To address this problem, we propose a training framework with certified robustness to eliminate the causes that trigger the generation of profanity.
To model the segmentation-diagnosis interaction, SeA-block first embeds the diagnosis feature based on the segmentation information via the encoder, and then transfers the embedding back to the diagnosis feature space by a decoder.
(ii) We propose a simple merging mechanism to average the weights of multiple adapter components to collapse to a single adapter in each Transformer layer, thereby, keeping the overall parameters also the same but with significant performance improvement.
In particular, for the task of automatic identification of individual Holstein-Friesians in real-world farm CCTV, we show that self-supervision, metric learning, cluster analysis, and active learning can complement each other to significantly reduce the annotation requirements usually needed to train cattle identification frameworks.
the feature maps are adopted to locate the critical features in each layer.
The first is the use of self-training to leverage large amounts of unlabeled data for prompt-based FN in few-shot settings.
Recently, a wide range of recommendation algorithms inspired by deep learning techniques have emerged as the performance leaders several standard recommendation benchmarks.
To tackle these challenges, we propose a novel casual graph based fair prediction framework, which integrates graph structure learning into fair prediction to ensure that unfair pathways are excluded in the causal graph.
In this work, we study the problem of named entity recognition (NER) in a low resource scenario, focusing on few-shot and zero-shot settings.
The experimental results show our proposed MetaFEND model can detect fake news on never-seen events effectively and outperform the state-of-the-art methods.
Through the derivation and analysis of the closed-form solutions for two basic regression and matrix factorization approaches, we found these two approaches are indeed inherently related but also diverge in how they "scale-down" the singular values of the original user-item interaction matrix.
Motivated by the labelling burden involved in constructing visual cattle identification systems, we propose exploiting the temporal coat pattern appearance across videos as a self-supervision signal for animal identity learning.
Meanwhile, we propose a post-processing framework to tune the original ensemble results through a stacking process so that we can achieve a trade off between fairness and detection performance.
The proposed approaches either are rather uninformative (linking sampling to metric evaluation) or can only work on simple metrics, such as Recall/Precision (Krichene and Rendle 2020; Li et al. 2020).
Neural sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing.
While self-training serves as an effective mechanism to learn from large amounts of unlabeled data -- meta-learning helps in adaptive sample re-weighting to mitigate error propagation from noisy pseudo-labels.
To tackle this challenging task, we propose a cross-graph representation learning framework, i. e., CrossVal, which can leverage an external KG to validate the facts in the target KG efficiently.
Holstein-Friesian cattle exhibit individually-characteristic black and white coat patterns visually akin to those arising from Turing's reaction-diffusion systems.
(1) We formalize the problem of validating the textual attribute values of products from a variety of categories as a natural language inference task in the few-shot learning setting, and propose a meta-learning latent variable model to jointly process the signals obtained from product profiles and textual attribute values.
In real-world recommendation systems, the cost of retraining recommendation models is high, and the interaction frequency between users and a recommendation system is restricted. Given these real-world restrictions, we propose to let the agent interact with a recommender simulator instead of the target recommendation system and leverage the transferability of the generated adversarial samples to poison the target system.
Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up.
In order to tackle this challenge, we propose a reinforced weakly-supervised fake news detection framework, i. e., WeFEND, which can leverage users' reports as weak supervision to enlarge the amount of training data for fake news detection.
Knowledge graph embedding (KGE) is a technique for learning continuous embeddings for entities and relations in the knowledge graph. Due to its benefit to a variety of downstream tasks such as knowledge graph completion, question answering and recommendation, KGE has gained significant attention recently.
Estimating individual treatment effect (ITE) is a challenging problem in causal inference, due to the missing counterfactuals and the selection bias.
Patients who have medical information demands tend to post questions about their health conditions on these crowdsourced Q&A websites and get answers from other users.
To better utilize sensory data, the problem of truth discovery, whose goal is to estimate user quality and infer reliable aggregated results through quality-aware data aggregation, has emerged as a hot topic.
We propose a novel approach, Adversarial Inference by Matching priors and conditionals (AIM), which explicitly matches prior and conditional distributions in both data and code spaces, and puts a direct constraint on the dependency structure of the generative model.
One of the unique challenges for fake news detection on social media is how to identify fake news on newly emerged events.
Question answering is an important and difficult task in the natural language processing domain, because many basic natural language processing tasks can be cast into a question answering task.
Existing work solves this problem by employing recurrent neural networks (RNNs) to model EHR data and utilizing simple attention mechanism to interpret the results.
We propose a novel multi-source hierarchical prediction consolidation method to effectively exploits the complicated hierarchical label structures to resolve the noisy and conflicting information that inherently originates from multiple imperfect sources.
Nonetheless, data nowadays are usually multilabeled, such that more than one label have to be predicted at the same time.
First, we can boost the diversity of classification ensemble by incorporating multiple clustering outputs, each of which provides grouping constraints for the joint label predictions of a set of related objects.