques. Few-Shot Learning on graphs is also studied in terms of metric learning techniques and optimization-based techniques. In all, this paper provides an extensive array of techniques that can be employed in solving graph processing problems faced in low-data scenarios.
Authors: Fatemeh Gholamzadeh Nasrabadi, AmirHossein Kashani, Pegah Zahedi, Mostafa Haghir Chehreghani
In recent years, graph neural networks (GNNs) have become a popular tool for solving various problems over graphs. In these models, the link structure of the graph is typically exploited and nodes' embeddings are iteratively updated based on adjacent nodes. Nodes' contents are used solely in the form of feature vectors, served as nodes' first-layer embeddings. However, the filters or convolutions, applied during iterations/layers to these initial embeddings lead to their impact diminish and contribute insignificantly to the final embeddings. In order to address this issue, in this paper we propose augmenting nodes' embeddings by embeddings generating from their content, at higher GNN layers. More precisely, we propose models wherein a structural embedding using a GNN and a content embedding are computed for each node. These two are combined using a combination layer to form the embedding of a node at a given layer. We suggest methods such as using an auto-encoder or building a content graph, to generate content embeddings. In the end, by conducting experiments over several real-world datasets, we demonstrate the high accuracy and performance of our models.
Authors: Duygu Altunkaya, Feyza Yildirim Okay, Suat Ozdemir
In the era of the Internet of Things (IoT), where smartphones, built-in systems, wireless sensors, and nearly every smart device connect through local networks or the internet, billions of smart things communicate with each other and generate vast amounts of time-series data. As IoT time-series data is high-dimensional and high-frequency, time-series classification or regression has been a challenging issue in IoT. Recently, deep learning algorithms have demonstrated superior performance results in time-series data classification in many smart and intelligent IoT applications. However, it is hard to explore the hidden dynamic patterns and trends in time-series. Recent studies show that transforming IoT data into images improves the performance of the learning model. In this paper, we present a review of these studies which use image transformation/encoding techniques in IoT domain. We examine the studies according to their encoding techniques, data types, and application areas. Lastly, we emphasize the challenges and future dimensions of image transformation.
Authors: Siyi Li, Arnaud Robert, A. Aldo Faisal, Matthew D. Piggott
This work proposes a novel data-driven model capable of providing accurate predictions for the power generation of all wind turbines in wind farms of arbitrary layout, yaw angle configurations and wind conditions. The proposed model functions by encoding a wind farm into a fully-connected graph and processing the graph representation through a graph transformer. The graph transformer surrogate is shown to generalise well and is able to uncover latent structural patterns within the graph representation of wind farms. It is demonstrated how the resulting surrogate model can be used to optimise yaw angle configurations using genetic algorithms, achieving similar levels of accuracy to industrially-standard wind farm simulation tools while only taking a fraction of the computational cost.
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 Occ3D. 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: Tim Peters, Hikmat Farhat
This paper proposes a novel method of classifying malware into families using high-resolution greyscale images and multiple instance learning to overcome adversarial binary enlargement. Current methods of visualisation-based malware classification largely rely on lossy transformations of inputs such as resizing to handle the large, variable-sized images. Through empirical analysis and experimentation, it is shown that these approaches cause crucial information loss that can be exploited. The proposed solution divides the images into patches and uses embedding-based multiple instance learning with a convolutional neural network and an attention aggregation function for classification. The implementation is evaluated on the Microsoft Malware Classification dataset and achieves accuracies of up to $96.6\%$ on adversarially enlarged samples compared to the baseline of $22.8\%$. The Python code is available online at https://github.com/timppeters/MIL-Malware-Images .
Authors: Boyang Yu, Aakash Kaku, Kangning Liu, Avinash Parnandi, Emily Fokas, Anita Venkatesan, Natasha Pandit, Rajesh Ranganath, Heidi Schambra, Carlos Fernandez-Granda
Automatic assessment of impairment and disease severity is a key challenge in data-driven medicine. We propose a novel framework to address this challenge, which leverages AI models trained exclusively on healthy individuals. The COnfidence-Based chaRacterization of Anomalies (COBRA) score exploits the decrease in confidence of these models when presented with impaired or diseased patients to quantify their deviation from the healthy population. We applied the COBRA score to address a key limitation of current clinical evaluation of upper-body impairment in stroke patients. The gold-standard Fugl-Meyer Assessment (FMA) requires in-person administration by a trained assessor for 30-45 minutes, which restricts monitoring frequency and precludes physicians from adapting rehabilitation protocols to the progress of each patient. The COBRA score, computed automatically in under one minute, is shown to be strongly correlated with the FMA on an independent test cohort for two different data modalities: wearable sensors ($\rho = 0.845$, 95% CI [0.743,0.908]) and video ($\rho = 0.746$, 95% C.I [0.594, 0.847]). To demonstrate the generalizability of the approach to other conditions, the COBRA score was also applied to quantify severity of knee osteoarthritis from magnetic-resonance imaging scans, again achieving significant correlation with an independent clinical assessment ($\rho = 0.644$, 95% C.I [0.585,0.696]).
Authors: Trung Dang, Jasper C.H. Lee, Maoyuan Song, Paul Valiant
There is growing interest in improving our algorithmic understanding of fundamental statistical problems such as mean estimation, driven by the goal of understanding the limits of what we can extract from valuable data. The state of the art results for mean estimation in $\mathbb{R}$ are 1) the optimal sub-Gaussian mean estimator by [LV22], with the tight sub-Gaussian constant for all distributions with finite but unknown variance, and 2) the analysis of the median-of-means algorithm by [BCL13] and a lower bound by [DLLO16], characterizing the big-O optimal errors for distributions for which only a $1+\alpha$ moment exists for $\alpha \in (0,1)$. Both results, however, are optimal only in the worst case. We initiate the fine-grained study of the mean estimation problem: Can algorithms leverage useful features of the input distribution to beat the sub-Gaussian rate, without explicit knowledge of such features?
We resolve this question with an unexpectedly nuanced answer: "Yes in limited regimes, but in general no". For any distribution $p$ with a finite mean, we construct a distribution $q$ whose mean is well-separated from $p$'s, yet $p$ and $q$ are not distinguishable with high probability, and $q$ further preserves $p$'s moments up to constants. The main consequence is that no reasonable estimator can asymptotically achieve better than the sub-Gaussian error rate for any distribution, matching the worst-case result of [LV22]. More generally, we introduce a new definitional framework to analyze the fine-grained optimality of algorithms, which we call "neighborhood optimality", interpolating between the unattainably strong "instance optimality" and the trivially weak "admissibility" definitions. Applying the new framework, we show that median-of-means is neighborhood optimal, up to constant factors. It is open to find a neighborhood-optimal estimator without constant factor slackness.
Authors: Samyak Jain, Robert Kirk, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka, Edward Grefenstette, Tim Rocktäschel, David Scott Krueger
Fine-tuning large pre-trained models has become the de facto strategy for developing both task-specific and general-purpose machine learning systems, including developing models that are safe to deploy. Despite its clear importance, there has been minimal work that explains how fine-tuning alters the underlying capabilities learned by a model during pretraining: does fine-tuning yield entirely novel capabilities or does it just modulate existing ones? We address this question empirically in synthetic, controlled settings where we can use mechanistic interpretability tools (e.g., network pruning and probing) to understand how the model's underlying capabilities are changing. We perform an extensive analysis of the effects of fine-tuning in these settings, and show that: (i) fine-tuning rarely alters the underlying model capabilities; (ii) a minimal transformation, which we call a 'wrapper', is typically learned on top of the underlying model capabilities, creating the illusion that they have been modified; and (iii) further fine-tuning on a task where such hidden capabilities are relevant leads to sample-efficient 'revival' of the capability, i.e., the model begins reusing these capability after only a few gradient steps. This indicates that practitioners can unintentionally remove a model's safety wrapper merely by fine-tuning it on a, e.g., superficially unrelated, downstream task. We additionally perform analysis on language models trained on the TinyStories dataset to support our claims in a more realistic setup.
Authors: Robert Geirhos, Jörn-Henrik Jacobsen, Claudio Michaelis, Richard Zemel, Wieland Brendel, Matthias Bethge, Felix A. Wichmann
Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently come into focus. In this perspective we seek to distill how many of deep learning's problems can be seen as different symptoms of the same underlying problem: shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in Comparative Psychology, Education and Linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike. Based on these observations, we develop a set of recommendations for model interpretation and benchmarking, highlighting recent advances in machine learning to improve robustness and transferability from the lab to real-world applications.
Authors: Chi-Hua Wang, Zhanyu Wang, Will Wei Sun, Guang Cheng
Devising dynamic pricing policy with always valid online statistical learning procedure is an important and as yet unresolved problem. Most existing dynamic pricing policy, which focus on the faithfulness of adopted customer choice models, exhibit a limited capability for adapting the online uncertainty of learned statistical model during pricing process. In this paper, we propose a novel approach for designing dynamic pricing policy based regularized online statistical learning with theoretical guarantees. The new approach overcomes the challenge of continuous monitoring of online Lasso procedure and possesses several appealing properties. In particular, we make the decisive observation that the always-validity of pricing decisions builds and thrives on the online regularization scheme. Our proposed online regularization scheme equips the proposed optimistic online regularized maximum likelihood pricing (OORMLP) pricing policy with three major advantages: encode market noise knowledge into pricing process optimism; empower online statistical learning with always-validity over all decision points; envelop prediction error process with time-uniform non-asymptotic oracle inequalities. This type of non-asymptotic inference results allows us to design more sample-efficient and robust dynamic pricing algorithms in practice. In theory, the proposed OORMLP algorithm exploits the sparsity structure of high-dimensional models and secures a logarithmic regret in a decision horizon. These theoretical advances are made possible by proposing an optimistic online Lasso procedure that resolves dynamic pricing problems at the process level, based on a novel use of non-asymptotic martingale concentration. In experiments, we evaluate OORMLP in different synthetic and real pricing problem settings, and demonstrate that OORMLP advances the state-of-the-art methods.
Authors: Chris Junchi Li, Wenlong Mou, Martin J. Wainwright, Michael I. Jordan
We study the problem of solving strongly convex and smooth unconstrained optimization problems using stochastic first-order algorithms. We devise a novel algorithm, referred to as \emph{Recursive One-Over-T SGD} (\ROOTSGD), based on an easily implementable, recursive averaging of past stochastic gradients. We prove that it simultaneously achieves state-of-the-art performance in both a finite-sample, nonasymptotic sense and an asymptotic sense. On the nonasymptotic side, we prove risk bounds on the last iterate of \ROOTSGD with leading-order terms that match the optimal statistical risk with a unity pre-factor, along with a higher-order term that scales at the sharp rate of $O(n^{-3/2})$ under the Lipschitz condition on the Hessian matrix. On the asymptotic side, we show that when a mild, one-point Hessian continuity condition is imposed, the rescaled last iterate of (multi-epoch) \ROOTSGD converges asymptotically to a Gaussian limit with the Cram\'{e}r-Rao optimal asymptotic covariance, for a broad range of step-size choices.
Authors: Hans-Peter Beise, Steve Dias Da Cruz
In Radhakrishnan et al. [2020], the authors empirically show that autoencoders trained with usual SGD methods shape out basins of attraction around their training data. We consider network functions of width not exceeding the input dimension and prove that in this situation basins of attraction are bounded and their complement cannot have bounded components. Our conditions in these results are met in several experiments of the latter work and we thus address a question posed therein. We also show that under some more restrictive conditions the basins of attraction are path-connected. The tightness of the conditions in our results is demonstrated by means of several examples. Finally, the arguments used to prove the above results allow us to derive a root cause why scalar-valued neural network functions that fulfill our bounded width condition are not dense in spaces of continuous functions.
Authors: Prashant Rajaram, Puneet Manchanda
Influencer marketing has become a very popular tool to reach customers. Despite the rapid growth in influencer videos, there has been little research on the effectiveness of their constituent features in explaining video engagement. We study YouTube influencers and analyze their unstructured video data across text, audio and images using an "interpretable deep learning" framework that accomplishes both goals of prediction and interpretation. Our prediction-based approach analyzes unstructured data and finds that "what is said" in words (text) is more influential than "how it is said" in imagery (images) or acoustics (audio). Our novel interpretation-based approach is implemented after completion of model prediction by analyzing the same source of unstructured data to measure importance attributed to the video features. We eliminate several spurious relationships in two steps, identifying a subset of relationships which are confirmed using theory. We uncover novel findings that establish distinct associations for measures of shallow and deep engagement based on the dual-system framework of human thinking. Our approach is validated using simulated data, and we discuss the learnings from our findings for influencers and brands.
Authors: Ilya Chevyrev, Andris Gerasimovics, Hendrik Weber
We investigate the use of models from the theory of regularity structures as features in machine learning tasks. A model is a polynomial function of a space-time signal designed to well-approximate solutions to partial differential equations (PDEs), even in low regularity regimes. Models can be seen as natural multi-dimensional generalisations of signatures of paths; our work therefore aims to extend the recent use of signatures in data science beyond the context of time-ordered data. We provide a flexible definition of a model feature vector associated to a space-time signal, along with two algorithms which illustrate ways in which these features can be combined with linear regression. We apply these algorithms in several numerical experiments designed to learn solutions to PDEs with a given forcing and boundary data. Our experiments include semi-linear parabolic and wave equations with forcing, and Burgers' equation with no forcing. We find an advantage in favour of our algorithms when compared to several alternative methods. Additionally, in the experiment with Burgers' equation, we find non-trivial predictive power when noise is added to the observations.
