The success of gradient-based meta-learning is primarily attributed to its ability to leverage related tasks to learn task-invariant information. However, the absence of interactions between different tasks in the inner loop leads to task-specific over-fitting in the initial phase of meta-training. While this is eventually corrected by the presence of these interactions in the outer loop, it comes at a significant cost of slower meta-learning. To address this limitation, we explicitly encode task relatedness via an inner loop regularization mechanism inspired by multi-task learning. Our algorithm shares gradient information from previously encountered tasks as well as concurrent tasks in the same task batch, and scales their contribution with meta-learned parameters. We show using two popular few-shot classification datasets that gradient sharing enables meta-learning under bigger inner loop learning rates and can accelerate the meta-training process by up to 134%.

Incremental Learning (IL) has been a long-standing problem in both vision and Natural Language Processing (NLP) communities. In recent years, as Pre-trained Language Models (PLMs) have achieved remarkable progress in various NLP downstream tasks, utilizing PLMs as backbones has become a common practice in recent research of IL in NLP. Most assume that catastrophic forgetting is the biggest obstacle to achieving superior IL performance and propose various techniques to overcome this issue. However, we find that this assumption is problematic. Specifically, we revisit more than 20 methods on four classification tasks (Text Classification, Intent Classification, Relation Extraction, and Named Entity Recognition) under the two most popular IL settings (Class-Incremental and Task-Incremental) and reveal that most of them severely underestimate the inherent anti-forgetting ability of PLMs. Based on the observation, we propose a frustratingly easy method called SEQ* for IL with PLMs. The results show that SEQ* has competitive or superior performance compared to state-of-the-art (SOTA) IL methods and requires considerably less trainable parameters and training time. These findings urge us to revisit the IL with PLMs and encourage future studies to have a fundamental understanding of the catastrophic forgetting in PLMs. The data, code and scripts are publicly available at https://github.com/zzz47zzz/pretrained-lm-for-incremental-learning.

Abstract--Due to the increasing sophistication of web attacks, Web Application Firewalls (WAFs) have to be tested and updated regularly to resist the relentless flow of web attacks. In practice, using a brute-force attack to discover vulnerabilities is infeasible due to the wide variety of attack patterns. Thus, various black-box testing techniques have been proposed in the literature. However, these techniques suffer from low efficiency. This paper presents Reinforcement-Learning-Driven and Adaptive Testing (RAT), an automated black-box testing strategy to discover injection vulnerabilities in WAFs. In particular, we focus on SQL injection and Cross-site Scripting, which have been among the top ten vulnerabilities over the past decade. It then utilizes a reinforcement learning technique combined with a novel adaptive search algorithm to discover almost all bypassing attack patterns efficiently. We compare RAT with three state-of-the-art methods considering their objectives. The experiments show that RAT performs 33.53% and 63.16% on average better than its counterparts in discovering the most possible bypassing payloads and reducing the number of attempts before finding the first bypassing payload when testing well-configured WAFs, respectively. Thus, an enormous amount of private data of individuals and organizations is stored in web applications databases, making them tempting targets for attackers. A recent report reveals that web applications may experience up to 26 attacks per minute [1]. Moreover, according to Symantec's security report, 76% of websites are vulnerable to several attacks [2].

Knowledge-grounded dialogue is a task of generating an informative response based on both the dialogue history and external knowledge source. In general, there are two forms of knowledge: manually annotated knowledge graphs and knowledge text from website. From various evaluation viewpoints, each type of knowledge has advantages and downsides. To further distinguish the principles and determinants from the intricate factors, we conduct a thorough experiment and study on the task to answer three essential questions. The questions involve the choice of appropriate knowledge form, the degree of mutual effects between knowledge and the model selection, and the few-shot performance of knowledge. Supported by statistical shreds of evidence, we offer conclusive solutions and sensible suggestions for directions and standards of future research.

Recent works have studied implicit biases in deep learning, especially the behavior of last-layer features and classifier weights. However, they usually need to simplify the intermediate dynamics under gradient flow or gradient descent due to the intractability of loss functions and model architectures. In this paper, we introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze the closed-form dynamics while requiring as few simplifications or assumptions as possible. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization. Based on the layer-peeled model that views last-layer features as free optimization variables, we conduct a thorough analysis in the unconstrained, regularized, and spherical constrained cases, as well as the case where the neural tangent kernel remains invariant. To bridge the performance of the unhinged loss to that of Cross-Entropy (CE), we investigate the scenario of fixing classifier weights with a specific structure, (e.g., a simplex equiangular tight frame). Our analysis shows that these dynamics converge exponentially fast to a solution depending on the initialization of features and classifier weights. These theoretical results not only offer valuable insights, including explicit feature regularization and rescaled learning rates for enhancing practical training with the unhinged loss, but also extend their applicability to other loss functions. Finally, we empirically demonstrate these theoretical results and insights through extensive experiments.

