Searcharxiv⌕ Search

arXiv subjects

Mohammad Akbari

Publications and source records attributed to Mohammad Akbari.

At least 37 records · Page 2Linked to original sources
arXiv2023

ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages

Building multi-modal language models has been a trend in the recent years, where additional modalities such as image, video, speech, etc. are jointly learned along with natural languages (i.e., textual information). Despite the success of these multi-modal language models with different modalities, there is no existing solution for neural network architectures and natural languages. Providing neural architectural information as a new modality allows us to provide fast architecture-2-text and text-2-architecture retrieval/generation services on the cloud with a single inference. Such solution is valuable in terms of helping beginner and intermediate ML users to come up with better neural architectures or AutoML approaches with a simple text query. In this paper, we propose ArchBERT, a bi-modal model for joint learning and understanding of neural architectures and natural languages, which opens up new avenues for research in this area. We also introduce a pre-training strategy named Masked Architecture Modeling (MAM) for a more generalized joint learning. Moreover, we introduce and publicly release two new bi-modal datasets for training and validating our methods. The ArchBERT's performance is verified through a set of numerical experiments on different downstream tasks such as architecture-oriented reasoning, question answering, and captioning (summarization). Datasets, codes, and demos are available supplementary materials.

cs.CL↗
arXiv2023

ETran: Energy-Based Transferability Estimation

This paper addresses the problem of ranking pre-trained models for object detection and image classification. Selecting the best pre-trained model by fine-tuning is an expensive and time-consuming task. Previous works have proposed transferability estimation based on features extracted by the pre-trained models. We argue that quantifying whether the target dataset is in-distribution (IND) or out-of-distribution (OOD) for the pre-trained model is an important factor in the transferability estimation. To this end, we propose ETran, an energy-based transferability assessment metric, which includes three scores: 1) energy score, 2) classification score, and 3) regression score. We use energy-based models to determine whether the target dataset is OOD or IND for the pre-trained model. In contrast to the prior works, ETran is applicable to a wide range of tasks including classification, regression, and object detection (classification+regression). This is the first work that proposes transferability estimation for object detection task. Our extensive experiments on four benchmarks and two tasks show that ETran outperforms previous works on object detection and classification benchmarks by an average of 21% and 12%, respectively, and achieves SOTA in transferability assessment.

cs.CV↗
arXiv2023

A Persian Benchmark for Joint Intent Detection and Slot Filling

Natural Language Understanding (NLU) is important in today's technology as it enables machines to comprehend and process human language, leading to improved human-computer interactions and advancements in fields such as virtual assistants, chatbots, and language-based AI systems. This paper highlights the significance of advancing the field of NLU for low-resource languages. With intent detection and slot filling being crucial tasks in NLU, the widely used datasets ATIS and SNIPS have been utilized in the past. However, these datasets only cater to the English language and do not support other languages. In this work, we aim to address this gap by creating a Persian benchmark for joint intent detection and slot filling based on the ATIS dataset. To evaluate the effectiveness of our benchmark, we employ state-of-the-art methods for intent detection and slot filling.

cs.CL↗
arXiv2022

Logarithmic Regret in Adaptive Control of Noisy Linear Quadratic Regulator Systems Using Hints

The problem of regret minimization for online adaptive control of linear-quadratic systems is studied. In this problem, the true system transition parameters (matrices $A$ and $B$) are unknown, and the objective is to design and analyze algorithms that generate control policies with sublinear regret. Recent studies show that when the system parameters are fully unknown, there exists a choice of these parameters such that any algorithm that only uses data from the past system trajectory at best achieves a square root of time horizon regret bound, providing a hard fundamental limit on the achievable regret in general. However, it is also known that (poly)-logarithmic regret is achievable when only matrix $A$ or only matrix $B$ is unknown. We present a result, encompassing both scenarios, showing that (poly)-logarithmic regret is achievable when both of these matrices are unknown, but a hint is periodically given to the controller.