Authors: Marta Monaci, Valerio Agasucci, Giorgio Grani
There is a growing interest in integrating machine learning techniques and optimization to solve challenging optimization problems. In this work, we propose a deep reinforcement learning methodology for the job shop scheduling problem (JSSP). The aim is to build up a greedy-like heuristic able to learn on some distribution of JSSP instances, different in the number of jobs and machines. The need for fast scheduling methods is well known, and it arises in many areas, from transportation to healthcare. We model the JSSP as a Markov Decision Process and then we exploit the efficacy of reinforcement learning to solve the problem. We adopt an actor-critic scheme, where the action taken by the agent is influenced by policy considerations on the state-value function. The procedures are adapted to take into account the challenging nature of JSSP, where the state and the action space change not only for every instance but also after each decision. To tackle the variability in the number of jobs and operations in the input, we modeled the agent using two incident LSTM models, a special type of deep neural network. Experiments show the algorithm reaches good solutions in a short time, proving that is possible to generate new greedy heuristics just from learning-based methodologies. Benchmarks have been generated in comparison with the commercial solver CPLEX. As expected, the model can generalize, to some extent, to larger problems or instances originated by a different distribution from the one used in training.
Authors: Haitao Mao, Lun Du, Yujia Zheng, Qiang Fu, Zelin Li, Xu Chen, Shi Han, Dongmei Zhang
Graph Neural Networks (GNNs) have achieved great success on a variety of tasks with graph-structural data, among which node classification is an essential one. Unsupervised Graph Domain Adaptation (UGDA) shows its practical value of reducing the labeling cost for node classification. It leverages knowledge from a labeled graph (i.e., source domain) to tackle the same task on another unlabeled graph (i.e., target domain). Most existing UGDA methods heavily rely on the labeled graph in the source domain. They utilize labels from the source domain as the supervision signal and are jointly trained on both the source graph and the target graph. However, in some real-world scenarios, the source graph is inaccessible because of privacy issues. Therefore, we propose a novel scenario named Source Free Unsupervised Graph Domain Adaptation (SFUGDA). In this scenario, the only information we can leverage from the source domain is the well-trained source model, without any exposure to the source graph and its labels. As a result, existing UGDA methods are not feasible anymore. To address the non-trivial adaptation challenges in this practical scenario, we propose a model-agnostic algorithm called SOGA for domain adaptation to fully exploit the discriminative ability of the source model while preserving the consistency of structural proximity on the target graph. We prove the effectiveness of the proposed algorithm both theoretically and empirically. The experimental results on four cross-domain tasks show consistent improvements in the Macro-F1 score and Macro-AUC.
Authors: Jing Xu, Jiaye Teng, Yang Yuan, Andrew Chi-Chih Yao
One of the major open problems in machine learning is to characterize generalization in the overparameterized regime, where most traditional generalization bounds become inconsistent even for overparameterized linear regression. In many scenarios, this failure can be attributed to obscuring the crucial interplay between the training algorithm and the underlying data distribution. This paper demonstrate that the generalization behavior of overparameterized model should be analyzed in a both data-relevant and algorithm-relevant manner. To make a formal characterization, We introduce a notion called data-algorithm compatibility, which considers the generalization behavior of the entire data-dependent training trajectory, instead of traditional last-iterate analysis. We validate our claim by studying the setting of solving overparameterized linear regression with gradient descent. Specifically, we perform a data-dependent trajectory analysis and derive a sufficient condition for compatibility in such a setting. Our theoretical results demonstrate that if we take early stopping iterates into consideration, generalization can hold with significantly weaker restrictions on the problem instance than the previous last-iterate analysis.
Authors: Yixuan He, Xitong Zhang, Junjie Huang, Benedek Rozemberczki, Mihai Cucuringu, Gesine Reinert
Networks are ubiquitous in many real-world applications (e.g., social networks encoding trust/distrust relationships, correlation networks arising from time series data). While many networks are signed or directed, or both, there is a lack of unified software packages on graph neural networks (GNNs) specially designed for signed and directed networks. In this paper, we present PyTorch Geometric Signed Directed (PyGSD), a software package which fills this gap. Along the way, we evaluate the implemented methods with experiments with a view to providing insights into which method to choose for a given task. The deep learning framework consists of easy-to-use GNN models, synthetic and real-world data, as well as task-specific evaluation metrics and loss functions for signed and directed networks. As an extension library for PyG, our proposed software is maintained with open-source releases, detailed documentation, continuous integration, unit tests and code coverage checks. The GitHub repository of the library is https://github.com/SherylHYX/pytorch_geometric_signed_directed.
Authors: Johannes O. Royset, Louis L. Chen, Eric Eckstrand
In practice, optimization models are often prone to unavoidable inaccuracies due to dubious assumptions and corrupted data. Traditionally, this placed special emphasis on risk-based and robust formulations, and their focus on ``conservative" decisions. We develop, in contrast, an ``optimistic" framework based on Rockafellian relaxations in which optimization is conducted not only over the original decision space but also jointly with a choice of model perturbation. The framework enables us to address challenging problems with ambiguous probability distributions from the areas of two-stage stochastic optimization without relatively complete recourse, probability functions lacking continuity properties, expectation constraints, and outlier analysis. We are also able to circumvent the fundamental difficulty in stochastic optimization that convergence of distributions fails to guarantee convergence of expectations. The framework centers on the novel concepts of exact and limit-exact Rockafellians, with interpretations of ``negative'' regularization emerging in certain settings. We illustrate the role of Phi-divergence, examine rates of convergence under changing distributions, and explore extensions to first-order optimality conditions. The main development is free of assumptions about convexity, smoothness, and even continuity of objective functions. Numerical results in the setting of computer vision and text analytics with label noise illustrate the framework.
Authors: Amanda A. Howard, Mauro Perego, George E. Karniadakis, Panos Stinis
Operator learning for complex nonlinear systems is increasingly common in modeling multi-physics and multi-scale systems. However, training such high-dimensional operators requires a large amount of expensive, high-fidelity data, either from experiments or simulations. In this work, we present a composite Deep Operator Network (DeepONet) for learning using two datasets with different levels of fidelity to accurately learn complex operators when sufficient high-fidelity data is not available. Additionally, we demonstrate that the presence of low-fidelity data can improve the predictions of physics-informed learning with DeepONets. We demonstrate the new multi-fidelity training in diverse examples, including modeling of the ice-sheet dynamics of the Humboldt glacier, Greenland, using two different fidelity models and also using the same physical model at two different resolutions.
Authors: Arshed Nabeel, Ashwin Karichannavar, Shuaib Palathingal, Jitesh Jhawar, David B. Brückner, Danny Raj M., Vishwesha Guttal
Stochastic differential equations (SDEs) are an important framework to model dynamics with randomness, as is common in most biological systems. The inverse problem of integrating these models with empirical data remains a major challenge. Here, we present a software package, PyDaDDy (Python Library for Data Driven Dynamics) that takes time series data as an input and outputs an interpretable SDE. We achieve this by combining traditional approaches from stochastic calculus literature with state-of-the-art equation discovery techniques. We validate our approach on synthetic datasets, and demonstrate the generality and applicability of the method on two real-world datasets of vastly different spatiotemporal scales: (i) collective movement of fish school where stochasticity plays a crucial role, and (ii) confined migration of a single cell, primarily following a relaxed oscillation. We make the method available as an easy-to-use, open-source Python package, PyDaddy (Python Library for Data Driven Dynamics).
Authors: Nadav Dym, Steven J. Gortler
This paper studies separating invariants: mappings on $D$ dimensional domains which are invariant to an appropriate group action, and which separate orbits. The motivation for this study comes from the usefulness of separating invariants in proving universality of equivariant neural network architectures.
We observe that in several cases the cardinality of separating invariants proposed in the machine learning literature is much larger than the dimension $D$. As a result, the theoretical universal constructions based on these separating invariants is unrealistically large. Our goal in this paper is to resolve this issue.
We show that when a continuous family of semi-algebraic separating invariants is available, separation can be obtained by randomly selecting $2D+1 $ of these invariants. We apply this methodology to obtain an efficient scheme for computing separating invariants for several classical group actions which have been studied in the invariant learning literature. Examples include matrix multiplication actions on point clouds by permutations, rotations, and various other linear groups.
Often the requirement of invariant separation is relaxed and only generic separation is required. In this case, we show that only $D+1$ invariants are required. More importantly, generic invariants are often significantly easier to compute, as we illustrate by discussing generic and full separation for weighted graphs. Finally we outline an approach for proving that separating invariants can be constructed also when the random parameters have finite precision.
Authors: Zhen Bi, Siyuan Cheng, Jing Chen, Xiaozhuan Liang, Feiyu Xiong, Ningyu Zhang
Transformers have achieved remarkable performance in widespread fields, including natural language processing, computer vision and graph mining. However, vanilla Transformer architectures have not yielded promising improvements in the Knowledge Graph (KG) representations, where the translational distance paradigm dominates this area. Note that vanilla Transformer architectures struggle to capture the intrinsically heterogeneous structural and semantic information of knowledge graphs. To this end, we propose a new variant of Transformer for knowledge graph representations dubbed Relphormer. Specifically, we introduce Triple2Seq which can dynamically sample contextualized sub-graph sequences as the input to alleviate the heterogeneity issue. We propose a novel structure-enhanced self-attention mechanism to encode the relational information and keep the semantic information within entities and relations. Moreover, we utilize masked knowledge modeling for general knowledge graph representation learning, which can be applied to various KG-based tasks including knowledge graph completion, question answering, and recommendation. Experimental results on six datasets show that Relphormer can obtain better performance compared with baselines. Code is available in https://github.com/zjunlp/Relphormer.
Authors: Weiqi Wang, Simone Brugiapaglia
High-dimensional Partial Differential Equations (PDEs) are a popular mathematical modelling tool, with applications ranging from finance to computational chemistry. However, standard numerical techniques for solving these PDEs are typically affected by the curse of dimensionality. In this work, we tackle this challenge while focusing on stationary diffusion equations defined over a high-dimensional domain with periodic boundary conditions. Inspired by recent progress in sparse function approximation in high dimensions, we propose a new method called compressive Fourier collocation. Combining ideas from compressive sensing and spectral collocation, our method replaces the use of structured collocation grids with Monte Carlo sampling and employs sparse recovery techniques, such as orthogonal matching pursuit and $\ell^1$ minimization, to approximate the Fourier coefficients of the PDE solution. We conduct a rigorous theoretical analysis showing that the approximation error of the proposed method is comparable with the best $s$-term approximation (with respect to the Fourier basis) to the solution. Using the recently introduced framework of random sampling in bounded Riesz systems, our analysis shows that the compressive Fourier collocation method mitigates the curse of dimensionality with respect to the number of collocation points under sufficient conditions on the regularity of the diffusion coefficient. We also present numerical experiments that illustrate the accuracy and stability of the method for the approximation of sparse and compressible solutions.
Authors: Fred Lu, Edward Raff, Francis Ferraro
Many metric learning tasks, such as triplet learning, nearest neighbor retrieval, and visualization, are treated primarily as embedding tasks where the ultimate metric is some variant of the Euclidean distance (e.g., cosine or Mahalanobis), and the algorithm must learn to embed points into the pre-chosen space. The study of non-Euclidean geometries is often not explored, which we believe is due to a lack of tools for learning non-Euclidean measures of distance. Recent work has shown that Bregman divergences can be learned from data, opening a promising approach to learning asymmetric distances. We propose a new approach to learning arbitrary Bergman divergences in a differentiable manner via input convex neural networks and show that it overcomes significant limitations of previous works. We also demonstrate that our method more faithfully learns divergences over a set of both new and previously studied tasks, including asymmetric regression, ranking, and clustering. Our tests further extend to known asymmetric, but non-Bregman tasks, where our method still performs competitively despite misspecification, showing the general utility of our approach for asymmetric learning.
Authors: Suhan Shetty, Teguh Lembono, Tobias Loew, Sylvain Calinon
The convergence of many numerical optimization techniques is highly dependent on the initial guess given to the solver. To address this issue, we propose a novel approach that utilizes tensor methods to initialize existing optimization solvers near global optima. Our method does not require access to a database of good solutions. We first transform the cost function, which depends on both task parameters and optimization variables, into a probability density function. Unlike existing approaches, the joint probability distribution of the task parameters and optimization variables is approximated using the Tensor Train model, which enables efficient conditioning and sampling. We treat the task parameters as random variables, and for a given task, we generate samples for decision variables from the conditional distribution to initialize the optimization solver. Our method can produce multiple solutions (when they exist) faster than existing methods. We first evaluate the approach on benchmark functions for numerical optimization that are hard to solve using gradient-based optimization solvers with a naive initialization. The results show that the proposed method can generate samples close to global optima and from multiple modes. We then demonstrate the generality and relevance of our framework to robotics by applying it to inverse kinematics with obstacles and motion planning problems with a 7-DoF manipulator.
Authors: Ruichu Cai, Weilin Chen, Zeqin Yang, Shu Wan, Chen Zheng, Xiaoqing Yang, Jiecheng Guo
Estimating long-term causal effects based on short-term surrogates is a significant but challenging problem in many real-world applications, e.g., marketing and medicine. Despite its success in certain domains, most existing methods estimate causal effects in an idealistic and simplistic way - ignoring the causal structure among short-term outcomes and treating all of them as surrogates. However, such methods cannot be well applied to real-world scenarios, in which the partially observed surrogates are mixed with their proxies among short-term outcomes. To this end, we develop our flexible method, Laser, to estimate long-term causal effects in the more realistic situation that the surrogates are observed or have observed proxies.Given the indistinguishability between the surrogates and proxies, we utilize identifiable variational auto-encoder (iVAE) to recover the whole valid surrogates on all the surrogates candidates without the need of distinguishing the observed surrogates or the proxies of latent surrogates. With the help of the recovered surrogates, we further devise an unbiased estimation of long-term causal effects. Extensive experimental results on the real-world and semi-synthetic datasets demonstrate the effectiveness of our proposed method.
