Search

Deep neural networks have been proven to be vulnerable to adversarial examples and various methods have been proposed to defend against adversarial attacks for natural language processing tasks. However, previous defense methods have limitations in maintaining effective defense while ensuring the performance of the original task. In this paper, we propose a malicious perturbation based adversarial training method (MPAT) for building robust deep neural networks against textual adversarial attacks. Specifically, we construct a multi-level malicious example generation strategy to generate adversarial examples with malicious perturbations, which are used instead of original inputs for model training. Additionally, we employ a novel training objective function to ensure achieving the defense goal without compromising the performance on the original task. We conduct comprehensive experiments to evaluate our defense method by attacking five victim models on three benchmark datasets. The result demonstrates that our method is more effective against malicious adversarial attacks compared with previous defense methods while maintaining or further improving the performance on the original task.

Numerous statistical methods have been developed to explore genomic imprinting and maternal effects, which are causes of parent-of-origin patterns in complex human diseases. Most of the methods, however, either only model one of these two confounded epigenetic effects, or make strong yet unrealistic assumptions about the population to avoid over-parameterization. A recent partial likelihood method (LIMEDSP ) can identify both epigenetic effects based on discordant sibpair family data without those assumptions. Theoretical and empirical studies have shown its validity and robustness. As LIMEDSP method obtains parameter estimation by maximizing partial likelihood, it is interesting to compare its efficiency with full likelihood maximizer. To overcome the difficulty in over-parameterization when using full likelihood, this study proposes a discordant sib-pair design based Monte Carlo Expectation Maximization (MCEMDSP ) method to detect imprinting and maternal effects jointly. Those unknown mating type probabilities, the nuisance parameters, are considered as latent variables in EM algorithm. Monte Carlo samples are used to numerically approximate the expectation function that cannot be solved algebraically. Our simulation results show that though this MCEMDSP algorithm takes longer computation time, it can generally detect both epigenetic effects with higher power, which demonstrates that it can be a good complement of LIMEDSP method

Numerous statistical methods have been developed to explore genomic imprinting and maternal effects, which are causes of parent-of-origin patterns in complex human diseases. However, most of them either only model one of these two confounded epigenetic effects, or make strong yet unrealistic assumptions about the population to avoid over-parameterization. A recent partial likelihood method (LIME) can identify both epigenetic effects based on case-control family data without those assumptions. Theoretical and empirical studies have shown its validity and robustness. However, because LIME obtains parameter estimation by maximizing partial likelihood, it is interesting to compare its efficiency with full likelihood maximizer. To overcome the difficulty in over-parameterization when using full likelihood, in this study we propose a Monte Carlo Expectation Maximization (MCEM) method to detect imprinting and maternal effects jointly. Those unknown mating type probabilities, the nuisance parameters, can be considered as latent variables in EM algorithm. Monte Carlo samples are used to numerically approximate the expectation function that cannot be solved algebraically. Our simulation results show that though this MCEM algorithm takes longer computational time, and can give higher bias in some simulations compared to LIME, it can generally detect both epigenetic effects with higher power and smaller standard error which demonstrates that it can be a good complement of LIME method.

Due to the remarkable capabilities of powerful Large Language Models (LLMs) in effectively following instructions, there has been a growing number of assistants in the community to assist humans. Recently, significant progress has been made in the development of Vision Language Models (VLMs), expanding the capabilities of LLMs and enabling them to execute more diverse instructions. However, it is foreseeable that models will likely need to handle tasks involving additional modalities such as speech, video, and others. This poses a particularly prominent challenge of dealing with the complexity of mixed modalities. To address this, we introduce a novel architecture called PILL: Plug Into LLM with adapter expert and attention gate to better decouple these complex modalities and leverage efficient fine-tuning. We introduce two modules: Firstly, utilizing Mixture-of-Modality-Adapter-Expert to independently handle different modalities, enabling better adaptation to downstream tasks while preserving the expressive capability of the original model. Secondly, by introducing Modality-Attention-Gating, which enables adaptive control of the contribution of modality tokens to the overall representation. In addition, we have made improvements to the Adapter to enhance its learning and expressive capabilities. Experimental results demonstrate that our approach exhibits competitive performance compared to other mainstream methods for modality fusion. For researchers interested in our work, we provide free access to the code and models at https://github.com/DsaltYfish/PILL.

Blind super-resolution (BSR) methods based on high-resolution (HR) reconstruction codebooks have achieved promising results in recent years. However, we find that a codebook based on HR reconstruction may not effectively capture the complex correlations between low-resolution (LR) and HR images. In detail, multiple HR images may produce similar LR versions due to complex blind degradations, causing the HR-dependent only codebooks having limited texture diversity when faced with confusing LR inputs. To alleviate this problem, we propose the Rich Texture-aware Codebook-based Network (RTCNet), which consists of the Degradation-robust Texture Prior Module (DTPM) and the Patch-aware Texture Prior Module (PTPM). DTPM effectively mines the cross-resolution correlation of textures between LR and HR images by exploiting the cross-resolution correspondence of textures. PTPM uses patch-wise semantic pre-training to correct the misperception of texture similarity in the high-level semantic regularization. By taking advantage of this, RTCNet effectively gets rid of the misalignment of confusing textures between HR and LR in the BSR scenarios. Experiments show that RTCNet outperforms state-of-the-art methods on various benchmarks by up to 0.16 ~ 0.46dB.

