-
The Need for Speed: Pruning Transformers with One Recipe arXiv.cs.LG Pub Date : 2024-03-26 Samir Khaki, Konstantinos N. Plataniotis
We introduce the $\textbf{O}$ne-shot $\textbf{P}$runing $\textbf{T}$echnique for $\textbf{I}$nterchangeable $\textbf{N}$etworks ($\textbf{OPTIN}$) framework as a tool to increase the efficiency of pre-trained transformer architectures $\textit{without requiring re-training}$. Recent works have explored improving transformer efficiency, however often incur computationally expensive re-training procedures
-
Image-based Novel Fault Detection with Deep Learning Classifiers using Hierarchical Labels arXiv.cs.LG Pub Date : 2024-03-26 Nurettin Sergin, Jiayu Huang, Tzyy-Shuh Chang, Hao Yan
One important characteristic of modern fault classification systems is the ability to flag the system when faced with previously unseen fault types. This work considers the unknown fault detection capabilities of deep neural network-based fault classifiers. Specifically, we propose a methodology on how, when available, labels regarding the fault taxonomy can be used to increase unknown fault detection
-
Empowering Data Mesh with Federated Learning arXiv.cs.LG Pub Date : 2024-03-26 Haoyuan Li, Salman Toor
The evolution of data architecture has seen the rise of data lakes, aiming to solve the bottlenecks of data management and promote intelligent decision-making. However, this centralized architecture is limited by the proliferation of data sources and the growing demand for timely analysis and processing. A new data paradigm, Data Mesh, is proposed to overcome these challenges. Data Mesh treats domains
-
Climate Downscaling: A Deep-Learning Based Super-resolution Model of Precipitation Data with Attention Block and Skip Connections arXiv.cs.LG Pub Date : 2024-03-26 Chia-Hao Chiang, Zheng-Han Huang, Liwen Liu, Hsin-Chien Liang, Yi-Chi Wang, Wan-Ling Tseng, Chao Wang, Che-Ta Chen, Ko-Chih Wang
Human activities accelerate consumption of fossil fuels and produce greenhouse gases, resulting in urgent issues today: global warming and the climate change. These indirectly cause severe natural disasters, plenty of lives suffering and huge losses of agricultural properties. To mitigate impacts on our lands, scientists are developing renewable, reusable, and clean energies and climatologists are
-
TractOracle: towards an anatomically-informed reward function for RL-based tractography arXiv.cs.LG Pub Date : 2024-03-26 Antoine Théberge, Maxime Descoteaux, Pierre-Marc Jodoin
Reinforcement learning (RL)-based tractography is a competitive alternative to machine learning and classical tractography algorithms due to its high anatomical accuracy obtained without the need for any annotated data. However, the reward functions so far used to train RL agents do not encapsulate anatomical knowledge which causes agents to generate spurious false positives tracts. In this paper,
-
Mechanistic Design and Scaling of Hybrid Architectures arXiv.cs.LG Pub Date : 2024-03-26 Michael Poli, Armin W Thomas, Eric Nguyen, Pragaash Ponnusamy, Björn Deiseroth, Kristian Kersting, Taiji Suzuki, Brian Hie, Stefano Ermon, Christopher Ré, Ce Zhang, Stefano Massaroli
The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale model training and evaluation. We set out to simplify this process by grounding it in an end-to-end mechanistic architecture design (MAD) pipeline, encompassing small-scale capability unit tests predictive of scaling laws
-
GPFL: A Gradient Projection-Based Client Selection Framework for Efficient Federated Learning arXiv.cs.LG Pub Date : 2024-03-26 Shijie Na, Yuzhi Liang, Siu-Ming Yiu
Federated learning client selection is crucial for determining participant clients while balancing model accuracy and communication efficiency. Existing methods have limitations in handling data heterogeneity, computational burdens, and independent client treatment. To address these challenges, we propose GPFL, which measures client value by comparing local and global descent directions. We also employ
-
Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms arXiv.cs.LG Pub Date : 2024-03-26 Michael Hanna, Sandro Pezzelle, Yonatan Belinkov