Authors: Md. Rezaul Karim, Md. Shajalal, Alex Graß, Till Döhmen, Sisay Adugna Chala, Alexander Boden, Christian Beecks, Stefan Decker
Deep neural networks (DNNs) have been shown to outperform traditional machine learning algorithms in a broad variety of application domains due to their effectiveness in modeling complex problems and handling high-dimensional datasets. Many real-life datasets, however, are of increasingly high dimensionality, where a large number of features may be irrelevant for both supervised and unsupervised learning tasks. The inclusion of such features would not only introduce unwanted noise but also increase computational complexity. Furthermore, due to high non-linearity and dependency among a large number of features, DNN models tend to be unavoidably opaque and perceived as black-box methods because of their not well-understood internal functioning. Their algorithmic complexity is often simply beyond the capacities of humans to understand the interplay among myriads of hyperparameters. A well-interpretable model can identify statistically significant features and explain the way they affect the model's outcome. In this paper, we propose an efficient method to improve the interpretability of black-box models for classification tasks in the case of high-dimensional datasets. First, we train a black-box model on a high-dimensional dataset to learn the embeddings on which the classification is performed. To decompose the inner working principles of the black-box model and to identify top-k important features, we employ different probing and perturbing techniques. We then approximate the behavior of the black-box model by means of an interpretable surrogate model on the top-k feature space. Finally, we derive decision rules and local explanations from the surrogate model to explain individual decisions. Our approach outperforms state-of-the-art methods like TabNet and XGboost when tested on different datasets with varying dimensionality between 50 and 20,000 w.r.t metrics and explainability.
Authors: Marcus Klasson, Hedvig Kjellström, Cheng Zhang
Replay methods are known to be successful at mitigating catastrophic forgetting in continual learning scenarios despite having limited access to historical data. However, storing historical data is cheap in many real-world settings, yet replaying all historical data is often prohibited due to processing time constraints. In such settings, we propose that continual learning systems should learn the time to learn and schedule which tasks to replay at different time steps. We first demonstrate the benefits of our proposal by using Monte Carlo tree search to find a proper replay schedule, and show that the found replay schedules can outperform fixed scheduling policies when combined with various replay methods in different continual learning settings. Additionally, we propose a framework for learning replay scheduling policies with reinforcement learning. We show that the learned policies can generalize better in new continual learning scenarios compared to equally replaying all seen tasks, without added computational cost. Our study reveals the importance of learning the time to learn in continual learning, which brings current research closer to real-world needs.
Authors: Dong-Young Lim, Ariel Neufeld, Sotirios Sabanis, Ying Zhang
We introduce a new Langevin dynamics based algorithm, called e-TH$\varepsilon$O POULA, to solve optimization problems with discontinuous stochastic gradients which naturally appear in real-world applications such as quantile estimation, vector quantization, CVaR minimization, and regularized optimization problems involving ReLU neural networks. We demonstrate both theoretically and numerically the applicability of the e-TH$\varepsilon$O POULA algorithm. More precisely, under the conditions that the stochastic gradient is locally Lipschitz in average and satisfies a certain convexity at infinity condition, we establish non-asymptotic error bounds for e-TH$\varepsilon$O POULA in Wasserstein distances and provide a non-asymptotic estimate for the expected excess risk, which can be controlled to be arbitrarily small. Three key applications in finance and insurance are provided, namely, multi-period portfolio optimization, transfer learning in multi-period portfolio optimization, and insurance claim prediction, which involve neural networks with (Leaky)-ReLU activation functions. Numerical experiments conducted using real-world datasets illustrate the superior empirical performance of e-TH$\varepsilon$O POULA compared to SGLD, TUSLA, ADAM, and AMSGrad in terms of model accuracy.
Authors: Samir M. Perlaza, Gaetan Bisson, Iñaki Esnaola, Alain Jean-Marie, Stefano Rini
The empirical risk minimization (ERM) problem with relative entropy regularization (ERM-RER) is investigated under the assumption that the reference measure is a {\sigma}-finite measure, and not necessarily a probability measure. Under this assumption, which leads to a generalization of the ERM-RER problem allowing a larger degree of flexibility for incorporating prior knowledge, numerous relevant properties are stated. Among these properties, the solution to this problem, if it exists, is shown to be a unique probability measure, often mutually absolutely continuous with the reference measure. Such a solution exhibits a probably-approximately-correct guarantee for the ERM problem independently of whether the latter possesses a solution. For a fixed dataset, the empirical risk is shown to be a sub-Gaussian random variable when the models are sampled from the solution to the ERM-RER problem. The generalization capabilities of the solution to the ERM-RER problem (the Gibbs algorithm) are studied via the sensitivity of the expected empirical risk to deviations from such a solution towards alternative probability measures. Finally, an interesting connection between sensitivity, generalization error, and lautum information is established
Authors: Junki Mori, Tomoyuki Yoshiyama, Furukawa Ryo, Isamu Teranishi
Federated learning (FL) is a decentralized machine learning technique that enables multiple clients to collaboratively train models without requiring clients to reveal their raw data to each other. Although traditional FL trains a single global model with average performance among clients, statistical data heterogeneity across clients has resulted in the development of personalized FL (PFL), which trains personalized models with good performance on each client's data. A key challenge with PFL is how to facilitate clients with similar data to collaborate more in a situation where each client has data from complex distribution and cannot determine one another's distribution. In this paper, we propose a new PFL method (pFedMB) using multi-branch architecture, which achieves personalization by splitting each layer of a neural network into multiple branches and assigning client-specific weights to each branch. We also design an aggregation method to improve the communication efficiency and the model performance, with which each branch is globally updated with weighted averaging by client-specific weights assigned to the branch. pFedMB is simple but effective in facilitating each client to share knowledge with similar clients by adjusting the weights assigned to each branch. We experimentally show that pFedMB performs better than the state-of-the-art PFL methods using the CIFAR10 and CIFAR100 datasets.
Authors: Yuan Zhang, Zhiqi Bu
Machine learning models have shone in a variety of domains and attracted increasing attention from both the security and the privacy communities. One important yet worrying question is: Will training models under the differential privacy (DP) constraint have an unfavorable impact on their adversarial robustness? While previous works have postulated that privacy comes at the cost of worse robustness, we give the first theoretical analysis to show that DP models can indeed be robust and accurate, even sometimes more robust than their naturally-trained non-private counterparts. We observe three key factors that influence the privacy-robustness-accuracy tradeoff: (1) hyper-parameters for DP optimizers are critical; (2) pre-training on public data significantly mitigates the accuracy and robustness drop; (3) choice of DP optimizers makes a difference. With these factors set properly, we achieve 90\% natural accuracy, 72\% robust accuracy ($+9\%$ than the non-private model) under $l_2(0.5)$ attack, and 69\% robust accuracy ($+16\%$ than the non-private model) with pre-trained SimCLRv2 model under $l_\infty(4/255)$ attack on CIFAR10 with $\epsilon=2$. In fact, we show both theoretically and empirically that DP models are Pareto optimal on the accuracy-robustness tradeoff. Empirically, the robustness of DP models is consistently observed across various datasets and models. We believe our encouraging results are a significant step towards training models that are private as well as robust.
Authors: Arnaud Bougaham, Mohammed El Adoui, Isabelle Linden, Benoît Frénay
In recent years, the industrial sector has evolved towards its fourth revolution. The quality control domain is particularly interested in advanced machine learning for computer vision anomaly detection. Nevertheless, several challenges have to be faced, including imbalanced datasets, the image complexity, and the zero-false-negative (ZFN) constraint to guarantee the high-quality requirement. This paper illustrates a use case for an industrial partner, where Printed Circuit Board Assembly (PCBA) images are first reconstructed with a Vector Quantized Generative Adversarial Network (VQGAN) trained on normal products. Then, several multi-level metrics are extracted on a few normal and abnormal images, highlighting anomalies through reconstruction differences. Finally, a classifer is trained to build a composite anomaly score thanks to the metrics extracted. This three-step approach is performed on the public MVTec-AD datasets and on the partner PCBA dataset, where it achieves a regular accuracy of 95.69% and 87.93% under the ZFN constraint.
Authors: Alon Zolfi, Guy Amit, Amit Baras, Satoru Koda, Ikuya Morikawa, Yuval Elovici, Asaf Shabtai
Out-of-distribution (OOD) detection has attracted a large amount of attention from the machine learning research community in recent years due to its importance in deployed systems. Most of the previous studies focused on the detection of OOD samples in the multi-class classification task. However, OOD detection in the multi-label classification task, a more common real-world use case, remains an underexplored domain. In this research, we propose YolOOD - a method that utilizes concepts from the object detection domain to perform OOD detection in the multi-label classification task. Object detection models have an inherent ability to distinguish between objects of interest (in-distribution) and irrelevant objects (e.g., OOD objects) in images that contain multiple objects belonging to different class categories. These abilities allow us to convert a regular object detection model into an image classifier with inherent OOD detection capabilities with just minor changes. We compare our approach to state-of-the-art OOD detection methods and demonstrate YolOOD's ability to outperform these methods on a comprehensive suite of in-distribution and OOD benchmark datasets.
Authors: Shvetank Prakash, Matthew Stewart, Colby Banbury, Mark Mazumder, Pete Warden, Brian Plancher, Vijay Janapa Reddi
The sustained growth of carbon emissions and global waste elicits significant sustainability concerns for our environment's future. The growing Internet of Things (IoT) has the potential to exacerbate this issue. However, an emerging area known as Tiny Machine Learning (TinyML) has the opportunity to help address these environmental challenges through sustainable computing practices. TinyML, the deployment of machine learning (ML) algorithms onto low-cost, low-power microcontroller systems, enables on-device sensor analytics that unlocks numerous always-on ML applications. This article discusses both the potential of these TinyML applications to address critical sustainability challenges, as well as the environmental footprint of this emerging technology. Through a complete life cycle analysis (LCA), we find that TinyML systems present opportunities to offset their carbon emissions by enabling applications that reduce the emissions of other sectors. Nevertheless, when globally scaled, the carbon footprint of TinyML systems is not negligible, necessitating that designers factor in environmental impact when formulating new devices. Finally, we outline research directions to enable further sustainable contributions of TinyML.
Authors: Adrian Celaya, Beatrice Riviere, David Fuentes
Within medical imaging segmentation, the Dice coefficient and Hausdorff-based metrics are standard measures of success for deep learning models. However, modern loss functions for medical image segmentation often only consider the Dice coefficient or similar region-based metrics during training. As a result, segmentation architectures trained over such loss functions run the risk of achieving high accuracy for the Dice coefficient but low accuracy for Hausdorff-based metrics. Low accuracy on Hausdorff-based metrics can be problematic for applications such as tumor segmentation, where such benchmarks are crucial. For example, high Dice scores accompanied by significant Hausdorff errors could indicate that the predictions fail to detect small tumors. We propose the Generalized Surface Loss function, a novel loss function to minimize Hausdorff-based metrics with more desirable numerical properties than current methods and with weighting terms for class imbalance. Our loss function outperforms other losses when tested on the LiTS and BraTS datasets using the state-of-the-art nnUNet architecture. These results suggest we can improve medical imaging segmentation accuracy with our novel loss function.
Authors: Luis Müller, Mikhail Galkin, Christopher Morris, Ladislav Rampášek
Recently, transformer architectures for graphs emerged as an alternative to established techniques for machine learning with graphs, such as (message-passing) graph neural networks. So far, they have shown promising empirical results, e.g., on molecular prediction datasets, often attributed to their ability to circumvent graph neural networks' shortcomings, such as over-smoothing and over-squashing. Here, we derive a taxonomy of graph transformer architectures, bringing some order to this emerging field. We overview their theoretical properties, survey structural and positional encodings, and discuss extensions for important graph classes, e.g., 3D molecular graphs. Empirically, we probe how well graph transformers can recover various graph properties, how well they can deal with heterophilic graphs, and to what extent they prevent over-squashing. Further, we outline open challenges and research direction to stimulate future work. Our code is available at https://github.com/luis-mueller/probing-graph-transformers.
Authors: Shihong Ding, Hanze Dong, Cong Fang, Zhouchen Lin, Tong Zhang
We consider the non-convex non-concave objective function in two-player zero-sum continuous games. The existence of pure Nash equilibrium requires stringent conditions, posing a major challenge for this problem. To circumvent this difficulty, we examine the problem of identifying a mixed Nash equilibrium, where strategies are randomized and characterized by probability distributions over continuous domains.To this end, we propose PArticle-based Primal-dual ALgorithm (PAPAL) tailored for a weakly entropy-regularized min-max optimization over probability distributions. This algorithm employs the stochastic movements of particles to represent the updates of random strategies for the $\epsilon$-mixed Nash equilibrium. We offer a comprehensive convergence analysis of the proposed algorithm, demonstrating its effectiveness. In contrast to prior research that attempted to update particle importance without movements, PAPAL is the first implementable particle-based algorithm accompanied by non-asymptotic quantitative convergence results, running time, and sample complexity guarantees. Our framework contributes novel insights into the particle-based algorithms for continuous min-max optimization in the general non-convex non-concave setting.
