Open Access. Powered by Scholars. Published by Universities.®
Artificial Intelligence and Robotics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Institution
Articles 1 - 17 of 17
Full-Text Articles in Artificial Intelligence and Robotics
Bertastic At Semeval-2023 Task 3: Fine-Tuning Pretrained Multilingual Transformers – Does Order Matter?, Tarek Mahmoud, Preslav Nakov
Bertastic At Semeval-2023 Task 3: Fine-Tuning Pretrained Multilingual Transformers – Does Order Matter?, Tarek Mahmoud, Preslav Nakov
Natural Language Processing Faculty Publications
The naïve approach for fine-tuning pretrained deep learning models on downstream tasks involves feeding them mini-batches of randomly sampled data. In this paper, we propose a more elaborate method for fine-tuning Pretrained Multilingual Transformers (PMTs) on multilingual data. Inspired by the success of curriculum learning approaches, we investigate the significance of fine-tuning PMTs on multilingual data in a sequential fashion language by language. Unlike the curriculum learning paradigm where the model is presented with increasingly complex examples, we do not adopt a notion of “easy” and “hard” samples. Instead, our experiments draw insight from psychological findings on how the human …
Safe Mdp Planning By Learning Temporal Patterns Of Undesirable Trajectories And Averting Negative Side Effects, Siow Meng Low, Akshat Kumar, Scott Sanner
Safe Mdp Planning By Learning Temporal Patterns Of Undesirable Trajectories And Averting Negative Side Effects, Siow Meng Low, Akshat Kumar, Scott Sanner
Research Collection School Of Computing and Information Systems
In safe MDP planning, a cost function based on the current state and action is often used to specify safety aspects. In real world, often the state representation used may lack sufficient fidelity to specify such safety constraints. Operating based on an incomplete model can often produce unintended negative side effects (NSEs). To address these challenges, first, we associate safety signals with state-action trajectories (rather than just immediate state-action). This makes our safety model highly general. We also assume categorical safety labels are given for different trajectories, rather than a numerical cost function, which is harder to specify by the …
Stability-Based Generalization Analysis For Mixtures Of Pointwise And Pairwise Learning, Jiahuan Wang, Jun Chen, Hong Chen, Bin Gu, Weifu Li, Xin Tang
Stability-Based Generalization Analysis For Mixtures Of Pointwise And Pairwise Learning, Jiahuan Wang, Jun Chen, Hong Chen, Bin Gu, Weifu Li, Xin Tang
Machine Learning Faculty Publications
Recently, some mixture algorithms of pointwise and pairwise learning (PPL) have been formulated by employing the hybrid error metric of “pointwise loss + pairwise loss” and have shown empirical effectiveness on feature selection, ranking and recommendation tasks. However, to the best of our knowledge, the learning theory foundation of PPL has not been touched in the existing works. In this paper, we try to fill this theoretical gap by investigating the generalization properties of PPL. After extending the definitions of algorithmic stability to the PPL setting, we establish the high-probability generalization bounds for uniformly stable PPL algorithms. Moreover, explicit convergence …
Truncated Matrix Power Iteration For Differentiable Dag Learning, Zhen Zhang, Ignavier Ng, Dong Gong, Yuhang Liu, Ehsan M. Abbasnejad, Mingming Gong, Kun Zhang, Javen Qinfeng Shi
Truncated Matrix Power Iteration For Differentiable Dag Learning, Zhen Zhang, Ignavier Ng, Dong Gong, Yuhang Liu, Ehsan M. Abbasnejad, Mingming Gong, Kun Zhang, Javen Qinfeng Shi
Machine Learning Faculty Publications
Recovering underlying Directed Acyclic Graph structures (DAG) from observational data is highly challenging due to the combinatorial nature of the DAG-constrained optimization problem. Recently, DAG learning has been cast as a continuous optimization problem by characterizing the DAG constraint as a smooth equality one, generally based on polynomials over adjacency matrices. Existing methods place very small coefficients on high-order polynomial terms for stabilization, since they argue that large coefficients on the higher-order terms are harmful due to numeric exploding. On the contrary, we discover that large coefficients on higher-order terms are beneficial for DAG learning, when the spectral radiuses of …