Many recent language model (LM) interpretability studies have adopted the circuits framework, which aims to find the minimal computational subgraph, or circuit, that explains LM behavior on a given task. Most studies determine which edges belong in a LM's circuit by performing causal interventions on each edge independently, but this scales poorly with model size. Edge attribution patching (EAP), gradient-based
-
Secure Aggregation is Not Private Against Membership Inference Attacks arXiv.cs.LG Pub Date : 2024-03-26 Khac-Hoang Ngo, Johan Östman, Giuseppe Durisi, Alexandre Graell i Amat
Secure aggregation (SecAgg) is a commonly-used privacy-enhancing mechanism in federated learning, affording the server access only to the aggregate of model updates while safeguarding the confidentiality of individual updates. Despite widespread claims regarding SecAgg's privacy-preserving capabilities, a formal analysis of its privacy is lacking, making such presumptions unjustified. In this paper
-
CCDSReFormer: Traffic Flow Prediction with a Criss-Crossed Dual-Stream Enhanced Rectified Transformer Model arXiv.cs.LG Pub Date : 2024-03-26 Zhiqi Shao, Michael G. H. Bell, Ze Wang, D. Glenn Geers, Xusheng Yao, Junbin Gao
Accurate, and effective traffic forecasting is vital for smart traffic systems, crucial in urban traffic planning and management. Current Spatio-Temporal Transformer models, despite their prediction capabilities, struggle with balancing computational efficiency and accuracy, favoring global over local information, and handling spatial and temporal data separately, limiting insight into complex interactions
-
Leave No Patient Behind: Enhancing Medication Recommendation for Rare Disease Patients arXiv.cs.LG Pub Date : 2024-03-26 Zihao Zhao, Yi Jing, Fuli Feng, Jiancan Wu, Chongming Gao, Xiangnan He
Medication recommendation systems have gained significant attention in healthcare as a means of providing tailored and effective drug combinations based on patients' clinical information. However, existing approaches often suffer from fairness issues, as recommendations tend to be more accurate for patients with common diseases compared to those with rare conditions. In this paper, we propose a novel
-
Masked Autoencoders are PDE Learners arXiv.cs.LG Pub Date : 2024-03-26 Anthony Zhou, Amir Barati Farimani
Neural solvers for partial differential equations (PDEs) have great potential, yet their practicality is currently limited by their generalizability. PDEs evolve over broad scales and exhibit diverse behaviors; predicting these phenomena will require learning representations across a wide variety of inputs, which may encompass different coefficients, geometries, or equations. As a step towards generalizable
-
MEP: Multiple Kernel Learning Enhancing Relative Positional Encoding Length Extrapolation arXiv.cs.LG Pub Date : 2024-03-26 Weiguo Gao
When the predicted sequence length exceeds the length seen during training, the transformer's inference accuracy diminishes. Existing relative position encoding methods, such as those based on the ALiBi technique, address the length extrapolation challenge exclusively through the implementation of a single kernel function, which introduces a constant bias to every post-softmax attention scores according
-
How Private is DP-SGD? arXiv.cs.LG Pub Date : 2024-03-26 Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang
We demonstrate a substantial gap between the privacy guarantees of the Adaptive Batch Linear Queries (ABLQ) mechanism under different types of batch sampling: (i) Shuffling, and (ii) Poisson subsampling; the typical analysis of Differentially Private Stochastic Gradient Descent (DP-SGD) follows by interpreting it as a post-processing of ABLQ. While shuffling based DP-SGD is more commonly used in practical
-
CANOS: A Fast and Scalable Neural AC-OPF Solver Robust To N-1 Perturbations arXiv.cs.LG Pub Date : 2024-03-26 Luis Piloto, Sofia Liguori, Sephora Madjiheurem, Miha Zgubic, Sean Lovett, Hamish Tomlinson, Sophie Elster, Chris Apps, Sims Witherspoon
Optimal Power Flow (OPF) refers to a wide range of related optimization problems with the goal of operating power systems efficiently and securely. In the simplest setting, OPF determines how much power to generate in order to minimize costs while meeting demand for power and satisfying physical and operational constraints. In even the simplest case, power grid operators use approximations of the AC-OPF