Explainable AI (XAI) has unfolded in two distinct research directions with, on the one hand, post-hoc methods that explain the predictions of a pre-trained black-box model and, on the other hand, self-explainable models (SEMs) which are trained directly to provide explanations alongside their predictions. While the latter is preferred in most safety-critical scenarios, post-hoc approaches have received the majority of attention until now, owing to their simplicity and ability to explain base models without retraining. Current SEMs instead, require complex architectures and heavily regularized loss functions, thus necessitating specific and costly training. To address this shortcoming and facilitate wider use of SEMs, we propose a simple yet efficient universal method called KMEx (K-Means Explainer), which can convert any existing pre-trained model into a prototypical SEM. The motivation behind KMEx is to push towards more transparent deep learning-based decision-making via class-prototype-based explanations that are guaranteed to be diverse and trustworthy without retraining the base model. We compare models obtained from KMEx to state-of-the-art SEMs using an extensive qualitative evaluation to highlight the strengths and weaknesses of each model, further paving the way toward a more reliable and objective evaluation of SEMs.

We develop $(\epsilon,\delta)$-differentially private projection-depth-based medians using the propose-test-release (PTR) and exponential mechanisms. Under general conditions on the input parameters and the population measure, (e.g. we do not assume any moment bounds), we quantify the probability the test in PTR fails, as well as the cost of privacy via finite sample deviation bounds. We demonstrate our main result on the canonical projection-depth-based median. In the Gaussian setting, we show that the resulting deviation bound matches the known lower bound for private Gaussian mean estimation, up to a polynomial function of the condition number of the covariance matrix. In the Cauchy setting, we show that the ``outlier error amplification'' effect resulting from the heavy tails outweighs the cost of privacy. This result is then verified via numerical simulations. Additionally, we present results on general PTR mechanisms and a uniform concentration result on the projected spacings of order statistics.

The growth in Internet usage has contributed to a large volume of continuously available data, and has created the need for automatic and efficient organization of the data. In this context, text clustering techniques are significant because they aim to organize documents according to their characteristics. More specifically, hierarchical and incremental clustering techniques can organize dynamic data in a hierarchical form, thus guaranteeing that this organization is updated and its exploration is facilitated. Based on the relevance and contemporary nature of the field, this study aims to analyze various hierarchical and incremental clustering techniques; the main contribution of this research is the organization and comparison of the techniques used by studies published between 2010 and 2018 that aimed to texts documents clustering. We describe the principal concepts related to the challenge and the different characteristics of these published works in order to provide a better understanding of the research in this field.

Psychiatry research seeks to understand the manifestations of psychopathology in behavior, as measured in questionnaire data, by identifying a small number of latent factors that explain them. While factor analysis is the traditional tool for this purpose, the resulting factors may not be interpretable, and may also be subject to confounding variables. Moreover, missing data are common, and explicit imputation is often required. To overcome these limitations, we introduce interpretability constrained questionnaire factorization (ICQF), a non-negative matrix factorization method with regularization tailored for questionnaire data. Our method aims to promote factor interpretability and solution stability. We provide an optimization procedure with theoretical convergence guarantees, and an automated procedure to detect latent dimensionality accurately. We validate these procedures using realistic synthetic data. We demonstrate the effectiveness of our method in a widely used general-purpose questionnaire, in two independent datasets (the Healthy Brain Network and Adolescent Brain Cognitive Development studies). Specifically, we show that ICQF improves interpretability, as defined by domain experts, while preserving diagnostic information across a range of disorders, and outperforms competing methods for smaller dataset sizes. This suggests that the regularization in our method matches domain characteristics. The python implementation for ICQF is available at \url{https://github.com/jefferykclam/ICQF}.

This work proposes the Two-headed DragoNet, a Transformer-based model for hierarchical multi-label classification of financial transactions. Our model is based on a stack of Transformers encoder layers that generates contextual embeddings from two short textual descriptors (merchant name and business activity), followed by a Context Fusion layer and two output heads that classify transactions according to a hierarchical two-level taxonomy (macro and micro categories). Finally, our proposed Taxonomy-aware Attention Layer corrects predictions that break categorical hierarchy rules defined in the given taxonomy. Our proposal outperforms classical machine learning methods in experiments of macro-category classification by achieving an F1-score of 93% on a card dataset and 95% on a current account dataset.