Authors: Jiani Huang, Ziyang Li, Mayur Naik, Ser-Nam Lim
We propose LASER, a neuro-symbolic approach to learn semantic video representations that capture rich spatial and temporal properties in video data by leveraging high-level logic specifications. In particular, we formulate the problem in terms of alignment between raw videos and spatio-temporal logic specifications. The alignment algorithm leverages a differentiable symbolic reasoner and a combination of contrastive, temporal, and semantics losses. It effectively and efficiently trains low-level perception models to extract fine-grained video representation in the form of a spatio-temporal scene graph that conforms to the desired high-level specification. In doing so, we explore a novel methodology that weakly supervises the learning of video semantic representations through logic specifications. We evaluate our method on two datasets with rich spatial and temporal specifications: 20BN-Something-Something and MUGEN. We demonstrate that our method learns better fine-grained video semantics than existing baselines.
Authors: Jiachen T. Wang, Saeed Mahloujifar, Tong Wu, Ruoxi Jia, Prateek Mittal
Bounding privacy leakage over compositions, i.e., privacy accounting, is a key challenge in differential privacy (DP). The privacy parameter ($\eps$ or $\delta$) is often easy to estimate but hard to bound. In this paper, we propose a new differential privacy paradigm called estimate-verify-release (EVR), which addresses the challenges of providing a strict upper bound for privacy parameter in DP compositions by converting an estimate of privacy parameter into a formal guarantee. The EVR paradigm first estimates the privacy parameter of a mechanism, then verifies whether it meets this guarantee, and finally releases the query output based on the verification result. The core component of the EVR is privacy verification. We develop a randomized privacy verifier using Monte Carlo (MC) technique. Furthermore, we propose an MC-based DP accountant that outperforms existing DP accounting techniques in terms of accuracy and efficiency. Our empirical evaluation shows the newly proposed EVR paradigm improves the utility-privacy tradeoff for privacy-preserving machine learning.
Authors: Junki Mori, Ryo Furukawa, Isamu Teranishi, Jun Sakuma
Heterogeneous unsupervised domain adaptation (HUDA) is the most challenging domain adaptation setting where the feature spaces of source and target domains are heterogeneous, and the target domain has only unlabeled data. Existing HUDA methods assume that both positive and negative examples are available in the source domain, which may not be satisfied in some real applications. This paper addresses a new challenging setting called positive and unlabeled heterogeneous unsupervised domain adaptation (PU-HUDA), a HUDA setting where the source domain only has positives. PU-HUDA can also be viewed as an extension of PU learning where the positive and unlabeled examples are sampled from different domains. A naive combination of existing HUDA and PU learning methods is ineffective in PU-HUDA due to the gap in label distribution between the source and target domains. To overcome this issue, we propose a novel method, predictive adversarial domain adaptation (PADA), which can predict likely positive examples from the unlabeled target data and simultaneously align the feature spaces to reduce the distribution divergence between the whole source data and the likely positive target data. PADA achieves this by a unified adversarial training framework for learning a classifier to predict positive examples and a feature transformer to transform the target feature space to that of the source. Specifically, they are both trained to fool a common discriminator that determines whether the likely positive examples are from the target or source domain. We experimentally show that PADA outperforms several baseline methods, such as the naive combination of HUDA and PU learning.
Authors: Ravid Shwartz-Ziv, Yann LeCun
Deep neural networks excel in supervised learning tasks but are constrained by the need for extensive labeled data. Self-supervised learning emerges as a promising alternative, allowing models to learn without explicit labels. Information theory, and notably the information bottleneck principle, has been pivotal in shaping deep neural networks. This principle focuses on optimizing the trade-off between compression and preserving relevant information, providing a foundation for efficient network design in supervised contexts. However, its precise role and adaptation in self-supervised learning remain unclear. In this work, we scrutinize various self-supervised learning approaches from an information-theoretic perspective, introducing a unified framework that encapsulates the \textit{self-supervised information-theoretic learning problem}. We weave together existing research into a cohesive narrative, delve into contemporary self-supervised methodologies, and spotlight potential research avenues and inherent challenges. Additionally, we discuss the empirical evaluation of information-theoretic quantities and their estimation methods. Overall, this paper furnishes an exhaustive review of the intersection of information theory, self-supervised learning, and deep neural networks.
Authors: Kristina Tesch, Timo Gerkmann
In a multi-channel separation task with multiple speakers, we aim to recover all individual speech signals from the mixture. In contrast to single-channel approaches, which rely on the different spectro-temporal characteristics of the speech signals, multi-channel approaches should additionally utilize the different spatial locations of the sources for a more powerful separation especially when the number of sources increases. To enhance the spatial processing in a multi-channel source separation scenario, in this work, we propose a deep neural network (DNN) based spatially selective filter (SSF) that can be spatially steered to extract the speaker of interest by initializing a recurrent neural network layer with the target direction. We compare the proposed SSF with a common end-to-end direct separation (DS) approach trained using utterance-wise permutation invariant training (PIT), which only implicitly learns to perform spatial filtering. We show that the SSF has a clear advantage over a DS approach with the same underlying network architecture when there are more than two speakers in the mixture, which can be attributed to a better use of the spatial information. Furthermore, we find that the SSF generalizes much better to additional noise sources that were not seen during training and to scenarios with speakers positioned at a similar angle.
Authors: Zakary Georgis-Yap, Milos R. Popovic, Shehroz S. Khan
Epilepsy affects more than 50 million people worldwide, making it one of the world's most prevalent neurological diseases. The main symptom of epilepsy is seizures, which occur abruptly and can cause serious injury or death. The ability to predict the occurrence of an epileptic seizure could alleviate many risks and stresses people with epilepsy face. We formulate the problem of detecting preictal (or pre-seizure) with reference to normal EEG as a precursor to incoming seizure. To this end, we developed several supervised deep learning approaches model to identify preictal EEG from normal EEG. We further develop novel unsupervised deep learning approaches to train the models on only normal EEG, and detecting pre-seizure EEG as an anomalous event. These deep learning models were trained and evaluated on two large EEG seizure datasets in a person-specific manner. We found that both supervised and unsupervised approaches are feasible; however, their performance varies depending on the patient, approach and architecture. This new line of research has the potential to develop therapeutic interventions and save human lives.
Authors: Xiaochen Du, James K. Damewood, Jaclyn R. Lunger, Reisel Millan, Bilge Yildiz, Lin Li, Rafael Gómez-Bombarelli
Understanding material surfaces and interfaces is vital in applications like catalysis or electronics. By combining energies from electronic structure with statistical mechanics, ab initio simulations can in principle predict the structure of material surfaces as a function of thermodynamic variables. However, accurate energy simulations are prohibitive when coupled to the vast phase space that must be statistically sampled. Here, we present a bi-faceted computational loop to predict surface phase diagrams of multi-component materials that accelerates both the energy scoring and statistical sampling methods. Fast, scalable, and data-efficient machine learning interatomic potentials are trained on high-throughput density-functional theory calculations through closed-loop active learning. Markov-chain Monte Carlo sampling in the semi-grand canonical ensemble is enabled by using virtual surface sites. The predicted surfaces for GaN(0001), Si(111), and SrTiO3(001) are in agreement with past work and suggest that the proposed strategy can model complex material surfaces and discover previously unreported surface terminations.
Authors: Yunzhe Zhang, Yao Lu, Qi Xuan
Contrastive learning, a dominant self-supervised technique, emphasizes similarity in representations between augmentations of the same input and dissimilarity for different ones. Although low contrastive loss often correlates with high classification accuracy, recent studies challenge this direct relationship, spotlighting the crucial role of inductive biases. We delve into these biases from a clustering viewpoint, noting that contrastive learning creates locally dense clusters, contrasting the globally dense clusters from supervised learning. To capture this discrepancy, we introduce the "RLD (Relative Local Density)" metric. While this cluster property can hinder linear classification accuracy, leveraging a Graph Convolutional Network (GCN) based classifier mitigates this, boosting accuracy and reducing parameter requirements. The code is available \href{https://github.com/xsgxlz/How-does-Contrastive-Learning-Organize-Images/tree/main}{here}.
Authors: Sang Michael Xie, Hieu Pham, Xuanyi Dong, Nan Du, Hanxiao Liu, Yifeng Lu, Percy Liang, Quoc V. Le, Tengyu Ma, Adams Wei Yu
The mixture proportions of pretraining data domains (e.g., Wikipedia, books, web text) greatly affect language model (LM) performance. In this paper, we propose Domain Reweighting with Minimax Optimization (DoReMi), which first trains a small proxy model using group distributionally robust optimization (Group DRO) over domains to produce domain weights (mixture proportions) without knowledge of downstream tasks. We then resample a dataset with these domain weights and train a larger, full-sized model. In our experiments, we use DoReMi on a 280M-parameter proxy model to set the domain weights for training an 8B-parameter model (30x larger) more efficiently. On The Pile, DoReMi improves perplexity across all domains, even when it downweights a domain. DoReMi improves average few-shot downstream accuracy by 6.5% points over a baseline model trained using The Pile's default domain weights and reaches the baseline accuracy with 2.6x fewer training steps. On the GLaM dataset, DoReMi, which has no knowledge of downstream tasks, even matches the performance of using domain weights tuned on downstream tasks.
Authors: Ben Tu, Nikolas Kantas, Robert M. Lee, Behrang Shafei
The goal of multi-objective optimization is to identify a collection of points which describe the best possible trade-offs between the multiple objectives. In order to solve this vector-valued optimization problem, practitioners often appeal to the use of scalarization functions in order to transform the multi-objective problem into a collection of single-objective problems. This set of scalarized problems can then be solved using traditional single-objective optimization techniques. In this work, we formalise this convention into a general mathematical framework. We show how this strategy effectively recasts the original multi-objective optimization problem into a single-objective optimization problem defined over sets. An appropriate class of objective functions for this new problem is the R2 utility function, which is defined as a weighted integral over the scalarized optimization problems. We show that this utility function is a monotone and submodular set function, which can be optimised effectively using greedy optimization algorithms. We analyse the performance of these greedy algorithms both theoretically and empirically. Our analysis largely focusses on Bayesian optimization, which is a popular probabilistic framework for black-box optimization.
Authors: Guillermo Ortiz-Jimenez, Alessandro Favero, Pascal Frossard
Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-trained models directly in weight space: By adding the fine-tuned weights of different tasks, the model's performance can be improved on these tasks, while negating them leads to task forgetting. Yet, our understanding of the effectiveness of task arithmetic and its underlying principles remains limited. We present a comprehensive study of task arithmetic in vision-language models and show that weight disentanglement is the crucial factor that makes it effective. This property arises during pre-training and manifests when distinct directions in weight space govern separate, localized regions in function space associated with the tasks. Notably, we show that fine-tuning models in their tangent space by linearizing them amplifies weight disentanglement. This leads to substantial performance improvements across multiple task arithmetic benchmarks and diverse models. Building on these findings, we provide theoretical and empirical analyses of the neural tangent kernel (NTK) of these models and establish a compelling link between task arithmetic and the spatial localization of the NTK eigenfunctions. Overall, our work uncovers novel insights into the fundamental mechanisms of task arithmetic and offers a more reliable and effective approach to edit pre-trained models through the NTK linearization.
Authors: Abbavaram Gowtham Reddy, Saketh Bachu, Saloni Dash, Charchit Sharma, Amit Sharma, Vineeth N Balasubramanian
Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the data generation process. In this paper, we formally analyze how confounding biases impact downstream classifiers and present a causal viewpoint to the solutions based on counterfactual data augmentation. We explore how removing confounding biases serves as a means to learn invariant features, ultimately aiding in generalization beyond the observed data distribution. Additionally, we present a straightforward yet powerful algorithm for generating counterfactual images, which effectively mitigates the influence of confounding effects on downstream classifiers. Through experiments on MNIST variants and the CelebA datasets, we demonstrate how our simple augmentation method helps existing state-of-the-art methods achieve good results.
Authors: Alexander Isenko, Ruben Mayer, Hans-Arno Jacobsen
Training deep learning models in the cloud or on dedicated hardware is expensive. A more cost-efficient option are hyperscale clouds offering spot instances, a cheap but ephemeral alternative to on-demand resources. As spot instance availability can change depending on the time of day, continent, and cloud provider, it could be more cost-efficient to distribute resources over the world. Still, it has not been investigated whether geo-distributed, data-parallel spot deep learning training could be a more cost-efficient alternative to centralized training.
This paper aims to answer the question: Can deep learning models be cost-efficiently trained on a global market of spot VMs spanning different data centers and cloud providers? To provide guidance, we extensively evaluate the cost and throughput implications of training in different zones, continents, and clouds for representative CV, NLP and ASR models. To expand the current training options further, we compare the scalability potential for hybrid-cloud scenarios by adding cloud resources to on-premise hardware to improve training throughput. Finally, we show how leveraging spot instance pricing enables a new cost-efficient way to train models with multiple cheap VMs, trumping both more centralized and powerful hardware and even on-demand cloud offerings at competitive prices.
Authors: Donald Loveland, Jiong Zhu, Mark Heimann, Benjamin Fish, Michael T. Schaub, Danai Koutra
Graph Neural Network (GNN) research has highlighted a relationship between high homophily (i.e., the tendency of nodes of the same class to connect) and strong predictive performance in node classification. However, recent work has found the relationship to be more nuanced, demonstrating that simple GNNs can learn in certain heterophilous settings. To resolve these conflicting findings and align closer to real-world datasets, we go beyond the assumption of a global graph homophily level and study the performance of GNNs when the local homophily level of a node deviates from the global homophily level. Through theoretical and empirical analysis, we systematically demonstrate how shifts in local homophily can introduce performance degradation, leading to performance discrepancies across local homophily levels. We ground the practical implications of this work through granular analysis on five real-world datasets with varying global homophily levels, demonstrating that (a) GNNs can fail to generalize to test nodes that deviate from the global homophily of a graph, and (b) high local homophily does not necessarily confer high performance for a node. We further show that GNNs designed for globally heterophilous graphs can alleviate performance discrepancy by improving performance across local homophily levels, offering a new perspective on how these GNNs achieve stronger global performance.