-
Uncertainty-aware Distributional Offline Reinforcement Learning arXiv.cs.LG Pub Date : 2024-03-26 Xiaocong Chen, Siyu Wang, Tong Yu, Lina Yao
Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various actions and environmental stochasticity. Traditional approaches primarily emphasize mitigating epistemic uncertainty by learning risk-averse policies, often overlooking
-
PeersimGym: An Environment for Solving the Task Offloading Problem with Reinforcement Learning arXiv.cs.LG Pub Date : 2024-03-26 Frederico Metelo, Stevo Racković, Pedro Ákos, Cláudia Soares
Task offloading, crucial for balancing computational loads across devices in networks such as the Internet of Things, poses significant optimization challenges, including minimizing latency and energy usage under strict communication and storage constraints. While traditional optimization falls short in scalability; and heuristic approaches lack in achieving optimal outcomes, Reinforcement Learning
-
Forest-ORE: Mining Optimal Rule Ensemble to interpret Random Forest models arXiv.cs.LG Pub Date : 2024-03-26 Haddouchi Maissae, Berrado Abdelaziz
Random Forest (RF) is well-known as an efficient ensemble learning method in terms of predictive performance. It is also considered a Black Box because of its hundreds of deep decision trees. This lack of interpretability can be a real drawback for acceptance of RF models in several real-world applications, especially those affecting one's lives, such as in healthcare, security, and law. In this work
-
Enhancing Privacy in Federated Learning through Local Training arXiv.cs.LG Pub Date : 2024-03-26 Nicola Bastianello, Changxin Liu, Karl H. Johansson
In this paper we propose the federated private local training algorithm (Fed-PLT) for federated learning, to overcome the challenges of (i) expensive communications and (ii) privacy preservation. We address (i) by allowing for both partial participation and local training, which significantly reduce the number of communication rounds between the central coordinator and computing agents. The algorithm
-
A Survey on Deep Learning and State-of-the-arts Applications arXiv.cs.LG Pub Date : 2024-03-26 Mohd Halim Mohd Noor, Ayokunle Olalekan Ige
Deep learning, a branch of artificial intelligence, is a computational model that uses multiple layers of interconnected units (neurons) to learn intricate patterns and representations directly from raw input data. Empowered by this learning capability, it has become a powerful tool for solving complex problems and is the core driver of many groundbreaking technologies and innovations. Building a deep
-
VDSC: Enhancing Exploration Timing with Value Discrepancy and State Counts arXiv.cs.LG Pub Date : 2024-03-26 Marius Captari, Remo Sasso, Matthia Sabatelli
Despite the considerable attention given to the questions of \textit{how much} and \textit{how to} explore in deep reinforcement learning, the investigation into \textit{when} to explore remains relatively less researched. While more sophisticated exploration strategies can excel in specific, often sparse reward environments, existing simpler approaches, such as $\epsilon$-greedy, persist in outperforming
-
BVR Gym: A Reinforcement Learning Environment for Beyond-Visual-Range Air Combat arXiv.cs.LG Pub Date : 2024-03-26 Edvards Scukins, Markus Klein, Lars Kroon, Petter Ögren
Creating new air combat tactics and discovering novel maneuvers can require numerous hours of expert pilots' time. Additionally, for each different combat scenario, the same strategies may not work since small changes in equipment performance may drastically change the air combat outcome. For this reason, we created a reinforcement learning environment to help investigate potential air combat tactics
-
Boosting Adversarial Training via Fisher-Rao Norm-based Regularization arXiv.cs.LG Pub Date : 2024-03-26 Xiangyu Yin, Wenjie Ruan
Adversarial training is extensively utilized to improve the adversarial robustness of deep neural networks. Yet, mitigating the degradation of standard generalization performance in adversarial-trained models remains an open problem. This paper attempts to resolve this issue through the lens of model complexity. First, We leverage the Fisher-Rao norm, a geometrically invariant metric for model complexity