math.OC↗
arXiv2022

A Deep Learning-Based Approach for Cell Outage Compensation in NOMA Networks

Cell outage compensation enables a network to react to a catastrophic cell failure quickly and serve users in the outage zone uninterruptedly. Utilizing the promising benefits of non-orthogonal multiple access (NOMA) for improving the throughput of cell edge users, we propose a newly NOMA-based cell outage compensation scheme. In this scheme, the compensation is formulated as a mixed integer non-linear program (MINLP) where outage zone users are associated to neighboring cells and their power are allocated with the objective of maximizing spectral efficiency, subject to maintaining the quality of service for the rest of the users. Owing to the importance of immediate management of cell outage and handling the computational complexity, we develop a low-complexity suboptimal solution for this problem in which the user association scheme is determined by a newly heuristic algorithm, and power allocation is set by applying an innovative deep neural network (DNN). The complexity of our proposed method is in the order of polynomial basis, which is much less than the exponential complexity of finding an optimal solution. Simulation results demonstrate that the proposed method approaches the optimal solution. Moreover, the developed scheme greatly improves fairness and increases the number of served users.

eess.SP↗
arXiv2022

E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models

Building huge and highly capable language models has been a trend in the past years. Despite their great performance, they incur high computational cost. A common solution is to apply model compression or choose light-weight architectures, which often need a separate fixed-size model for each desirable computational budget, and may lose performance in case of heavy compression. This paper proposes an effective dynamic inference approach, called E-LANG, which distributes the inference between large accurate Super-models and light-weight Swift models. To this end, a decision making module routes the inputs to Super or Swift models based on the energy characteristics of the representations in the latent space. This method is easily adoptable and architecture agnostic. As such, it can be applied to black-box pre-trained models without a need for architectural manipulations, reassembling of modules, or re-training. Unlike existing methods that are only applicable to encoder-only backbones and classification tasks, our method also works for encoder-decoder structures and sequence-to-sequence tasks such as translation. The E-LANG performance is verified through a set of experiments with T5 and BERT backbones on GLUE, SuperGLUE, and WMT. In particular, we outperform T5-11B with an average computations speed-up of 3.3$\times$ on GLUE and 2.9$\times$ on SuperGLUE. We also achieve BERT-based SOTA on GLUE with 3.2$\times$ less computations. Code and demo are available in the supplementary materials.

cs.CL↗
arXiv2021

Deep Learning meets Liveness Detection: Recent Advancements and Challenges

Facial biometrics has been recently received tremendous attention as a convenient replacement for traditional authentication systems. Consequently, detecting malicious attempts has found great significance, leading to extensive studies in face anti-spoofing~(FAS),i.e., face presentation attack detection. Deep feature learning and techniques, as opposed to hand-crafted features, have promised a dramatic increase in the FAS systems' accuracy, tackling the key challenges of materializing the real-world application of such systems. Hence, a new research area dealing with the development of more generalized as well as accurate models is increasingly attracting the attention of the research community and industry. In this paper, we present a comprehensive survey on the literature related to deep-feature-based FAS methods since 2017. To shed light on this topic, a semantic taxonomy based on various features and learning methodologies is represented. Further, we cover predominant public datasets for FAS in chronological order, their evolutional progress, and the evaluation criteria (both intra-dataset and inter-dataset). Finally, we discuss the open research challenges and future directions.

cs.CV↗
arXiv2021

EBJR: Energy-Based Joint Reasoning for Adaptive Inference

State-of-the-art deep learning models have achieved significant performance levels on various benchmarks. However, the excellent performance comes at a cost of inefficient computational cost. Light-weight architectures, on the other hand, achieve moderate accuracies, but at a much more desirable latency. This paper presents a new method of jointly using the large accurate models together with the small fast ones. To this end, we propose an Energy-Based Joint Reasoning (EBJR) framework that adaptively distributes the samples between shallow and deep models to achieve an accuracy close to the deep model, but latency close to the shallow one. Our method is applicable to out-of-the-box pre-trained models as it does not require an architecture change nor re-training. Moreover, it is easy to use and deploy, especially for cloud services. Through a comprehensive set of experiments on different down-stream tasks, we show that our method outperforms strong state-of-the-art approaches with a considerable margin. In addition, we propose specialized EBJR, an extension of our method where we create a smaller specialized side model that performs the target task only partially, but yields an even higher accuracy and faster inference. We verify the strengths of our methods with both theoretical and experimental evaluations.

cs.CV↗
arXiv2021

Advances and Challenges in Deep Lip Reading

Driven by deep learning techniques and large-scale datasets, recent years have witnessed a paradigm shift in automatic lip reading. While the main thrust of Visual Speech Recognition (VSR) was improving accuracy of Audio Speech Recognition systems, other potential applications, such as biometric identification, and the promised gains of VSR systems, have motivated extensive efforts on developing the lip reading technology. This paper provides a comprehensive survey of the state-of-the-art deep learning based VSR research with a focus on data challenges, task-specific complications, and the corresponding solutions. Advancements in these directions will expedite the transformation of silent speech interface from theory to practice. We also discuss the main modules of a VSR pipeline and the influential datasets. Finally, we introduce some typical VSR application concerns and impediments to real-world scenarios as well as future research directions.