Reliable pseudo-labels from unlabeled data play a key role in semi-supervised object detection (SSOD). However, the state-of-the-art SSOD methods all rely on pseudo-labels with high confidence, which ignore valuable pseudo-labels with lower confidence. Additionally, the insufficient excavation for unlabeled data results in an excessively low recall rate thus hurting the network training. In this paper, we propose a novel Low-confidence Samples Mining (LSM) method to utilize low-confidence pseudo-labels efficiently. Specifically, we develop an additional pseudo information mining (PIM) branch on account of low-resolution feature maps to extract reliable large-area instances, the IoUs of which are higher than small-area ones. Owing to the complementary predictions between PIM and the main branch, we further design self-distillation (SD) to compensate for both in a mutually-learning manner. Meanwhile, the extensibility of the above approaches enables our LSM to apply to Faster-RCNN and Deformable-DETR respectively. On the MS-COCO benchmark, our method achieves 3.54% mAP improvement over state-of-the-art methods under 5% labeling ratios.

{\em Personalized PageRank (PPR)} stands as a fundamental proximity measure in graph mining. Since computing an exact SSPPR query answer is prohibitive, most existing solutions turn to approximate queries with guarantees. The state-of-the-art solutions for approximate SSPPR queries are index-based and mainly focus on static graphs, while real-world graphs are usually dynamically changing. However, existing index-update schemes can not achieve a sub-linear update time. Motivated by this, we present an efficient indexing scheme to maintain indexed random walks in expected $O(1)$ time after each graph update. To reduce the space consumption, we further propose a new sampling scheme to remove the auxiliary data structure for vertices while still supporting $O(1)$ index update cost on evolving graphs. Extensive experiments show that our update scheme achieves orders of magnitude speed-up on update performance over existing index-based dynamic schemes without sacrificing the query efficiency.

This study delves into semi-supervised object detection (SSOD) to improve detector performance with additional unlabeled data. State-of-the-art SSOD performance has been achieved recently by self-training, in which training supervision consists of ground truths and pseudo-labels. In current studies, we observe that class imbalance in SSOD severely impedes the effectiveness of self-training. To address the class imbalance, we propose adaptive class-rebalancing self-training (ACRST) with a novel memory module called CropBank. ACRST adaptively rebalances the training data with foreground instances extracted from the CropBank, thereby alleviating the class imbalance. Owing to the high complexity of detection tasks, we observe that both self-training and data-rebalancing suffer from noisy pseudo-labels in SSOD. Therefore, we propose a novel two-stage filtering algorithm to generate accurate pseudo-labels. Our method achieves satisfactory improvements on MS-COCO and VOC benchmarks. When using only 1\% labeled data in MS-COCO, our method achieves 17.02 mAP improvement over supervised baselines, and 5.32 mAP improvement compared with state-of-the-art methods.

We study a fully funded, collective defined-contribution (DC) pension system with multiple overlapping generations. We investigate whether the welfare of participants can be improved by intergenerational risk sharing (IRS) implemented with a realistic investment strategy (e.g., no borrowing) and without an outside entity (e.g., share holders) that helps finance the pension fund. To implement IRS, the pension system uses an automatic adjustment rule for the indexation of individual accounts, which adapts to the notional funding ratio of the pension system. The pension system has two parameters that determine the investment strategy and the strength of the adjustment rule, which are optimized by expected utility maximization using Bayesian optimization. The volatility of the retirement benefits and that of the funding ratio are analyzed, and it is shown that the trade-off between them can be controlled by the optimal adjustment parameter to attain IRS. Compared with the optimal individual DC benchmark using the life-cycle strategy, the studied pension system with IRS is shown to improve the welfare of risk-averse participants, when the financial market is volatile.

We study a non-concave optimization problem in which a financial company maximizes the expected utility of the surplus under a risk-based regulatory constraint. For this problem, we consider four different prevalent risk constraints (Expected Shortfall, Expected Discounted Shortfall, Value-at-Risk, and Average Value-at-Risk), and investigate their effects on the optimal solution. Our main contributions are in obtaining an analytical solution under each of the four risk constraints, in the form of the optimal terminal wealth. We show that the four risk constraints lead to the same optimal solution, which differs from previous conclusions obtained from the corresponding concave optimization problem under a risk constraint. Compared with the benchmark (unconstrained) non-concave utility maximization problem, all four risk constraints effectively and equivalently reduce the set of zero terminal wealth, but do not fully eliminate this set, indicating the success and failure of the respective financial regulations.