-
DS-AL: A Dual-Stream Analytic Learning for Exemplar-Free Class-Incremental Learning arXiv.cs.LG Pub Date : 2024-03-26 Huiping Zhuang, Run He, Kai Tong, Ziqian Zeng, Cen Chen, Zhiping Lin
Class-incremental learning (CIL) under an exemplar-free constraint has presented a significant challenge. Existing methods adhering to this constraint are prone to catastrophic forgetting, far more so than replay-based techniques that retain access to past samples. In this paper, to solve the exemplar-free CIL problem, we propose a Dual-Stream Analytic Learning (DS-AL) approach. The DS-AL contains
-
Variational Graph Auto-Encoder Based Inductive Learning Method for Semi-Supervised Classification arXiv.cs.LG Pub Date : 2024-03-26 Hanxuan Yang, Zhaoxin Yu, Qingchao Kong, Wei Liu, Wenji Mao
Graph representation learning is a fundamental research issue in various domains of applications, of which the inductive learning problem is particularly challenging as it requires models to generalize to unseen graph structures during inference. In recent years, graph neural networks (GNNs) have emerged as powerful graph models for inductive learning tasks such as node classification, whereas they
-
A Unified Kernel for Neural Network Learning arXiv.cs.LG Pub Date : 2024-03-26 Shao-Qun Zhang, Zong-Yi Chen, Yong-Ming Tian, Xun Lu
Past decades have witnessed a great interest in the distinction and connection between neural network learning and kernel learning. Recent advancements have made theoretical progress in connecting infinite-wide neural networks and Gaussian processes. Two predominant approaches have emerged: the Neural Network Gaussian Process (NNGP) and the Neural Tangent Kernel (NTK). The former, rooted in Bayesian
-
Imitating Cost-Constrained Behaviors in Reinforcement Learning arXiv.cs.LG Pub Date : 2024-03-26 Qian Shao, Pradeep Varakantham, Shih-Fen Cheng
Complex planning and scheduling problems have long been solved using various optimization or heuristic approaches. In recent years, imitation learning that aims to learn from expert demonstrations has been proposed as a viable alternative to solving these problems. Generally speaking, imitation learning is designed to learn either the reward (or preference) model or directly the behavioral policy by
-
Incorporating Exponential Smoothing into MLP: A Simple but Effective Sequence Model arXiv.cs.LG Pub Date : 2024-03-26 Jiqun Chu, Zuoquan Lin
Modeling long-range dependencies in sequential data is a crucial step in sequence learning. A recently developed model, the Structured State Space (S4), demonstrated significant effectiveness in modeling long-range sequences. However, It is unclear whether the success of S4 can be attributed to its intricate parameterization and HiPPO initialization or simply due to State Space Models (SSMs). To further
-
Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study arXiv.cs.LG Pub Date : 2024-03-26 Jinze Zhao, Peihao Wang, Zhangyang Wang
Mixture-of-Experts (MoE) represents an ensemble methodology that amalgamates predictions from several specialized sub-models (referred to as experts). This fusion is accomplished through a router mechanism, dynamically assigning weights to each expert's contribution based on the input data. Conventional MoE mechanisms select all available experts, incurring substantial computational costs. In contrast
-
Application-Driven Innovation in Machine Learning arXiv.cs.LG Pub Date : 2024-03-26 David Rolnick, Alan Aspuru-Guzik, Sara Beery, Bistra Dilkina, Priya L. Donti, Marzyeh Ghassemi, Hannah Kerner, Claire Monteleoni, Esther Rolf, Milind Tambe, Adam White
As applications of machine learning proliferate, innovative algorithms inspired by specific real-world challenges have become increasingly important. Such work offers the potential for significant impact not merely in domains of application but also in machine learning itself. In this paper, we describe the paradigm of application-driven research in machine learning, contrasting it with the more standard
-
Deep Support Vectors arXiv.cs.LG Pub Date : 2024-03-26 Junhoo Lee, Hyunho Lee, Kyomin Hwang, Nojun Kwak