cs.CV↗
arXiv2021

Bagging Supervised Autoencoder Classifier for Credit Scoring

Credit scoring models, which are among the most potent risk management tools that banks and financial institutes rely on, have been a popular subject for research in the past few decades. Accordingly, many approaches have been developed to address the challenges in classifying loan applicants and improve and facilitate decision-making. The imbalanced nature of credit scoring datasets, as well as the heterogeneous nature of features in credit scoring datasets, pose difficulties in developing and implementing effective credit scoring models, targeting the generalization power of classification models on unseen data. In this paper, we propose the Bagging Supervised Autoencoder Classifier (BSAC) that mainly leverages the superior performance of the Supervised Autoencoder, which learns low-dimensional embeddings of the input data exclusively with regards to the ultimate classification task of credit scoring, based on the principles of multi-task learning. BSAC also addresses the data imbalance problem by employing a variant of the Bagging process based on the undersampling of the majority class. The obtained results from our experiments on the benchmark and real-life credit scoring datasets illustrate the robustness and effectiveness of the Bagging Supervised Autoencoder Classifier in the classification of loan applicants that can be regarded as a positive development in credit scoring models.

cs.LG↗
arXiv2021

Age of Information Aware VNF Scheduling in Industrial IoT Using Deep Reinforcement Learning

In delay-sensitive industrial internet of things (IIoT) applications, the age of information (AoI) is employed to characterize the freshness of information. Meanwhile, the emerging network function virtualization provides flexibility and agility for service providers to deliver a given network service using a sequence of virtual network functions (VNFs). However, suitable VNF placement and scheduling in these schemes is NP-hard and finding a globally optimal solution by traditional approaches is complex. Recently, deep reinforcement learning (DRL) has appeared as a viable way to solve such problems. In this paper, we first utilize single agent low-complex compound action actor-critic RL to cover both discrete and continuous actions and jointly minimize VNF cost and AoI in terms of network resources under end-to end Quality of Service constraints. To surmount the single-agent capacity limitation for learning, we then extend our solution to a multi-agent DRL scheme in which agents collaborate with each other. Simulation results demonstrate that single-agent schemes significantly outperform the greedy algorithm in terms of average network cost and AoI. Moreover, multi-agent solution decreases the average cost by dividing the tasks between the agents. However, it needs more iterations to be learned due to the requirement on the agents collaboration.

eess.SP↗
arXiv2021

An Iterative Riccati Algorithm for Online Linear Quadratic Control

An online policy learning problem of linear control systems is studied. In this problem, the control system is known and linear, and a sequence of quadratic cost functions is revealed to the controller in hindsight, and the controller updates its policy to achieve a sublinear regret, similar to online optimization. A modified online Riccati algorithm is introduced that under some boundedness assumption leads to logarithmic regret bound. In particular, the logarithmic regret for the scalar case is achieved without boundedness assumption. Our algorithm, while achieving a better regret bound, also has reduced complexity compared to earlier algorithms which rely on solving semi-definite programs at each stage.

math.OC↗
arXiv2021

A Compact Deep Learning Model for Face Spoofing Detection

In recent years, face biometric security systems are rapidly increasing, therefore, the presentation attack detection (PAD) has received significant attention from research communities and has become a major field of research. Researchers have tackled the problem with various methods, from exploiting conventional texture feature extraction such as LBP, BSIF, and LPQ to using deep neural networks with different architectures. Despite the results each of these techniques has achieved for a certain attack scenario or dataset, most of them still failed to generalized the problem for unseen conditions, as the efficiency of each is limited to certain type of presentation attacks and instruments (PAI). In this paper, instead of completely extracting hand-crafted texture features or relying only on deep neural networks, we address the problem via fusing both wide and deep features in a unified neural architecture. The main idea is to take advantage of the strength of both methods to derive well-generalized solution for the problem. We also evaluated the effectiveness of our method by comparing the results with each of the mentioned techniques separately. The procedure is done on different spoofing datasets such as ROSE-Youtu, SiW and NUAA Imposter datasets. In particular, we simultanously learn a low dimensional latent space empowered with data-driven features learnt via Convolutional Neural Network designes for spoofing detection task (i.e., deep channel) as well as leverages spoofing detection feature already popular for spoofing in frequency and temporal dimensions ( i.e., via wide channel).