Action-Sufficient State Representation Learning For Control With Structural Constraints, Biwei Huang, Chaochao Lu, Liu Leqi, Josã© Miguel Hernã¡Ndez-Lobato, Clark Glymour, Bernhard Schã¶Lkopf, Kun Zhang
Action-Sufficient State Representation Learning For Control With Structural Constraints, Biwei Huang, Chaochao Lu, Liu Leqi, Josã© Miguel Hernã¡Ndez-Lobato, Clark Glymour, Bernhard Schã¶Lkopf, Kun Zhang
Machine Learning Faculty Publications
Perceived signals in real-world scenarios are usually high-dimensional and noisy, and finding and using their representation that contains essential and sufficient information required by downstream decision-making tasks will help improve computational efficiency and generalization ability in the tasks. In this paper, we focus on partially observable environments and propose to learn a minimal set of state representations that capture sufficient information for decision-making, termed Action-Sufficient state Representations (ASRs). We build a generative environment model for the structural relationships among variables in the system and present a principled way to characterize ASRs based on structural constraints and the goal of maximizing …
Learning To Generalize Dispatching Rules On The Job Shop Scheduling, Zangir Iklassov, Dmitrii Medvedev, Ruben Solozabal, Martin Takac
Learning To Generalize Dispatching Rules On The Job Shop Scheduling, Zangir Iklassov, Dmitrii Medvedev, Ruben Solozabal, Martin Takac
Machine Learning Faculty Publications
This paper introduces a Reinforcement Learning approach to better generalize heuristic dispatching rules on the Job-shop Scheduling Problem (JSP). Current models on the JSP do not focus on generalization, although, as we show in this work, this is key to learning better heuristics on the problem. A well-known technique to improve generalization is to learn on increasingly complex instances using Curriculum Learning (CL). However, as many works in the literature indicate, this technique might suffer from catastrophic forgetting when transferring the learned skills between different problem sizes. To address this issue, we introduce a novel Adversarial Curriculum Learning (ACL) strategy, …
Flecs: A Federated Learning Second-Order Framework Via Compression And Sketching, Artem Agafonov, Dmitry Kamzolov, Rachael Tappenden, Alexander Gasnikov, Martin Takac
Flecs: A Federated Learning Second-Order Framework Via Compression And Sketching, Artem Agafonov, Dmitry Kamzolov, Rachael Tappenden, Alexander Gasnikov, Martin Takac
Machine Learning Faculty Publications
Inspired by the recent work FedNL (Safaryan et al, FedNL: Making Newton-Type Methods Applicable to Federated Learning), we propose a new communication efficient second-order framework for Federated learning, namely FLECS. The proposed method reduces the high-memory requirements of FedNL by the usage of an L-SR1 type update for the Hessian approximation which is stored on the central server. A low dimensional 'sketch' of the Hessian is all that is needed by each device to generate an update, so that memory costs as well as number of Hessian-vector products for the agent are low. Biased and unbiased compressions are utilized to …
Offline Reinforcement Learning With Causal Structured World Models, Zheng-Mao Zhu, Xiong-Hui Chen, Hong-Long Tian, Kun Zhang, Yang Yu
Offline Reinforcement Learning With Causal Structured World Models, Zheng-Mao Zhu, Xiong-Hui Chen, Hong-Long Tian, Kun Zhang, Yang Yu
Machine Learning Faculty Publications
Model-based methods have recently shown promising for offline reinforcement learning (RL), aiming to learn good policies from historical data without interacting with the environment. Previous model-based offline RL methods learn fully connected nets as world-models to map the states and actions to the next-step states. However, it is sensible that a world-model should adhere to the underlying causal effect such that it will support learning an effective policy generalizing well in unseen states. In this paper, We first provide theoretical results that causal world-models can outperform plain world-models for offline RL by incorporating the causal structure into the generalization error …