While the success of deep learning is commonly attributed to its theoretical equivalence with Support Vector Machines (SVM), the practical implications of this relationship have not been thoroughly explored. This paper pioneers an exploration in this domain, specifically focusing on the identification of Deep Support Vectors (DSVs) within deep learning models. We introduce the concept of DeepKKT conditions
-
Not All Federated Learning Algorithms Are Created Equal: A Performance Evaluation Study arXiv.cs.LG Pub Date : 2024-03-26 Gustav A. Baumgart, Jaemin Shin, Ali Payani, Myungjin Lee, Ramana Rao Kompella
Federated Learning (FL) emerged as a practical approach to training a model from decentralized data. The proliferation of FL led to the development of numerous FL algorithms and mechanisms. Many prior efforts have given their primary focus on accuracy of those approaches, but there exists little understanding of other aspects such as computational overheads, performance and training stability, etc
-
Neural Image Compression with Quantization Rectifier arXiv.cs.LG Pub Date : 2024-03-25 Wei Luo, Bo Chen
Neural image compression has been shown to outperform traditional image codecs in terms of rate-distortion performance. However, quantization introduces errors in the compression process, which can degrade the quality of the compressed image. Existing approaches address the train-test mismatch problem incurred during quantization, the random impact of quantization on the expressiveness of image features
-
Uncertainty Quantification for Gradient-based Explanations in Neural Networks arXiv.cs.LG Pub Date : 2024-03-25 Mihir Mulye, Matias Valdenegro-Toro
Explanation methods help understand the reasons for a model's prediction. These methods are increasingly involved in model debugging, performance optimization, and gaining insights into the workings of a model. With such critical applications of these methods, it is imperative to measure the uncertainty associated with the explanations generated by these methods. In this paper, we propose a pipeline
-
Sanity Checks for Explanation Uncertainty arXiv.cs.LG Pub Date : 2024-03-25 Matias Valdenegro-Toro, Mihir Mulye
Explanations for machine learning models can be hard to interpret or be wrong. Combining an explanation method with an uncertainty estimation method produces explanation uncertainty. Evaluating explanation uncertainty is difficult. In this paper we propose sanity checks for uncertainty explanation methods, where a weight and data randomization tests are defined for explanations with uncertainty, allowing
-
Less Is More - On the Importance of Sparsification for Transformers and Graph Neural Networks for TSP arXiv.cs.LG Pub Date : 2024-03-25 Attila Lischka, Jiaming Wu, Rafael Basso, Morteza Haghir Chehreghani, Balázs Kulcsár
Most of the recent studies tackling routing problems like the Traveling Salesman Problem (TSP) with machine learning use a transformer or Graph Neural Network (GNN) based encoder architecture. However, many of them apply these encoders naively by allowing them to aggregate information over the whole TSP instances. We, on the other hand, propose a data preprocessing method that allows the encoders to
-
Exploring the potential of prototype-based soft-labels data distillation for imbalanced data classification arXiv.cs.LG Pub Date : 2024-03-25 Radu-Andrei Rosu, Mihaela-Elena Breaban, Henri Luchian
Dataset distillation aims at synthesizing a dataset by a small number of artificially generated data items, which, when used as training data, reproduce or approximate a machine learning (ML) model as if it were trained on the entire original dataset. Consequently, data distillation methods are usually tied to a specific ML algorithm. While recent literature deals mainly with distillation of large
-
Stochastic Gradient Langevin Unlearning arXiv.cs.LG Pub Date : 2024-03-25 Eli Chien, Haoyu Wang, Ziang Chen, Pan Li
``The right to be forgotten'' ensured by laws for user data privacy becomes increasingly important. Machine unlearning aims to efficiently remove the effect of certain data points on the trained model parameters so that it can be approximately the same as if one retrains the model from scratch. This work proposes stochastic gradient Langevin unlearning, the first unlearning framework based on noisy
-