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: Ziqian Zhong, Ziming Liu, Max Tegmark, Jacob Andreas
Do neural networks, trained on well-understood algorithmic tasks, reliably rediscover known algorithms for solving those tasks? Several recent studies, on tasks ranging from group arithmetic to in-context linear regression, have suggested that the answer is yes. Using modular addition as a prototypical problem, we show that algorithm discovery in neural networks is sometimes more complex. Small changes to model hyperparameters and initializations can induce the discovery of qualitatively different algorithms from a fixed training set, and even parallel implementations of multiple such algorithms. Some networks trained to perform modular addition implement a familiar Clock algorithm; others implement a previously undescribed, less intuitive, but comprehensible procedure which we term the Pizza algorithm, or a variety of even more complex procedures. Our results show that even simple learning problems can admit a surprising diversity of solutions, motivating the development of new tools for characterizing the behavior of neural networks across their algorithmic phase space.
Authors: Jonas Jürß, Dulhan Jayalath, Petar Veličković
Learning models that execute algorithms can enable us to address a key problem in deep learning: generalizing to out-of-distribution data. However, neural networks are currently unable to execute recursive algorithms because they do not have arbitrarily large memory to store and recall state. To address this, we (1) propose a way to augment graph neural networks (GNNs) with a stack, and (2) develop an approach for capturing intermediate algorithm trajectories that improves algorithmic alignment with recursive algorithms over previous methods. The stack allows the network to learn to store and recall a portion of the state of the network at a particular time, analogous to the action of a call stack in a recursive algorithm. This augmentation permits the network to reason recursively. We empirically demonstrate that our proposals significantly improve generalization to larger input graphs over prior work on depth-first search (DFS).
Authors: Zhihong Deng, Jing Jiang, Guodong Long, Chengqi Zhang
Reinforcement learning is an essential paradigm for solving sequential decision problems under uncertainty. Despite many remarkable achievements in recent decades, applying reinforcement learning methods in the real world remains challenging. One of the main obstacles is that reinforcement learning agents lack a fundamental understanding of the world and must therefore learn from scratch through numerous trial-and-error interactions. They may also face challenges in providing explanations for their decisions and generalizing the acquired knowledge. Causality, however, offers a notable advantage as it can formalize knowledge in a systematic manner and leverage invariance for effective knowledge transfer. This has led to the emergence of causal reinforcement learning, a subfield of reinforcement learning that seeks to enhance existing algorithms by incorporating causal relationships into the learning process. In this survey, we comprehensively review the literature on causal reinforcement learning. We first introduce the basic concepts of causality and reinforcement learning, and then explain how causality can address core challenges in non-causal reinforcement learning. We categorize and systematically review existing causal reinforcement learning approaches based on their target problems and methodologies. Finally, we outline open issues and future directions in this emerging field.
Authors: Denis C. Ilie-Ablachim, Bogdan Dumitrescu, Cristian Rusu
This paper presents a kernelized version of the t-SNE algorithm, capable of mapping high-dimensional data to a low-dimensional space while preserving the pairwise distances between the data points in a non-Euclidean metric. This can be achieved using a kernel trick only in the high dimensional space or in both spaces, leading to an end-to-end kernelized version. The proposed kernelized version of the t-SNE algorithm can offer new views on the relationships between data points, which can improve performance and accuracy in particular applications, such as classification problems involving kernel methods. The differences between t-SNE and its kernelized version are illustrated for several datasets, showing a neater clustering of points belonging to different classes.
Authors: Leander Girrbach, Anders Christensen, Ole Winther, Zeynep Akata, A. Sophia Koepke
Neural Persistence is a prominent measure for quantifying neural network complexity, proposed in the emerging field of topological data analysis in deep learning. In this work, however, we find both theoretically and empirically that the variance of network weights and spatial concentration of large weights are the main factors that impact neural persistence. Whilst this captures useful information for linear classifiers, we find that no relevant spatial structure is present in later layers of deep neural networks, making neural persistence roughly equivalent to the variance of weights. Additionally, the proposed averaging procedure across layers for deep neural networks does not consider interaction between layers. Based on our analysis, we propose an extension of the filtration underlying neural persistence to the whole neural network instead of single layers, which is equivalent to calculating neural persistence on one particular matrix. This yields our deep graph persistence measure, which implicitly incorporates persistent paths through the network and alleviates variance-related issues through standardisation. Code is available at https://github.com/ExplainableML/Deep-Graph-Persistence .
Authors: Marcel Kollovieh, Abdul Fatir Ansari, Michael Bohlke-Schneider, Jasper Zschiegner, Hao Wang, Yuyang Wang
Diffusion models have achieved state-of-the-art performance in generative modeling tasks across various domains. Prior works on time series diffusion models have primarily focused on developing conditional models tailored to specific forecasting or imputation tasks. In this work, we explore the potential of task-agnostic, unconditional diffusion models for several time series applications. We propose TSDiff, an unconditionally-trained diffusion model for time series. Our proposed self-guidance mechanism enables conditioning TSDiff for downstream tasks during inference, without requiring auxiliary networks or altering the training procedure. We demonstrate the effectiveness of our method on three different time series tasks: forecasting, refinement, and synthetic data generation. First, we show that TSDiff is competitive with several task-specific conditional forecasting methods (predict). Second, we leverage the learned implicit probability density of TSDiff to iteratively refine the predictions of base forecasters with reduced computational overhead over reverse diffusion (refine). Notably, the generative performance of the model remains intact -- downstream forecasters trained on synthetic samples from TSDiff outperform forecasters that are trained on samples from other state-of-the-art generative time series models, occasionally even outperforming models trained on real data (synthesize).
Authors: Juyoung Yun
In this research, we address critical concerns related to the numerical instability observed in 16-bit computations of machine learning models. Such instability, particularly when employing popular optimization algorithms like Adam, often leads to unstable training of deep neural networks. This not only disrupts the learning process but also poses significant challenges in deploying dependable models in real-world applications. Our investigation identifies the epsilon hyperparameter as the primary source of this instability. A nuanced exploration reveals that subtle adjustments to epsilon within 16-bit computations can enhance the numerical stability of Adam, enabling more stable training of 16-bit neural networks. We propose a novel, dependable approach that leverages updates from the Adam optimizer to bolster the stability of the learning process. Our contributions provide deeper insights into optimization challenges in low-precision computations and offer solutions to ensure the stability of deep neural network training, paving the way for their dependable use in various applications.
Authors: Yongcheng Yao, Junru Zhong, Liping Zhang, Sheheryar Khan, Weitian Chen
We introduce CartiMorph, a framework for automated knee articular cartilage morphometrics. It takes an image as input and generates quantitative metrics for cartilage subregions, including the percentage of full-thickness cartilage loss (FCL), mean thickness, surface area, and volume. CartiMorph leverages the power of deep learning models for hierarchical image feature representation. Deep learning models were trained and validated for tissue segmentation, template construction, and template-to-image registration. We established methods for surface-normal-based cartilage thickness mapping, FCL estimation, and rule-based cartilage parcellation. Our cartilage thickness map showed less error in thin and peripheral regions. We evaluated the effectiveness of the adopted segmentation model by comparing the quantitative metrics obtained from model segmentation and those from manual segmentation. The root-mean-squared deviation of the FCL measurements was less than 8%, and strong correlations were observed for the mean thickness (Pearson's correlation coefficient $\rho \in [0.82,0.97]$), surface area ($\rho \in [0.82,0.98]$) and volume ($\rho \in [0.89,0.98]$) measurements. We compared our FCL measurements with those from a previous study and found that our measurements deviated less from the ground truths. We observed superior performance of the proposed rule-based cartilage parcellation method compared with the atlas-based approach. CartiMorph has the potential to promote imaging biomarkers discovery for knee osteoarthritis.
Authors: Lukas Rauch, Raphael Schwinger, Moritz Wirth, Bernhard Sick, Sven Tomforde, Christoph Scholz
We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL). Leveraging transformer models, we aim to bypass traditional spectrogram conversions, enabling direct raw audio processing. ActiveBird2Vec is set to generate high-quality bird sound representations through SSL, potentially accelerating the assessment of environmental changes and decision-making processes for wind farms. Additionally, we seek to utilize the wide variety of bird vocalizations through DAL, reducing the reliance on extensively labeled datasets by human experts. We plan to curate a comprehensive set of tasks through Huggingface Datasets, enhancing future comparability and reproducibility of bioacoustic research. A comparative analysis between various transformer models will be conducted to evaluate their proficiency in bird sound recognition tasks. We aim to accelerate the progression of avian bioacoustic research and contribute to more effective conservation strategies.
Authors: Mikołaj Spytek, Mateusz Krzyziński, Sophie Hanna Langbein, Hubert Baniecki, Marvin N. Wright, Przemysław Biecek
Due to their flexibility and superior performance, machine learning models frequently complement and outperform traditional statistical survival models. However, their widespread adoption is hindered by a lack of user-friendly tools to explain their internal operations and prediction rationales. To tackle this issue, we introduce the survex R package, which provides a cohesive framework for explaining any survival model by applying explainable artificial intelligence techniques. The capabilities of the proposed software encompass understanding and diagnosing survival models, which can lead to their improvement. By revealing insights into the decision-making process, such as variable effects and importances, survex enables the assessment of model reliability and the detection of biases. Thus, transparency and responsibility may be promoted in sensitive areas, such as biomedical research and healthcare applications.
Authors: Caroline Mazini Rodrigues (LIGM, LRDE), Nicolas Boutry (LRDE), Laurent Najman (LIGM)
Providing interpretability of deep-learning models to non-experts, while fundamental for a responsible real-world usage, is challenging. Attribution maps from xAI techniques, such as Integrated Gradients, are a typical example of a visualization technique containing a high level of information, but with difficult interpretation. In this paper, we propose two methods, Maximum Activation Groups Extraction (MAGE) and Multiscale Interpretable Visualization (Ms-IV), to explain the model's decision, enhancing global interpretability. MAGE finds, for a given CNN, combinations of features which, globally, form a semantic meaning, that we call concepts. We group these similar feature patterns by clustering in ``concepts'', that we visualize through Ms-IV. This last method is inspired by Occlusion and Sensitivity analysis (incorporating causality), and uses a novel metric, called Class-aware Order Correlation (CaOC), to globally evaluate the most important image regions according to the model's decision space. We compare our approach to xAI methods such as LIME and Integrated Gradients. Experimental results evince the Ms-IV higher localization and faithfulness values. Finally, qualitative evaluation of combined MAGE and Ms-IV demonstrates humans' ability to agree, based on the visualization, with the decision of clusters' concepts; and, to detect, among a given set of networks, the existence of bias.
Authors: Yake Wei, Ruoxuan Feng, Zihe Wang, Di Hu
One primary topic of multi-modal learning is to jointly incorporate heterogeneous information from different modalities. However, most models often suffer from unsatisfactory multi-modal cooperation, which could not jointly utilize all modalities well. Some methods are proposed to identify and enhance the worse learnt modality, but are often hard to provide the fine-grained observation of multi-modal cooperation at sample-level with theoretical support. Hence, it is essential to reasonably observe and improve the fine-grained cooperation between modalities, especially when facing realistic scenarios where the modality discrepancy could vary across different samples. To this end, we introduce a fine-grained modality valuation metric to evaluate the contribution of each modality at sample-level. Via modality valuation, we regretfully observe that the multi-modal model tends to rely on one specific modality, resulting in other modalities being low-contributing. We further analyze this issue and improve cooperation between modalities by enhancing the discriminative ability of low-contributing modalities in a targeted manner. Overall, our methods reasonably observe the fine-grained uni-modal contribution at sample-level and achieve considerable improvement on different multi-modal models.
Authors: Raghav Jumade, Nicolas PD Sawaya
Though there has been substantial progress in developing quantum algorithms to study classical datasets, the cost of simply loading classical data is an obstacle to quantum advantage. When the amplitude encoding is used, loading an arbitrary classical vector requires up to exponential circuit depths with respect to the number of qubits. Here, we address this "input problem" with two contributions. First, we introduce a circuit compilation method based on tensor network (TN) theory. Our method -- AMLET (Automatic Multi-layer Loader Exploiting TNs) -- proceeds via careful construction of a specific TN topology and can be tailored to arbitrary circuit depths. Second, we perform numerical experiments on real-world classical data from four distinct areas: finance, images, fluid mechanics, and proteins. To the best of our knowledge, this is the broadest numerical analysis to date of loading classical data into a quantum computer. Consistent with other recent work in this area, the required circuit depths are often several orders of magnitude lower than the exponentially-scaling general loading algorithm would require. Besides introducing a more efficient loading algorithm, this work demonstrates that many classical datasets are loadable in depths that are much shorter than previously expected, which has positive implications for speeding up classical workloads on quantum computers.
Authors: Avital Shafran, Ilia Shumailov, Murat A. Erdogdu, Nicolas Papernot
Model extraction attacks are designed to steal trained models with only query access, as is often provided through APIs that ML-as-a-Service providers offer. ML models are expensive to train, in part because data is hard to obtain, and a primary incentive for model extraction is to acquire a model while incurring less cost than training from scratch. Literature on model extraction commonly claims or presumes that the attacker is able to save on both data acquisition and labeling costs. We show that the attacker often does not. This is because current attacks implicitly rely on the adversary being able to sample from the victim model's data distribution. We thoroughly evaluate factors influencing the success of model extraction. We discover that prior knowledge of the attacker, i.e. access to in-distribution data, dominates other factors like the attack policy the adversary follows to choose which queries to make to the victim model API. Thus, an adversary looking to develop an equally capable model with a fixed budget has little practical incentive to perform model extraction, since for the attack to work they need to collect in-distribution data, saving only on the cost of labeling. With low labeling costs in the current market, the usefulness of such attacks is questionable. Ultimately, we demonstrate that the effect of prior knowledge needs to be explicitly decoupled from the attack policy. To this end, we propose a benchmark to evaluate attack policy directly.