Deep Learning For Anomaly Detection, Guansong Pang, Charu Aggarwal, Chunhua Shen, Nicu Sebe
Deep Learning For Anomaly Detection, Guansong Pang, Charu Aggarwal, Chunhua Shen, Nicu Sebe
Research Collection School Of Computing and Information Systems
A nomaly detection aims at identifying data points which are rare or significantly different from the majority of data points. Many techniques are explored to build highly efficient and effective anomaly detection systems, but they are confronted with many difficulties when dealing with complex data, such as failing to capture intricate feature interactions or extract good feature representations. Deep-learning techniques have shown very promising performance in tackling different types of complex data in a broad range of tasks/problems, including anomaly detection. To address this new trend, we organized this Special Issue on Deep Learning for Anomaly Detection to cover the …
Self-Supervised Video Object Segmentation Via Cutout Prediction And Tagging, Jyoti Kini, Fahad Shahbaz Khan, Salman Khan, Mubarak Shah
Self-Supervised Video Object Segmentation Via Cutout Prediction And Tagging, Jyoti Kini, Fahad Shahbaz Khan, Salman Khan, Mubarak Shah
Computer Vision Faculty Publications
We propose a novel self-supervised Video Object Segmentation (VOS) approach that strives to achieve better object-background discriminability for accurate object segmentation. Distinct from previous self-supervised VOS methods, our approach is based on a discriminative learning loss formulation that takes into account both object and background information to ensure object-background discriminability, rather than using only object appearance. The discriminative learning loss comprises cutout-based reconstruction (cutout region represents part of a frame, whose pixels are replaced with some constant values) and tag prediction loss terms. The cutout-based reconstruction term utilizes a simple cutout scheme to learn the pixel-wise correspondence between the current …
Hsva: Hierarchical Semantic-Visual Adaptation For Zero-Shot Learning, Shiming Chen, Guo Sen Xie, Yang Liu, Qinmu Peng, Baigui Sun, Hao Li, Xinge You, Ling Shao
Hsva: Hierarchical Semantic-Visual Adaptation For Zero-Shot Learning, Shiming Chen, Guo Sen Xie, Yang Liu, Qinmu Peng, Baigui Sun, Hao Li, Xinge You, Ling Shao
Machine Learning Faculty Publications
Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to unseen ones. Typically, to guarantee desirable knowledge transfer, a common (latent) space is adopted for associating the visual and semantic domains in ZSL. However, existing common space learning methods align the semantic and visual domains by merely mitigating distribution disagreement through one-step adaptation. This strategy is usually ineffective due to the heterogeneous nature of the feature representations in the two domains, which intrinsically contain both distribution and structure variations. To address this and advance ZSL, we propose a novel hierarchical semantic-visual adaptation (HSVA) framework. …
Learning From Mistakes - A Framework For Neural Architecture Search, Bhanu Garg, Li Zhang, Pradyumna Sridhara, Ramtin Hosseini, Eric P. Xing, Pengtao Xie
Learning From Mistakes - A Framework For Neural Architecture Search, Bhanu Garg, Li Zhang, Pradyumna Sridhara, Ramtin Hosseini, Eric P. Xing, Pengtao Xie
Machine Learning Faculty Publications
Learning from one's mistakes is an effective human learning technique where the learners focus more on the topics where mistakes were made, so as to deepen their understanding. In this paper, we investigate if this human learning strategy can be applied in machine learning. We propose a novel machine learning method called Learning From Mistakes (LFM), wherein the learner improves its ability to learn by focusing more on the mistakes during revision. We formulate LFM as a three-stage optimization problem: 1) learner learns; 2) learner re-learns focusing on the mistakes, and; 3) learner validates its learning. We develop an efficient …
Orthogonal Inductive Matrix Completion, Antoine Ledent, Rrodrigo Alves, Marius Kloft
Orthogonal Inductive Matrix Completion, Antoine Ledent, Rrodrigo Alves, Marius Kloft
Research Collection School Of Computing and Information Systems