Stochastic parameter reduced-order model based on hybrid machine learning approaches arXiv.cs.LG Pub Date : 2024-03-24 Cheng Fang, Jinqiao Duan
Establishing appropriate mathematical models for complex systems in natural phenomena not only helps deepen our understanding of nature but can also be used for state estimation and prediction. However, the extreme complexity of natural phenomena makes it extremely challenging to develop full-order models (FOMs) and apply them to studying many quantities of interest. In contrast, appropriate reduced-order
-
The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization arXiv.cs.LG Pub Date : 2024-03-24 Shengyi Huang, Michael Noukhovitch, Arian Hosseini, Kashif Rasul, Weixun Wang, Lewis Tunstall
This work is the first to openly reproduce the Reinforcement Learning from Human Feedback (RLHF) scaling behaviors reported in OpenAI's seminal TL;DR summarization work. We create an RLHF pipeline from scratch, enumerate over 20 key implementation details, and share key insights during the reproduction. Our RLHF-trained Pythia models demonstrate significant gains in response quality that scale with
-
Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic arXiv.cs.LG Pub Date : 2024-03-26 Connor Pryor, Quan Yuan, Jeremiah Liu, Mehran Kazemi, Deepak Ramachandran, Tania Bedrax-Weiss, Lise Getoor
Dialog Structure Induction (DSI) is the task of inferring the latent dialog structure (i.e., a set of dialog states and their temporal transitions) of a given goal-oriented dialog. It is a critical component for modern dialog system design and discourse analysis. Existing DSI approaches are often purely data-driven, deploy models that infer latent states without access to domain knowledge, underperform
-
DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions arXiv.cs.LG Pub Date : 2024-03-26 Sammy Christen, Shreyas Hampali, Fadime Sener, Edoardo Remelli, Tomas Hodan, Eric Sauser, Shugao Ma, Bugra Tekin
Generating natural hand-object interactions in 3D is challenging as the resulting hand and object motions are expected to be physically plausible and semantically meaningful. Furthermore, generalization to unseen objects is hindered by the limited scale of available hand-object interaction datasets. We propose DiffH2O, a novel method to synthesize realistic, one or two-handed object interactions from
-
SciNews: From Scholarly Complexities to Public Narratives -- A Dataset for Scientific News Report Generation arXiv.cs.LG Pub Date : 2024-03-26 Dongqi Pu, Yifan Wang, Jia Loy, Vera Demberg
Scientific news reports serve as a bridge, adeptly translating complex research articles into reports that resonate with the broader public. The automated generation of such narratives enhances the accessibility of scholarly insights. In this paper, we present a new corpus to facilitate this paradigm development. Our corpus comprises a parallel compilation of academic publications and their corresponding
-
Noise2Noise Denoising of CRISM Hyperspectral Data arXiv.cs.LG Pub Date : 2024-03-26 Robert Platt, Rossella Arcucci, Cédric M. John
Hyperspectral data acquired by the Compact Reconnaissance Imaging Spectrometer for Mars (CRISM) have allowed for unparalleled mapping of the surface mineralogy of Mars. Due to sensor degradation over time, a significant portion of the recently acquired data is considered unusable. Here a new data-driven model architecture, Noise2Noise4Mars (N2N4M), is introduced to remove noise from CRISM images. Our
-
EulerFormer: Sequential User Behavior Modeling with Complex Vector Attention arXiv.cs.LG Pub Date : 2024-03-26 Zhen Tian, Wayne Xin Zhao, Changwang Zhang, Xin Zhao, Zhongrui Ma, Ji-Rong Wen
To capture user preference, transformer models have been widely applied to model sequential user behavior data. The core of transformer architecture lies in the self-attention mechanism, which computes the pairwise attention scores in a sequence. Due to the permutation-equivariant nature, positional encoding is used to enhance the attention between token representations. In this setting, the pairwise
-
PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition arXiv.cs.LG Pub Date : 2024-03-26 Chenhongyi Yang, Zehui Chen, Miguel Espinosa, Linus Ericsson, Zhenyu Wang, Jiaming Liu, Elliot J. Crowley
