Narrow Results

Automatic seizure detection from Electroencephalography (EEG) is of great importance in aiding the diagnosis and treatment of epilepsy due to the advantages of convenience and economy. Existing seizure detection methods are usually patient-specific, the training and testing are carried out on the same patient, limiting their scalability to other patients. To address this issue, we propose a cross-subject seizure detection method via unsupervised domain adaptation. The proposed method aims to obtain seizure specific information through shallow and deep feature alignments. For shallow feature alignment, we use convolutional neural network (CNN) to extract seizure-related features. The distribution gap of the shallow features between different patients is minimized by multi-kernel maximum mean discrepancies (MK-MMD). For deep feature alignment, adversarial learning is utilized. The feature extractor tries to learn feature representations that try to confuse the domain classifier, making the extracted deep features more generalizable to new patients. The performance of our method is evaluated on the CHB-MIT and Siena databases in epoch-based experiments. Additionally, event-based experiments are also conducted on the CHB-MIT dataset. The results validate the feasibility of our method in diminishing the domain disparities among different patients.

We analyze the problem of designing pattern recognition systems in adversarial settings, under an engineering viewpoint, motivated by their increasing exploitation in security-sensitive applications like spam and malware detection, despite their vulnerability to potential attacks has not yet been deeply understood. We first review previous work and report examples of how a complex system may be evaded either by leveraging on trivial vulnerabilities of its untrained components, e.g. parsing errors in the pre-processing steps, or by exploiting more subtle vulnerabilities of learning algorithms. We then discuss the need of exploiting both reactive and proactive security paradigms complementarily to improve the security by design. Our ultimate goal is to provide some useful guidelines for improving the security of pattern recognition in adversarial settings, and to suggest related open issues to foster research in this area.

The application of deep hashing methods for cross-modal retrieval has seen growing interest due to their storage efficiency and fast query execution. However, the challenge posed by the “heterogeneity gap” in multi-modal datasets cannot be understated. To address this, we present a novel framework named Dual-Pathway Deep Hashing-Based Adversarial Learning (DP-DHAL), engineered to surmount this challenge. The architecture of DP-DHAL integrates three key components: (a) a dual-pathway representation learning module tasked with extracting modality-specific features; (b) an adversarial module working to align the distributions of cross-modal features; and (c) a deep hashing module responsible for generating hash codes that uphold the similarity relationships across different modalities. Additionally, we have developed a unique Hamming triplet-margin loss function to refine the assessment of content similarities. The DP-DHAL model is trained through an adversarial process where the adversarial module’s goal is to discern cross-modal features with the aim of reducing the heterogeneity gap. Simultaneously, the representation learning module is focused on producing representations that can both deceive the adversarial module and preserve cross-modal similarities to yield distinctive hash codes. Comprehensive experiments on varied datasets have shown that our proposed method outperforms other leading cross-modal hashing techniques.

Word composition is a promising method to learn the representations of long text. Unfortunately, word composition falls short when inferring representations for non-compositional multiword expressions, such as “go banana.” Presently, many methods treat multiword expressions as single words and learn their representations in a manner similar to individual word representations. However, numerous multiword expressions exhibit ambiguity, expressing distinct meanings, whether literal or idiomatic, depending on the context. In response to these challenges, our paper proposes an adversarial context-aware representation learning method for multiword expressions, which generates representations based on the contexts of their occurrences. An adversarial training framework is introduced to further enhance the representation learning method. Experimental results confirm the benefits of sense disambiguation for multiword expressions in representation learning. Moreover, our proposed method demonstrates competitive performance on idiom token classification and compositionality prediction tasks.

This study investigates the effective incorporation of meta-information such as domain and language in finetuning a pretrained model based on self-supervised learning (SSL) for automatic speech recognition (ASR) in very low-resource settings. SSL pretrained models have been shown to achieve comparable or even better performance to conventional end-to-end systems even when we finetune them with a small dataset. However, it still requires the specific target dataset with a considerable amount of labeled data, like 10 h, to achieve satisfactory performance. Thus, we propose to exploit heterogeneous datasets which are partially matched either in language or domain and apply multi-task learning (MTL) or adversarial learning (ADV) using the meta-information. The finetuning comprises (1) domain adaptation, which uses in-domain multi-lingual datasets, and (2) language adaptation, which uses datasets of the same language but different domains. The auxiliary task is domain identification for language adaptation and language identification for domain adaptation. We then embed the output of the auxiliary task into the encoder output of the ASR task. The target dataset is the Khmer corpus of the Extraordinary Chambers in the Courts of Cambodia (ECCC) in various sizes from one hour to 10 h. The experimental evaluations demonstrate that fusing the meta-information in MTL or ADV significantly improves ASR accuracy. Moreover, a two-step adaptation method which first conducts domain adaptation and then language adaptation is the most effective. We also show that the target labeled dataset of only 5 h gives an almost saturated performance.

Personalized tag recommender systems are crucial for collaborative tagging systems. However, traditional personalized tag recommendation models tend to usually vulnerable to adversarial perturbations on their model parameters, which leads to poor generalization performance. In this paper, we propose an adversarial learning based personalized tag recommendation method, which integrates adversarial learning into the classic pairwise interaction tensor factorization model. Specifically, we integrate adversarial perturbations into the embedded representations of users, items and tags, and minimize the objective function of the pairwise interaction tensor factorization model with the perturbed parameters to increase the robustness of underlying factorization model. Experimental results on real world datasets show that our proposed adversarial learning based personalized tag recommendation model outperforms traditional tag recommendation models.