Authors: Zhoubo Li, Ningyu Zhang, Yunzhi Yao, Mengru Wang, Xi Chen, Huajun Chen
As the cost associated with fine-tuning Large Language Models (LLMs) continues to rise, recent research efforts have pivoted towards developing methodologies to edit implicit knowledge embedded within LLMs. Yet, there's still a dark cloud lingering overhead -- will knowledge editing trigger butterfly effect? since it is still unclear whether knowledge editing might introduce side effects that pose potential risks or not. This paper pioneers the investigation into the potential pitfalls associated with knowledge editing for LLMs. To achieve this, we introduce new benchmark datasets and propose innovative evaluation metrics. Our results underline two pivotal concerns: (1) Knowledge Conflict: Editing groups of facts that logically clash can magnify the inherent inconsistencies in LLMs-a facet neglected by previous methods. (2) Knowledge Distortion: Altering parameters with the aim of editing factual knowledge can irrevocably warp the innate knowledge structure of LLMs. Experimental results vividly demonstrate that knowledge editing might inadvertently cast a shadow of unintended consequences on LLMs, which warrant attention and efforts for future works. Code is available at https://github.com/zjunlp/PitfallsKnowledgeEditing.
Authors: Shengyu Mao, Ningyu Zhang, Xiaohan Wang, Mengru Wang, Yunzhi Yao, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen
This paper introduces an innovative task focused on editing the personality traits of Large Language Models (LLMs). This task seeks to adjust the models' responses to opinion-related questions on specified topics since an individual's personality often manifests in the form of their expressed opinions, thereby showcasing different personality traits. Specifically, we construct a new benchmark dataset PersonalityEdit to address this task. Drawing on the theory in Social Psychology, we isolate three representative traits, namely Neuroticism, Extraversion, and Agreeableness, as the foundation for our benchmark. We then gather data using GPT-4, generating responses that not only align with a specified topic but also embody the targeted personality trait. We conduct comprehensive experiments involving various baselines and discuss the representation of personality behavior in LLMs. Our intriguing findings uncover potential challenges of the proposed task, illustrating several remaining issues. We anticipate that our work can provide the NLP community with insights. Code and datasets will be released at https://github.com/zjunlp/EasyEdit.
Authors: Jianchao Lu, Yuzhe Tian, Yang Zhang, Jiaqi Ge, Quan Z. Sheng, Xi Zheng
Brain-Computer Interfaces (BCIs) are a groundbreaking technology for interacting with external devices using brain signals. Despite advancements, electroencephalogram (EEG)-based Motor Imagery (MI) tasks face challenges like amplitude and phase variability, and complex spatial correlations, with a need for smaller model size and faster inference. This study introduces the LGL-BCI framework, employing a Geometric Deep Learning Framework for EEG processing in non-Euclidean metric spaces, particularly the Symmetric Positive Definite (SPD) Manifold space. LGL-BCI offers robust EEG data representation and captures spatial correlations. We propose an EEG channel selection solution via a feature decomposition algorithm to reduce SPD matrix dimensionality, with a lossless transformation boosting inference speed. Extensive experiments show LGL-BCI's superior accuracy and efficiency compared to current solutions, highlighting geometric deep learning's potential in MI-BCI applications. The efficiency, assessed on two public EEG datasets and two real-world EEG devices, significantly outperforms the state-of-the-art solution in accuracy ($82.54\%$ versus $62.22\%$) with fewer parameters (64.9M compared to 183.7M).
Authors: Jina Lee, Youngtaek Hong, Dawun Jeong, Yeonggul Jang, Sihyeon Jeong, Taekgeun Jung, Yeonyee E. Yoon, Inki Moon, Seung-Ah Lee, Hyuk-Jae Chang
Radiomics, a medical imaging technique, extracts quantitative handcrafted features from images to predict diseases. Harmonization in those features ensures consistent feature extraction across various imaging devices and protocols. Methods for harmonization include standardized imaging protocols, statistical adjustments, and evaluating feature robustness. Myocardial diseases such as Left Ventricular Hypertrophy (LVH) and Hypertensive Heart Disease (HHD) are diagnosed via echocardiography, but variable imaging settings pose challenges. Harmonization techniques are crucial for applying handcrafted features in disease diagnosis in such scenario. Self-supervised learning (SSL) enhances data understanding within limited datasets and adapts to diverse data settings. ConvNeXt-V2 integrates convolutional layers into SSL, displaying superior performance in various tasks. This study focuses on convolutional filters within SSL, using them as preprocessing to convert images into feature maps for handcrafted feature harmonization. Our proposed method excelled in harmonization evaluation and exhibited superior LVH classification performance compared to existing methods.
Authors: Zhenyu Tao, Wei Xu, Xiaohu You
The proliferation of diverse wireless services in 5G and beyond has led to the emergence of network slicing technologies. Among these, admission control plays a crucial role in achieving service-oriented optimization goals through the selective acceptance of service requests. Although deep reinforcement learning (DRL) forms the foundation in many admission control approaches thanks to its effectiveness and flexibility, initial instability with excessive convergence delay of DRL models hinders their deployment in real-world networks. We propose a digital twin (DT) accelerated DRL solution to address this issue. Specifically, we first formulate the admission decision-making process as a semi-Markov decision process, which is subsequently simplified into an equivalent discrete-time Markov decision process to facilitate the implementation of DRL methods. A neural network-based DT is established with a customized output layer for queuing systems, trained through supervised learning, and then employed to assist the training phase of the DRL model. Extensive simulations show that the DT-accelerated DRL improves resource utilization by over 40% compared to the directly trained state-of-the-art dueling deep Q-learning model. This improvement is achieved while preserving the model's capability to optimize the long-term rewards of the admission process.
Authors: Róbert Csordás, Kazuki Irie, Jürgen Schmidhuber
How to reduce compute and memory requirements of neural networks (NNs) without sacrificing performance? Many recent works use sparse Mixtures of Experts (MoEs) to build resource-efficient large language models (LMs). Here we introduce several novel perspectives on MoEs, presenting a general framework that unifies various methods to approximate two-layer NNs (e.g., feedforward blocks of Transformers), including product-key memories (PKMs). Leveraging insights from this framework, we propose methods to improve both MoEs and PKMs. Unlike prior work that compares MoEs with dense baselines under the compute-equal condition, our evaluation condition is parameter-equal, which is crucial to properly evaluate LMs. We show that our MoEs are competitive with the dense Transformer-XL on both the WikiText-103 and enwiki8 datasets at two different scales, while being much more resource efficient. This demonstrates that MoEs are relevant not only to extremely large LMs but also to any-scale resource-efficient LMs. Our code is public.
Authors: S. M. Fazle Rabby Labib, Joyanta Jyoti Mondal, Meem Arafat Manab
Deep neural networks (DNNs) have significantly advanced various domains, but their vulnerability to adversarial attacks poses serious concerns. Understanding these vulnerabilities and developing effective defense mechanisms is crucial. DeepFool, an algorithm proposed by Moosavi-Dezfooli et al. (2016), finds minimal perturbations to misclassify input images. However, DeepFool lacks a targeted approach, making it less effective in specific attack scenarios. Also, in previous related works, researchers primarily focus on success, not considering how much an image is getting distorted; the integrity of the image quality, and the confidence level to misclassifying. So, in this paper, we propose Enhanced Targeted DeepFool, an augmented version of DeepFool that allows targeting specific classes for misclassification and also introduce a minimum confidence score requirement hyperparameter to enhance flexibility. Our experiments demonstrate the effectiveness and efficiency of the proposed method across different deep neural network architectures while preserving image integrity as much and perturbation rate as less as possible. By using our approach, the behavior of models can be manipulated arbitrarily using the perturbed images, as we can specify both the target class and the associated confidence score, unlike other DeepFool-derivative works, such as Targeted DeepFool by Gajjar et al. (2022). Results show that one of the deep convolutional neural network architectures, AlexNet, and one of the state-of-the-art model Vision Transformer exhibit high robustness to getting fooled. This approach can have larger implication, as our tuning of confidence level can expose the robustness of image recognition models. Our code will be made public upon acceptance of the paper.
Authors: Weiye Zhao, Feihan Li, Yifan Sun, Rui Chen, Tianhao Wei, Changliu Liu
In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily emphasize improvement in expected performance, lacking the ability to control over the worst-case performance outcomes. To address this limitation, we introduce a novel objective function; by optimizing which, it will lead to guaranteed monotonic improvement in the lower bound of near-total performance samples (absolute performance). Considering this groundbreaking theoretical advancement, we then refine this theoretically grounded algorithm through a series of approximations, resulting in a practical solution called Absolute Policy Optimization (APO). Our experiments demonstrate the effectiveness of our approach across challenging continuous control benchmark tasks and extend its applicability to mastering Atari games. Our findings reveal that APO significantly outperforms state-of-the-art policy gradient algorithms, resulting in substantial improvements in both expected performance and worst-case performance.
Authors: Mikhail Kudriavtsev, Marija Bezbradica, Andrew McCarren
Association rule mining techniques can generate a large volume of sequential data when implemented on transactional databases. Extracting insights from a large set of association rules has been found to be a challenging process. When examining a ruleset, the fundamental question is how to summarise and represent meaningful mined knowledge efficiently. Many algorithms and strategies have been developed to address issue of knowledge extraction; however, the effectiveness of this process can be limited by the data structures. A better data structure can sufficiently affect the speed of the knowledge extraction process. This paper proposes a novel data structure, called the Trie of rules, for storing a ruleset that is generated by association rule mining. The resulting data structure is a prefix-tree graph structure made of pre-mined rules. This graph stores the rules as paths within the prefix-tree in a way that similar rules overlay each other. Each node in the tree represents a rule where a consequent is this node, and an antecedent is a path from this node to the root of the tree. The evaluation showed that the proposed representation technique is promising. It compresses a ruleset with almost no data loss and benefits in terms of time for basic operations such as searching for a specific rule and sorting, which is the base for many knowledge discovery methods. Moreover, our method demonstrated a significant improvement in traversing time, achieving an 8-fold increase compared to traditional data structures.
Authors: Nitish Joshi, Javier Rando, Abulhair Saparov, Najoung Kim, He He
Large Language Models (LLMs) are trained on vast amounts of text from the internet, which contains both factual and misleading information about the world. Can language models discern truth from falsehood in this contradicting data? Expanding on the view that LLMs can model different communicative agents, we present the persona hypothesis: LLMs can cluster agents into personas using common features of their generations. For instance, a truthful persona is a group of agents that are likely to produce truthful text and that share similar features like formal writing styles and scientific references. By modeling this persona, LLMs can generalize truthfulness beyond the specific contexts in which each agent generated the training text. For example, the model can infer that the agent ``Wikipedia'' will behave truthfully on topics that were only generated by ``Science'' because they both belong to the truthful persona. We show evidence for the persona hypothesis via two observations: (1) we can probe whether a model's answer will be truthful before it is generated; (2) finetuning a model on a set of facts improves its truthfulness on unseen topics. Next, using arithmetics as a synthetic environment, we show that language models can separate true and false statements, and generalize truthfulness across agents; but only if agents in the training data share a truthful generative process that enables the creation of a truthful persona. Overall, our findings suggest that models can exploit hierarchical structures in the data to learn abstract concepts like truthfulness.
Authors: Ziqi Zhang, Xiao Xiong, Zifeng Zhuang, Jinxin Liu, Donglin Wang
Offline-to-online RL can make full use of pre-collected offline datasets to initialize policies, resulting in higher sample efficiency and better performance compared to only using online algorithms alone for policy training. However, direct fine-tuning of the pre-trained policy tends to result in sub-optimal performance. A primary reason is that conservative offline RL methods diminish the agent's capability of exploration, thereby impacting online fine-tuning performance. To encourage agent's exploration during online fine-tuning and enhance the overall online fine-tuning performance, we propose a generalized reward augmentation method called Sample Efficient Reward Augmentation (SERA). Specifically, SERA encourages agent to explore by computing Q conditioned entropy as intrinsic reward. The advantage of SERA is that it can extensively utilize offline pre-trained Q to encourage agent uniformly coverage of state space while considering the imbalance between the distributions of high-value and low-value states. Additionally, SERA can be effortlessly plugged into various RL algorithms to improve online fine-tuning and ensure sustained asymptotic improvement. Moreover, extensive experimental results demonstrate that when conducting offline-to-online problems, SERA consistently and effectively enhances the performance of various offline algorithms.
Authors: Cesare Donati, Martina Mammarella, Fabrizio Dabbene, Carlo Novara, Constantino Lagoa
The aim of this paper is to present a novel physics-based framework for the identification of dynamical systems, in which the physical and structural insights are reflected directly into a backpropagation-based learning algorithm. The main result is a method to compute in closed form the gradient of a multi-step loss function, while enforcing physical properties and constraints. The derived algorithm has been exploited to identify the unknown inertia matrix of a space debris, and the results show the reliability of the method in capturing the physical adherence of the estimated parameters.