We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitive with other architectures on sequential data and initial attempts have been made to apply it to images. In this paper, we further adapt the selective scanning process of Mamba to the visual domain, enhancing its ability
-
Retentive Decision Transformer with Adaptive Masking for Reinforcement Learning based Recommendation Systems arXiv.cs.LG Pub Date : 2024-03-26 Siyu Wang, Xiaocong Chen, Lina Yao
Reinforcement Learning-based Recommender Systems (RLRS) have shown promise across a spectrum of applications, from e-commerce platforms to streaming services. Yet, they grapple with challenges, notably in crafting reward functions and harnessing large pre-existing datasets within the RL framework. Recent advancements in offline RLRS provide a solution for how to address these two challenges. However
-
Data-driven Energy Consumption Modelling for Electric Micromobility using an Open Dataset arXiv.cs.LG Pub Date : 2024-03-26 Yue Ding, Sen Yan, Maqsood Hussain Shah, Hongyuan Fang, Ji Li, Mingming Liu
The escalating challenges of traffic congestion and environmental degradation underscore the critical importance of embracing E-Mobility solutions in urban spaces. In particular, micro E-Mobility tools such as E-scooters and E-bikes, play a pivotal role in this transition, offering sustainable alternatives for urban commuters. However, the energy consumption patterns for these tools are a critical
-
Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets arXiv.cs.LG Pub Date : 2024-03-26 Patrick Grommelt, Louis Weiss, Franz-Josef Pfreundt, Janis Keuper
The widespread adoption of generative image models has highlighted the urgent need to detect artificial content, which is a crucial step in combating widespread manipulation and misinformation. Consequently, numerous detectors and associated datasets have emerged. However, many of these datasets inadvertently introduce undesirable biases, thereby impacting the effectiveness and evaluation of detectors
-
LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation arXiv.cs.LG Pub Date : 2024-03-26 Ke Guo, Zhenwei Miao, Wei Jing, Weiwei Liu, Weizi Li, Dayang Hao, Jia Pan
Microscopic traffic simulation plays a crucial role in transportation engineering by providing insights into individual vehicle behavior and overall traffic flow. However, creating a realistic simulator that accurately replicates human driving behaviors in various traffic conditions presents significant challenges. Traditional simulators relying on heuristic models often fail to deliver accurate simulations
-
Towards a Zero-Data, Controllable, Adaptive Dialog System arXiv.cs.LG Pub Date : 2024-03-26 Dirk Väth, Lindsey Vanderlyn, Ngoc Thang Vu
Conversational Tree Search (V\"ath et al., 2023) is a recent approach to controllable dialog systems, where domain experts shape the behavior of a Reinforcement Learning agent through a dialog tree. The agent learns to efficiently navigate this tree, while adapting to information needs, e.g., domain familiarity, of different users. However, the need for additional training data hinders deployment in
-
Capacity Provisioning Motivated Online Non-Convex Optimization Problem with Memory and Switching Cost arXiv.cs.LG Pub Date : 2024-03-26 Rahul Vaze, Jayakrishnan Nair
An online non-convex optimization problem is considered where the goal is to minimize the flow time (total delay) of a set of jobs by modulating the number of active servers, but with a switching cost associated with changing the number of active servers over time. Each job can be processed by at most one fixed speed server at any time. Compared to the usual online convex optimization (OCO) problem
-
Natural Language Requirements Testability Measurement Based on Requirement Smells arXiv.cs.LG Pub Date : 2024-03-26 Morteza Zakeri-Nasrabadi, Saeed Parsa
Requirements form the basis for defining software systems' obligations and tasks. Testable requirements help prevent failures, reduce maintenance costs, and make it easier to perform acceptance tests. However, despite the importance of measuring and quantifying requirements testability, no automatic approach for measuring requirements testability has been proposed based on the requirements smells,
-