cs.CV↗
arXiv2020

Generalized Octave Convolutions for Learned Multi-Frequency Image Compression

Learned image compression has recently shown the potential to outperform the standard codecs. State-of-the-art rate-distortion (R-D) performance has been achieved by context-adaptive entropy coding approaches in which hyperprior and autoregressive models are jointly utilized to effectively capture the spatial dependencies in the latent representations. However, the latents are feature maps of the same spatial resolution in previous works, which contain some redundancies that affect the R-D performance. In this paper, we propose the first learned multi-frequency image compression and entropy coding approach that is based on the recently developed octave convolutions to factorize the latents into high and low frequency (resolution) components, where the low frequency is represented by a lower resolution. Therefore, its spatial redundancy is reduced, which improves the R-D performance. Novel generalized octave convolution and octave transposed-convolution architectures with internal activation layers are also proposed to preserve more spatial structure of the information. Experimental results show that the proposed scheme not only outperforms all existing learned methods as well as standard codecs such as the next-generation video coding standard VVC (4:2:0) on the Kodak dataset in both PSNR and MS-SSIM. We also show that the proposed generalized octave convolution can improve the performance of other auto-encoder-based computer vision tasks such as semantic segmentation and image denoising.

eess.IV↗
arXiv2020

Learned Multi-Resolution Variable-Rate Image Compression with Octave-based Residual Blocks

Recently deep learning-based image compression has shown the potential to outperform traditional codecs. However, most existing methods train multiple networks for multiple bit rates, which increase the implementation complexity. In this paper, we propose a new variable-rate image compression framework, which employs generalized octave convolutions (GoConv) and generalized octave transposed-convolutions (GoTConv) with built-in generalized divisive normalization (GDN) and inverse GDN (IGDN) layers. Novel GoConv- and GoTConv-based residual blocks are also developed in the encoder and decoder networks. Our scheme also uses a stochastic rounding-based scalar quantization. To further improve the performance, we encode the residual between the input and the reconstructed image from the decoder network as an enhancement layer. To enable a single model to operate with different bit rates and to learn multi-rate image features, a new objective function is introduced. Experimental results show that the proposed framework trained with variable-rate objective function outperforms the standard codecs such as H.265/HEVC-based BPG and state-of-the-art learning-based variable-rate methods.

cs.CV↗
arXiv2020

Twitter Spam Detection: A Systematic Review

Nowadays, with the rise of Internet access and mobile devices around the globe, more people are using social networks for collaboration and receiving real-time information. Twitter, the microblogging that is becoming a critical source of communication and news propagation, has grabbed the attention of spammers to distract users. So far, researchers have introduced various defense techniques to detect spams and combat spammer activities on Twitter. To overcome this problem, in recent years, many novel techniques have been offered by researchers, which have greatly enhanced the spam detection performance. Therefore, it raises a motivation to conduct a systematic review about different approaches of spam detection on Twitter. This review focuses on comparing the existing research techniques on Twitter spam detection systematically. Literature review analysis reveals that most of the existing methods rely on Machine Learning-based algorithms. Among these Machine Learning algorithms, the major differences are related to various feature selection methods. Hence, we propose a taxonomy based on different feature selection methods and analyses, namely content analysis, user analysis, tweet analysis, network analysis, and hybrid analysis. Then, we present numerical analyses and comparative studies on current approaches, coming up with open challenges that help researchers develop solutions in this topic.

cs.CR↗
arXiv2020

Dynamic Ensemble Learning for Credit Scoring: A Comparative Study

Automatic credit scoring, which assesses the probability of default by loan applicants, plays a vital role in peer-to-peer lending platforms to reduce the risk of lenders. Although it has been demonstrated that dynamic selection techniques are effective for classification tasks, the performance of these techniques for credit scoring has not yet been determined. This study attempts to benchmark different dynamic selection approaches systematically for ensemble learning models to accurately estimate the credit scoring task on a large and high-dimensional real-life credit scoring data set. The results of this study indicate that dynamic selection techniques are able to boost the performance of ensemble models, especially in imbalanced training environments.

cs.LG↗