Authors: Jiarong Xu, Renhong Huang, Xin Jiang, Yuxuan Cao, Carl Yang, Chunping Wang, Yang Yang
Pre-training on graph neural networks (GNNs) aims to learn transferable knowledge for downstream tasks with unlabeled data, and it has recently become an active research area. The success of graph pre-training models is often attributed to the massive amount of input data. In this paper, however, we identify the curse of big data phenomenon in graph pre-training: more training data do not necessarily lead to better downstream performance. Motivated by this observation, we propose a better-with-less framework for graph pre-training: fewer, but carefully chosen data are fed into a GNN model to enhance pre-training. The proposed pre-training pipeline is called the data-active graph pre-training (APT) framework, and is composed of a graph selector and a pre-training model. The graph selector chooses the most representative and instructive data points based on the inherent properties of graphs as well as predictive uncertainty. The proposed predictive uncertainty, as feedback from the pre-training model, measures the confidence level of the model in the data. When fed with the chosen data, on the other hand, the pre-training model grasps an initial understanding of the new, unseen data, and at the same time attempts to remember the knowledge learned from previous data. Therefore, the integration and interaction between these two components form a unified framework (APT), in which graph pre-training is performed in a progressive and iterative way. Experiment results show that the proposed APT is able to obtain an efficient pre-training model with fewer training data and better downstream performance.
Authors: Kai Yan, Alexander G. Schwing, Yu-xiong Wang
In real-world scenarios, arbitrary interactions with the environment can often be costly, and actions of expert demonstrations are not always available. To reduce the need for both, Offline Learning from Observations (LfO) is extensively studied, where the agent learns to solve a task with only expert states and \textit{task-agnostic} non-expert state-action pairs. The state-of-the-art DIstribution Correction Estimation (DICE) methods minimize the state occupancy divergence between the learner and expert policies. However, they are limited to either $f$-divergences (KL and $\chi^2$) or Wasserstein distance with Rubinstein duality, the latter of which constrains the underlying distance metric crucial to the performance of Wasserstein-based solutions. To address this problem, we propose Primal Wasserstein DICE (PW-DICE), which minimizes the primal Wasserstein distance between the expert and learner state occupancies with a pessimistic regularizer and leverages a contrastively learned distance as the underlying metric for the Wasserstein distance. Theoretically, we prove that our framework is a generalization of the state-of-the-art, SMODICE, and unifies $f$-divergence and Wasserstein minimization. Empirically, we find that PW-DICE improves upon several state-of-the-art methods on multiple testbeds.
Authors: Di Luo, David D. Dai, Liang Fu
We develop a pairing-based graph neural network for simulating quantum many-body systems. Our architecture augments a BCS-type geminal wavefunction with a generalized pair amplitude parameterized by a graph neural network. Variational Monte Carlo with our neural network simultaneously provides an accurate, flexible, and scalable method for simulating many-electron systems. We apply this method to two-dimensional semiconductor electron-hole bilayers and obtain accurate results on a variety of interaction-induced phases, including the exciton Bose-Einstein condensate, electron-hole superconductor, and bilayer Wigner crystal. Our study demonstrates the potential of physically-motivated neural network wavefunctions for quantum materials simulations.
Authors: Hengyuan Hu, Suvir Mirchandani, Dorsa Sadigh
Despite the considerable potential of reinforcement learning (RL), robotics control tasks predominantly rely on imitation learning (IL) owing to its better sample efficiency. However, given the high cost of collecting extensive demonstrations, RL is still appealing if it can utilize limited imitation data for efficient autonomous self-improvement. Existing RL methods that utilize demonstrations either initialize the replay buffer with demonstrations and oversample them during RL training, which does not benefit from the generalization potential of modern IL methods, or pretrain the RL policy with IL on the demonstrations, which requires additional mechanisms to prevent catastrophic forgetting during RL fine-tuning. We propose imitation bootstrapped reinforcement learning (IBRL), a novel framework that first trains an IL policy on a limited number of demonstrations and then uses it to propose alternative actions for both online exploration and target value bootstrapping. IBRL achieves SoTA performance and sample efficiency on 7 challenging sparse reward continuous control tasks in simulation while learning directly from pixels. As a highlight of our method, IBRL achieves $6.4\times$ higher success rate than RLPD, a strong method that combines the idea of oversampling demonstrations with modern RL improvements, under the budget of 10 demos and 100K interactions in the challenging PickPlaceCan task in the Robomimic benchmark.
Authors: Elisa Warner, Joonsang Lee, William Hsu, Tanveer Syeda-Mahmood, Charles Kahn, Olivier Gevaert, Arvind Rao
Machine learning (ML) applications in medical artificial intelligence (AI) systems have shifted from traditional and statistical methods to increasing application of deep learning models. This survey navigates the current landscape of multimodal ML, focusing on its profound impact on medical image analysis and clinical decision support systems. Emphasizing challenges and innovations in addressing multimodal representation, fusion, translation, alignment, and co-learning, the paper explores the transformative potential of multimodal models for clinical predictions. It also questions practical implementation of such models, bringing attention to the dynamics between decision support systems and healthcare providers. Despite advancements, challenges such as data biases and the scarcity of "big data" in many biomedical domains persist. We conclude with a discussion on effective innovation and collaborative efforts to further the miss
Authors: Derek Lilienthal, Paul Mello, Magdalini Eirinaki, Stas Tiomkin
While recommender systems have become an integral component of the Web experience, their heavy reliance on user data raises privacy and security concerns. Substituting user data with synthetic data can address these concerns, but accurately replicating these real-world datasets has been a notoriously challenging problem. Recent advancements in generative AI have demonstrated the impressive capabilities of diffusion models in generating realistic data across various domains. In this work we introduce a Score-based Diffusion Recommendation Module (SDRM), which captures the intricate patterns of real-world datasets required for training highly accurate recommender systems. SDRM allows for the generation of synthetic data that can replace existing datasets to preserve user privacy, or augment existing datasets to address excessive data sparsity. Our method outperforms competing baselines such as generative adversarial networks, variational autoencoders, and recently proposed diffusion models in synthesizing various datasets to replace or augment the original data by an average improvement of 4.30% in Recall@$k$ and 4.65% in NDCG@$k$.
Authors: James T. Meech
We present a new high-level synthesis methodology for using large language model tools to generate hardware designs. The methodology uses exclusively open-source tools excluding the large language model. As a case study, we use our methodology to generate a permuted congruential random number generator design with a wishbone interface. We verify the functionality and quality of the random number generator design using large language model-generated simulations and the Dieharder randomness test suite. We document all the large language model chat logs, Python scripts, Verilog scripts, and simulation results used in the case study. We believe that our method of hardware design generation coupled with the open source silicon 130 nm design tools will revolutionize application-specific integrated circuit design. Our methodology significantly lowers the bar to entry when building domain-specific computing accelerators for the Internet of Things and proof of concept prototypes for later fabrication in more modern process nodes.
Authors: Swati Padmanabhan, David P. Woodruff, Qiuyi Zhang
Recent works in dimensionality reduction for regression tasks have introduced the notion of sensitivity, an estimate of the importance of a specific datapoint in a dataset, offering provable guarantees on the quality of the approximation after removing low-sensitivity datapoints via subsampling. However, fast algorithms for approximating $\ell_p$ sensitivities, which we show is equivalent to approximate $\ell_p$ regression, are known for only the $\ell_2$ setting, in which they are termed leverage scores.
In this work, we provide efficient algorithms for approximating $\ell_p$ sensitivities and related summary statistics of a given matrix. In particular, for a given $n \times d$ matrix, we compute $\alpha$-approximation to its $\ell_1$ sensitivities at the cost of $O(n/\alpha)$ sensitivity computations. For estimating the total $\ell_p$ sensitivity (i.e. the sum of $\ell_p$ sensitivities), we provide an algorithm based on importance sampling of $\ell_p$ Lewis weights, which computes a constant factor approximation to the total sensitivity at the cost of roughly $O(\sqrt{d})$ sensitivity computations. Furthermore, we estimate the maximum $\ell_1$ sensitivity, up to a $\sqrt{d}$ factor, using $O(d)$ sensitivity computations. We generalize all these results to $\ell_p$ norms for $p > 1$. Lastly, we experimentally show that for a wide class of matrices in real-world datasets, the total sensitivity can be quickly approximated and is significantly smaller than the theoretical prediction, demonstrating that real-world datasets have low intrinsic effective dimensionality.
Authors: Qiyang Li, Jason Zhang, Dibya Ghosh, Amy Zhang, Sergey Levine
Learning to solve tasks from a sparse reward signal is a major challenge for standard reinforcement learning (RL) algorithms. However, in the real world, agents rarely need to solve sparse reward tasks entirely from scratch. More often, we might possess prior experience to draw on that provides considerable guidance about which actions and outcomes are possible in the world, which we can use to explore more effectively for new tasks. In this work, we study how prior data without reward labels may be used to guide and accelerate exploration for an agent solving a new sparse reward task. We propose a simple approach that learns a reward model from online experience, labels the unlabeled prior data with optimistic rewards, and then uses it concurrently alongside the online data for downstream policy and critic optimization. This general formula leads to rapid exploration in several challenging sparse-reward domains where tabula rasa exploration is insufficient, including the AntMaze domain, Adroit hand manipulation domain, and a visual simulated robotic manipulation domain. Our results highlight the ease of incorporating unlabeled prior data into existing online RL algorithms, and the (perhaps surprising) effectiveness of doing so.
Authors: Javier Marin
In recent years, significant progress in generative AI has highlighted the important role of physics-inspired models that utilize advanced mathematical concepts based on fundamental physics principles to enhance artificial intelligence capabilities. Among these models, those based on diffusion equations have greatly improved image quality. This study aims to explore the potential uses of Maxwell-Boltzmann equation, which forms the basis of the kinetic theory of gases, and the Michaelis-Menten model in Marketing Mix Modelling (MMM) applications. We propose incorporating these equations into Hierarchical Bayesian models to analyse consumer behaviour in the context of advertising. These equation sets excel in accurately describing the random dynamics in complex systems like social interactions and consumer-advertising interactions.
Authors: Junyoung Park, Jin Kim, Hyeongjun Kwon, Ilhoon Yoon, Kwanghoon Sohn
Given the inevitability of domain shifts during inference in real-world applications, test-time adaptation (TTA) is essential for model adaptation after deployment. However, the real-world scenario of continuously changing target distributions presents challenges including catastrophic forgetting and error accumulation. Existing TTA methods for non-stationary domain shifts, while effective, incur excessive computational load, making them impractical for on-device settings. In this paper, we introduce a layer-wise auto-weighting algorithm for continual and gradual TTA that autonomously identifies layers for preservation or concentrated adaptation. By leveraging the Fisher Information Matrix (FIM), we first design the learning weight to selectively focus on layers associated with log-likelihood changes while preserving unrelated ones. Then, we further propose an exponential min-max scaler to make certain layers nearly frozen while mitigating outliers. This minimizes forgetting and error accumulation, leading to efficient adaptation to non-stationary target distribution. Experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C show our method outperforms conventional continual and gradual TTA approaches while significantly reducing computational load, highlighting the importance of FIM-based learning weight in adapting to continuously or gradually shifting target domains.
Authors: Adam J Shephard, Mostafa Jahanifar, Ruoyu Wang, Muhammad Dawood, Simon Graham, Kastytis Sidlauskas, Syed Ali Khurram, Nasir M Rajpoot, Shan E Ahmed Raza
Tumour-infiltrating lymphocytes (TILs) are considered as a valuable prognostic markers in both triple-negative and human epidermal growth factor receptor 2 (HER2) positive breast cancer. In this study, we introduce an innovative deep learning pipeline based on the Efficient-UNet architecture to predict the TILs score for breast cancer whole-slide images (WSIs). We first segment tumour and stromal regions in order to compute a tumour bulk mask. We then detect TILs within the tumour-associated stroma, generating a TILs score by closely mirroring the pathologist's workflow. Our method exhibits state-of-the-art performance in segmenting tumour/stroma areas and TILs detection, as demonstrated by internal cross-validation on the TiGER Challenge training dataset and evaluation on the final leaderboards. Additionally, our TILs score proves competitive in predicting survival outcomes within the same challenge, underscoring the clinical relevance and potential of our automated TILs scoring pipeline as a breast cancer prognostic tool.
Authors: A. Gilad Kusne, Austin McDannald, Brian DeCost
Autonomous materials research labs require the ability to combine and learn from diverse data streams. This is especially true for learning material synthesis-process-structure-property relationships, key to accelerating materials optimization and discovery as well as accelerating mechanistic understanding. We present the Synthesis-process-structure-property relAtionship coreGionalized lEarner (SAGE) algorithm. A fully Bayesian algorithm that uses multimodal coregionalization to merge knowledge across data sources to learn synthesis-process-structure-property relationships. SAGE outputs a probabilistic posterior for the relationships including the most likely relationships given the data.
Authors: Shahriar Golchin, Mihai Surdeanu
We propose the Data Contamination Quiz, a simple and effective approach to detect data contamination in large language models (LLMs) and estimate the amount of it. Specifically, we frame data contamination detection as a series of multiple-choice questions. We devise a quiz format wherein three perturbed versions of each dataset instance are created. These changes only include word-level perturbations, replacing words with their contextual synonyms, ensuring both the semantic and sentence structure remain exactly the same as the original instance. Together with the original instance, these perturbed versions constitute the choices in the quiz. Given that the only distinguishing signal among these choices is the exact wording, an LLM, when tasked with identifying the original instance from the choices, opts for the original if it has memorized it in its pre-training phase--a trait intrinsic to LLMs. A dataset partition is then marked as contaminated if the LLM's performance on the quiz surpasses what random chance suggests. Our evaluation spans seven datasets and their respective splits (train and test/validation) on two state-of-the-art LLMs: GPT-4 and GPT-3.5. While lacking access to the pre-training data, our results suggest that our approach not only enhances the detection of data contamination but also provides an accurate estimation of its extent, even when the contamination signal is weak.