Expectations Versus Reality: Evaluating Intrusion Detection Systems in Practice arXiv.cs.LG Pub Date : 2024-03-26 Jake Hesford, Daniel Cheng, Alan Wan, Larry Huynh, Seungho Kim, Hyoungshick Kim, Jin B. Hong
Our paper provides empirical comparisons between recent IDSs to provide an objective comparison between them to help users choose the most appropriate solution based on their requirements. Our results show that no one solution is the best, but is dependent on external variables such as the types of attacks, complexity, and network environment in the dataset. For example, BoT_IoT and Stratosphere IoT
-
Robust and Scalable Model Editing for Large Language Models arXiv.cs.LG Pub Date : 2024-03-26 Yingfa Chen, Zhengyan Zhang, Xu Han, Chaojun Xiao, Zhiyuan Liu, Chen Chen, Kuai Li, Tao Yang, Maosong Sun
Large language models (LLMs) can make predictions using parametric knowledge--knowledge encoded in the model weights--or contextual knowledge--knowledge presented in the context. In many scenarios, a desirable behavior is that LLMs give precedence to contextual knowledge when it conflicts with the parametric knowledge, and fall back to using their parametric knowledge when the context is irrelevant
-
Masked Multi-Domain Network: Multi-Type and Multi-Scenario Conversion Rate Prediction with a Single Model arXiv.cs.LG Pub Date : 2024-03-26 Wentao Ouyang, Xiuwu Zhang, Chaofeng Guo, Shukui Ren, Yupei Sui, Kun Zhang, Jinmei Luo, Yunfeng Chen, Dongbo Xu, Xiangzheng Liu, Yanlong Du
In real-world advertising systems, conversions have different types in nature and ads can be shown in different display scenarios, both of which highly impact the actual conversion rate (CVR). This results in the multi-type and multi-scenario CVR prediction problem. A desired model for this problem should satisfy the following requirements: 1) Accuracy: the model should achieve fine-grained accuracy
-
Transcribing Bengali Text with Regional Dialects to IPA using District Guided Tokens arXiv.cs.LG Pub Date : 2024-03-26 S M Jishanul Islam, Sadia Ahmmed, Sahid Hossain Mustakim
Accurate transcription of Bengali text to the International Phonetic Alphabet (IPA) is a challenging task due to the complex phonology of the language and context-dependent sound changes. This challenge is even more for regional Bengali dialects due to unavailability of standardized spelling conventions for these dialects, presence of local and foreign words popular in those regions and phonological
-
Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance arXiv.cs.LG Pub Date : 2024-03-26 Donghoon Ahn, Hyoungwon Cho, Jaewon Min, Wooseok Jang, Jungwoo Kim, SeonHwa Kim, Hyun Hee Park, Kyong Hwan Jin, Seungryong Kim
Recent studies have demonstrated that diffusion models are capable of generating high-quality samples, but their quality heavily depends on sampling guidance techniques, such as classifier guidance (CG) and classifier-free guidance (CFG). These techniques are often not applicable in unconditional generation or in various downstream tasks such as image restoration. In this paper, we propose a novel
-
AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving arXiv.cs.LG Pub Date : 2024-03-26 Mingfu Liang, Jong-Chyi Su, Samuel Schulter, Sparsh Garg, Shiyu Zhao, Ying Wu, Manmohan Chandraker
Autonomous vehicle (AV) systems rely on robust perception models as a cornerstone of safety assurance. However, objects encountered on the road exhibit a long-tailed distribution, with rare or unseen categories posing challenges to a deployed perception model. This necessitates an expensive process of continuously curating and annotating data with significant human effort. We propose to leverage recent
-
Language Models are Free Boosters for Biomedical Imaging Tasks arXiv.cs.LG Pub Date : 2024-03-26 Zhixin Lai, Jing Wu, Suiyao Chen, Yucheng Zhou, Anna Hovakimyan, Naira Hovakimyan
In this study, we uncover the unexpected efficacy of residual-based large language models (LLMs) as part of encoders for biomedical imaging tasks, a domain traditionally devoid of language or textual data. The approach diverges from established methodologies by utilizing a frozen transformer block, extracted from pre-trained LLMs, as an innovative encoder layer for the direct processing of visual tokens