We propose orthogonal inductive matrix completion (OMIC), an interpretable approach to matrix completion based on a sum of multiple orthonormal side information terms, together with nuclear-norm regularization. The approach allows us to inject prior knowledge about the singular vectors of the ground-truth matrix. We optimize the approach by a provably converging algorithm, which optimizes all components of the model simultaneously. We study the generalization capabilities of our method in both the distribution-free setting and in the case where the sampling distribution admits uniform marginals, yielding learning guarantees that improve with the quality of the injected knowledge in both cases. As …
Learning To Fuse Asymmetric Feature Maps In Siamese Trackers, Wencheng Han, Xingping Dong, Fahad Shahbaz Khan, Ling Shao, Jianbing Shen
Learning To Fuse Asymmetric Feature Maps In Siamese Trackers, Wencheng Han, Xingping Dong, Fahad Shahbaz Khan, Ling Shao, Jianbing Shen
Computer Vision Faculty Publications
Recently, Siamese-based trackers have achieved promising performance in visual tracking. Most recent Siamese-based trackers typically employ a depth-wise cross-correlation (DW-XCorr) to obtain multi-channel correlation information from the two feature maps (target and search region). However, DW-XCorr has several limitations within Siamese-based tracking: it can easily be fooled by distractors, has fewer activated channels and provides weak discrimination of object boundaries. Further, DW-XCorr is a handcrafted parameter-free module and cannot fully benefit from offline learning on large-scale data. We propose a learnable module, called the asymmetric convolution (ACM), which learns to better capture the semantic correlation information in offline training on …
Recurrent Neural Networks With Auxiliary Labels For Cross-Domain Opinion Target Extraction, Ying Ding, Jianfei Yu, Jing Jiang
Recurrent Neural Networks With Auxiliary Labels For Cross-Domain Opinion Target Extraction, Ying Ding, Jianfei Yu, Jing Jiang
Research Collection School Of Computing and Information Systems
Opinion target extraction is a fundamental task in opinion mining. In recent years, neural network based supervised learning methods have achieved competitive performance on this task. However, as with any supervised learning method, neural network based methods for this task cannot work well when the training data comes from a different domain than the test data. On the other hand, some rule-based unsupervised methods have shown to be robust when applied to different domains. In this work, we use rule-based unsupervised methods to create auxiliary labels and use neural network models to learn a hidden representation that works well for …
Message Passing For Collective Graphical Models, Tao Sun, Daniel Sheldon, Akshat Kumar
Message Passing For Collective Graphical Models, Tao Sun, Daniel Sheldon, Akshat Kumar
Research Collection School Of Computing and Information Systems
Collective graphical models (CGMs) are a formalism for inference and learning about a population of independent and identically distributed individuals when only noisy aggregate data are available. We highlight a close connection between approximate MAP inference in CGMs and marginal inference in standard graphical models. The connection leads us to derive a novel Belief Propagation (BP) style algorithm for collective graphical models. Mathematically, the algorithm is a strict generalization of BP—it can be viewed as an extension to minimize the Bethe free energy plus additional energy terms that are non-linear functions of the marginals. For CGMs, the algorithm is much …
Motivated Learning As An Extension Of Reinforcement Learning, Janusz Starzyk, Pawel Raif, Ah-Hwee Tan
Motivated Learning As An Extension Of Reinforcement Learning, Janusz Starzyk, Pawel Raif, Ah-Hwee Tan
Research Collection School Of Computing and Information Systems
We have developed a unified framework to conduct computational experiments with both learning systems: Motivated learning based on Goal Creation System, and reinforcedment learning using RL Q-Learning Algorithm. Future work includes combining motivated learning to set abstract motivations and manage goals with reinforcement learning to learn proper actions. This will allow testing of motivated learning on typical reinforcement learning benchmarks with large dimensionality of the state/action spaces.