Authors: Siao Tang, Xin Wang, Hong Chen, Chaoyu Guan, Zewen Wu, Yansong Tang, Wenwu Zhu
Diffusion models have achieved great success due to their remarkable generation ability. However, their high computational overhead is still a troublesome problem. Recent studies have leveraged post-training quantization (PTQ) to compress diffusion models. However, most of them only focus on unconditional models, leaving the quantization of widely used large pretrained text-to-image models, e.g., Stable Diffusion, largely unexplored. In this paper, we propose a novel post-training quantization method PCR (Progressive Calibration and Relaxing) for text-to-image diffusion models, which consists of a progressive calibration strategy that considers the accumulated quantization error across timesteps, and an activation relaxing strategy that improves the performance with negligible cost. Additionally, we demonstrate the previous metrics for text-to-image diffusion model quantization are not accurate due to the distribution gap. To tackle the problem, we propose a novel QDiffBench benchmark, which utilizes data in the same domain for more accurate evaluation. Besides, QDiffBench also considers the generalization performance of the quantized model outside the calibration dataset. Extensive experiments on Stable Diffusion and Stable Diffusion XL demonstrate the superiority of our method and benchmark. Moreover, we are the first to achieve quantization for Stable Diffusion XL while maintaining the performance.
Authors: Hao Xu, Yifei Wang, Yunrui Li, Pengyu Hong
The versatility of multimodal deep learning holds tremendous promise for advancing scientific research and practical applications. As this field continues to evolve, the collective power of cross-modal analysis promises to drive transformative innovations, leading us to new frontiers in chemical understanding and discovery. Hence, we introduce Asymmetric Contrastive Multimodal Learning (ACML) as a novel approach tailored for molecules, showcasing its potential to advance the field of chemistry. ACML harnesses the power of effective asymmetric contrastive learning to seamlessly transfer information from various chemical modalities to molecular graph representations. By combining pre-trained chemical unimodal encoders and a shallow-designed graph encoder, ACML facilitates the assimilation of coordinated chemical semantics from different modalities, leading to comprehensive representation learning with efficient training. This innovative framework enhances the interpretability of learned representations and bolsters the expressive power of graph neural networks. Through practical tasks such as isomer discrimination and uncovering crucial chemical properties for drug discovery, ACML exhibits its capability to revolutionize chemical research and applications, providing a deeper understanding of chemical semantics of different modalities.
Authors: Amanda A Howard, Sarah H Murphy, Shady E Ahmed, Panos Stinis
Physics-informed neural networks and operator networks have shown promise for effectively solving equations modeling physical systems. However, these networks can be difficult or impossible to train accurately for some systems of equations. We present a novel multifidelity framework for stacking physics-informed neural networks and operator networks that facilitates training. We successively build a chain of networks, where the output at one step can act as a low-fidelity input for training the next step, gradually increasing the expressivity of the learned model. The equations imposed at each step of the iterative process can be the same or different (akin to simulated annealing). The iterative (stacking) nature of the proposed method allows us to progressively learn features of a solution that are hard to learn directly. Through benchmark problems including a nonlinear pendulum, the wave equation, and the viscous Burgers equation, we show how stacking can be used to improve the accuracy and reduce the required size of physics-informed neural networks and operator networks.
Authors: Sara Babakniya, Zalan Fabian, Chaoyang He, Mahdi Soltanolkotabi, Salman Avestimehr
Deep learning models often suffer from forgetting previously learned information when trained on new data. This problem is exacerbated in federated learning (FL), where the data is distributed and can change independently for each user. Many solutions are proposed to resolve this catastrophic forgetting in a centralized setting. However, they do not apply directly to FL because of its unique complexities, such as privacy concerns and resource limitations. To overcome these challenges, this paper presents a framework for $\textbf{federated class incremental learning}$ that utilizes a generative model to synthesize samples from past distributions. This data can be later exploited alongside the training data to mitigate catastrophic forgetting. To preserve privacy, the generative model is trained on the server using data-free methods at the end of each task without requesting data from clients. Moreover, our solution does not demand the users to store old data or models, which gives them the freedom to join/leave the training at any time. Additionally, we introduce SuperImageNet, a new regrouping of the ImageNet dataset specifically tailored for federated continual learning. We demonstrate significant improvements compared to existing baselines through extensive experiments on multiple datasets.
Authors: Joshua Maher
We introduce a new construction of embeddings of arbitrary recursive data structures into high dimensional vectors. These embeddings provide an interpretable model for the latent state vectors of transformers. We demonstrate that these embeddings can be decoded to the original data structure when the embedding dimension is sufficiently large. This decoding algorithm has a natural implementation as a transformer. We also show that these embedding vectors can be manipulated directly to perform computations on the underlying data without decoding. As an example we present an algorithm that constructs the embedded parse tree of an embedded token sequence using only vector operations in embedding space.
Authors: Peter Belcak, Roger Wattenhofer
Language models only really need to use an exponential fraction of their neurons for individual inferences. As proof, we present UltraFastBERT, a BERT variant that uses 0.3% of its neurons during inference while performing on par with similar BERT models. UltraFastBERT selectively engages just 12 out of 4095 neurons for each layer inference. This is achieved by replacing feedforward networks with fast feedforward networks (FFFs). While no truly efficient implementation currently exists to unlock the full acceleration potential of conditional neural execution, we provide high-level CPU code achieving 78x speedup over the optimized baseline feedforward implementation, and a PyTorch implementation delivering 40x speedup over the equivalent batched feedforward inference. We publish our training code, benchmarking setup, and model weights.
Authors: Yan Cathy Hua, Paul Denny, Katerina Taskova, Jörg Wicker
Aspect-based Sentiment Analysis (ABSA) is a type of fine-grained sentiment analysis (SA) that identifies aspects and the associated opinions from a given text. In the digital era, ABSA gained increasing popularity and applications in mining opinionated text data to obtain insights and support decisions. ABSA research employs linguistic, statistical, and machine-learning approaches and utilises resources such as labelled datasets, aspect and sentiment lexicons and ontology. By its nature, ABSA is domain-dependent and can be sensitive to the impact of misalignment between the resource and application domains. However, to our knowledge, this topic has not been explored by the existing ABSA literature reviews. In this paper, we present a Systematic Literature Review (SLR) of ABSA studies with a focus on the research application domain, dataset domain, and the research methods to examine their relationships and identify trends over time. Our results suggest a number of potential systemic issues in the ABSA research literature, including the predominance of the ``product/service review'' dataset domain among the majority of studies that did not have a specific research application domain, coupled with the prevalence of dataset-reliant methods such as supervised machine learning. This review makes a number of unique contributions to the ABSA research field: 1) To our knowledge, it is the first SLR that links the research domain, dataset domain, and research method through a systematic perspective; 2) it is one of the largest scoped SLR on ABSA, with 519 eligible studies filtered from 4191 search results without time constraint; and 3) our review methodology adopted an innovative automatic filtering process based on PDF-mining, which enhanced screening quality and reliability. Suggestions and our review limitations are also discussed.
Authors: Wentao Zhang, Yilei Zhao, Shuo Sun, Jie Ying, Yonggang Xie, Zitao Song, Xinrun Wang, Bo An
Portfolio management (PM) is a fundamental financial trading task, which explores the optimal periodical reallocation of capitals into different stocks to pursue long-term profits. Reinforcement learning (RL) has recently shown its potential to train profitable agents for PM through interacting with financial markets. However, existing work mostly focuses on fixed stock pools, which is inconsistent with investors' practical demand. Specifically, the target stock pool of different investors varies dramatically due to their discrepancy on market states and individual investors may temporally adjust stocks they desire to trade (e.g., adding one popular stocks), which lead to customizable stock pools (CSPs). Existing RL methods require to retrain RL agents even with a tiny change of the stock pool, which leads to high computational cost and unstable performance. To tackle this challenge, we propose EarnMore, a rEinforcement leARNing framework with Maskable stOck REpresentation to handle PM with CSPs through one-shot training in a global stock pool (GSP). Specifically, we first introduce a mechanism to mask out the representation of the stocks outside the target pool. Second, we learn meaningful stock representations through a self-supervised masking and reconstruction process. Third, a re-weighting mechanism is designed to make the portfolio concentrate on favorable stocks and neglect the stocks outside the target pool. Through extensive experiments on 8 subset stock pools of the US stock market, we demonstrate that EarnMore significantly outperforms 14 state-of-the-art baselines in terms of 6 popular financial metrics with over 40% improvement on profit.
Authors: Jun Wang, Kaiyuan Tan, Zihe Sun, Yiannis Kantaros
Several methods have been proposed recently to learn neural network (NN) controllers for autonomous agents, with unknown and stochastic dynamics, tasked with complex missions captured by Linear Temporal Logic (LTL). Due to the sample-inefficiency of the majority of these works, compositional learning methods have been proposed decomposing the LTL specification into smaller sub-tasks. Then, separate controllers are learned and composed to satisfy the original task. A key challenge within these approaches is that they often lack safety guarantees or the provided guarantees are impractical. This paper aims to address this challenge. Particularly, we consider autonomous systems with unknown and stochastic dynamics and LTL-encoded tasks. We assume that the system is equipped with a finite set of base skills modeled by trained NN feedback controllers. Our goal is to check if there exists a temporal composition of the trained NN controllers - and if so, to compute it - that will yield a composite system behavior that satisfies the assigned LTL task with probability one. We propose a new approach that relies on a novel integration of automata theory and data-driven reachability analysis tools for NN-controlled stochastic systems. The resulting neuro-symbolic controller allows the agent to generate safe behaviors for unseen complex temporal logic tasks in a zero-shot fashion by leveraging its base skills. We show correctness of the proposed method and we provide conditions under which it is complete. To the best of our knowledge, this is the first work that designs verified temporal compositions of NN controllers for unknown and stochastic systems. Finally, we provide extensive numerical simulations and hardware experiments on robot navigation tasks to demonstrate the proposed method.
Authors: Shaunak Joshi, Raghav Gaggar
With the increase in video-sharing platforms across the internet, it is difficult for humans to moderate the data for explicit content. Hence, an automated pipeline to scan through video data for explicit content has become the need of the hour. We propose a novel pipeline that uses multi-modal deep learning to first extract the explicit segments of input videos and then summarize their content using text to determine its age appropriateness and age rating. We also evaluate our pipeline's effectiveness in the end using standard metrics.
Authors: Yuheng Ma, Hanfang Yang
In this work, we investigate the problem of public data-assisted non-interactive LDP (Local Differential Privacy) learning with a focus on non-parametric classification. Under the posterior drift assumption, we for the first time derive the mini-max optimal convergence rate with LDP constraint. Then, we present a novel approach, the locally private classification tree, which attains the mini-max optimal convergence rate. Furthermore, we design a data-driven pruning procedure that avoids parameter tuning and produces a fast converging estimator. Comprehensive experiments conducted on synthetic and real datasets show the superior performance of our proposed method. Both our theoretical and experimental findings demonstrate the effectiveness of public data compared to private data, which leads to practical suggestions for prioritizing non-private data collection.
Authors: Ilya Loshchilov
We note that decoupled weight decay regularization is a particular case of weight norm control where the target norm of weights is set to 0. Any optimization method (e.g., Adam) which uses decoupled weight decay regularization (respectively, AdamW) can be viewed as a particular case of a more general algorithm with weight norm control (respectively, AdamWN). We argue that setting the target norm of weights to 0 can be suboptimal and other target norm values can be considered. For instance, any training run where AdamW achieves a particular norm of weights can be challenged by AdamWN scheduled to achieve a comparable norm of weights. We discuss various implications of introducing weight norm control instead of weight decay.
Authors: Eli Verwimp, Rahaf Aljundi, Shai Ben-David, Matthias Bethge, Andrea Cossu, Alexander Gepperth, Tyler L. Hayes, Eyke Hüllermeier, Christopher Kanan, Dhireesha Kudithipudi, Christoph H. Lampert, Martin Mundt, Razvan Pascanu, Adrian Popescu, Andreas S. Tolias, Joost van de Weijer, Bing Liu, Vincenzo Lomonaco, Tinne Tuytelaars, Gido M. van de Ven
Continual learning is a sub-field of machine learning, which aims to allow machine learning models to continuously learn on new data, by accumulating knowledge without forgetting what was learned in the past. In this work, we take a step back, and ask: "Why should one care about continual learning in the first place?". We set the stage by surveying recent continual learning papers published at three major machine learning conferences, and show that memory-constrained settings dominate the field. Then, we discuss five open problems in machine learning, and even though they seem unrelated to continual learning at first sight, we show that continual learning will inevitably be part of their solution. These problems are model-editing, personalization, on-device learning, faster (re-)training and reinforcement learning. Finally, by comparing the desiderata from these unsolved problems and the current assumptions in continual learning, we highlight and discuss four future directions for continual learning research. We hope that this work offers an interesting perspective on the future of continual learning, while displaying its potential value and the paths we have to pursue in order to make it successful. This work is the result of the many discussions the authors had at the Dagstuhl seminar on Deep Continual Learning, in March 2023.
Authors: Ali Abbasi, Parsa Nooralinejad, Hamed Pirsiavash, Soheil Kolouri
Continual learning has gained substantial attention within the deep learning community, offering promising solutions to the challenging problem of sequential learning. Yet, a largely unexplored facet of this paradigm is its susceptibility to adversarial attacks, especially with the aim of inducing forgetting. In this paper, we introduce "BrainWash," a novel data poisoning method tailored to impose forgetting on a continual learner. By adding the BrainWash noise to a variety of baselines, we demonstrate how a trained continual learner can be induced to forget its previously learned tasks catastrophically, even when using these continual learning baselines. An important feature of our approach is that the attacker requires no access to previous tasks' data and is armed merely with the model's current parameters and the data belonging to the most recent task. Our extensive experiments highlight the efficacy of BrainWash, showcasing degradation in performance across various regularization-based continual learning methods.