Most deep learning research has focused on developing new model and training procedures. On the other hand the training objective has usually been restricted to combinations of standard losses. When the objective aligns well with the evaluation metric, this is not a major issue. However when dealing with complex structured outputs, the ideal objective can be hard to optimize and the efficacy of usual objectives as a proxy for the true objective can be questionable. In this work, we argue that the existing inference network based structure prediction methods ( Tu and Gimpel 2018; Tu, Pang, and Gimpel 2020) are indirectly learning to optimize a dynamic loss objective parameterized by the energy model. We then explore using implicit-gradient based technique to learn the corresponding dynamic objectives. Our experiments show that implicitly learning a dynamic loss landscape is an effective method for improving model performance in structure prediction.

Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data. There is an emerging literature on tackling this problem by minimizing the worst-case risk over an uncertainty set. However, existing methods mostly construct ambiguity sets by treating all variables equally regardless of the stability of their correlations with the target, resulting in the overwhelmingly-large uncertainty set and low confidence of the learner. In this paper, we propose a novel Stable Adversarial Learning (SAL) algorithm that leverages heterogeneous data sources to construct a more practical uncertainty set and conduct differentiated robustness optimization, where covariates are differentiated according to the stability of their correlations with the target. We theoretically show that our method is tractable for stochastic gradient-based optimization and provide the performance guarantees for our method. Empirical studies on both simulation and real datasets validate the effectiveness of our method in terms of uniformly good performance across unknown distributional shifts.

Recent works suggest that transformer models are capable of multi-tasking on diverse NLP tasks and adapting to new tasks efficiently. However, the potential of these multi-task models may be limited as they use the same set of parameters for all tasks. In contrast, humans tackle tasks in a more flexible way, by making proper presumptions on what skills and knowledge are relevant and executing only the necessary computations. Inspired by this, we propose to use task-level mixture-of-expert models, which has a collection of transformer layers (i.e., experts) and a router component that chooses from these experts dynamically and flexibly. We find that these models help improve the average performance gain (ARG) metric by 2.6% when adapting to unseen tasks in the few-shot setting and by 5.6% in the zero-shot generalization setting. Further, we show that the learned routing decisions partly rediscover human categorization of NLP tasks -- certain experts are strongly associated with extractive tasks, some with classification tasks, and some with tasks requiring world knowledge.

In natural language processing, extreme multi-label text classification is an emerging but essential task. The problem of extreme multi-label text classification (XMTC) is to recall some of the most relevant labels for a text from an extremely large label set. Large-scale pre-trained models have brought a new trend to this problem. Though the large-scale pre-trained models have made significant achievements on this problem, the valuable fine-tuned methods have yet to be studied. Though label semantics have been introduced in XMTC, the vast semantic gap between texts and labels has yet to gain enough attention. This paper builds a new guide network (GUDN) to help fine-tune the pre-trained model to instruct classification later. Furthermore, GUDN uses raw label semantics combined with a helpful label reinforcement strategy to effectively explore the latent space between texts and labels, narrowing the semantic gap, which can further improve predicted accuracy. Experimental results demonstrate that GUDN outperforms state-of-the-art methods on Eurlex-4k and has competitive results on other popular datasets. In an additional experiment, we investigated the input lengths' influence on the Transformer-based model's accuracy. Our source code is released at https://t.hk.uy/aFSH.

Graph neural networks, a powerful deep learning tool to model graph-structured data, have demonstrated remarkable performance on numerous graph learning tasks. To address the data noise and data scarcity issues in deep graph learning, the research on graph data augmentation has intensified lately. However, conventional data augmentation methods can hardly handle graph-structured data which is defined in non-Euclidean space with multi-modality. In this survey, we formally formulate the problem of graph data augmentation and further review the representative techniques and their applications in different deep graph learning problems. Specifically, we first propose a taxonomy for graph data augmentation techniques and then provide a structured review by categorizing the related work based on the augmented information modalities. Moreover, we summarize the applications of graph data augmentation in two representative problems in data-centric deep graph learning: (1) reliable graph learning which focuses on enhancing the utility of input graph as well as the model capacity via graph data augmentation; and (2) low-resource graph learning which targets on enlarging the labeled training data scale through graph data augmentation. For each problem, we also provide a hierarchical problem taxonomy and review the existing literature related to graph data augmentation. Finally, we point out promising research directions and the challenges in future research.

Careful prompt design is critical to the use of large language models in zeroshot or few-shot learning. As a consequence, there is a growing interest in automated methods to design optimal prompts. In this work, we propose TEst-tiMe Prompt Editing using Reinforcement leArning (TEMPERA). In contrast to prior prompt generation methods, TEMPERA can efficiently leverage prior knowledge, is adaptive to different queries, and provides an interpretable prompt for every query. To achieve this, we design a novel action space that allows flexible editing of the initial prompts covering a comprehensive set of commonly-used components like instructions, few-shot exemplars, and verbalizers. The proposed method achieves significant gains compared with recent SoTA approaches like prompt tuning, AutoPrompt, and RLPrompt, across a variety of tasks, including sentiment analysis, topic classification, natural language inference, and reading comprehension. Our method achieves 5.33x on average improvement in sample efficiency when compared to the traditional fine-tuning methods. With the recent advances in pre-training large language models (Brown et al., 2020; Fedus et al., 2021; Raffel et al., 2020; Chowdhery et al., 2022), prompting, or in-context learning provides a dataefficient framework for performing NLU (Li & Liang, 2021; Shin et al., 2020b; Gao et al., 2020b). Such methods achieve impressive zero-shot and few-show performance in many downstream tasks. However, the prompt often has to be carefully tuned to achieve consistent performance for each task (Lu et al., 2021). For example, prompt tuning aims to optimize a continuous prefix embedding via gradient descent and directly takes generated output from the frozen pre-trained language model (Lester et al., 2021; Liu et al., 2021b;a). On the contrary, discrete prompt optimization focuses on constructing meaningful instructions, in-context exemplars and verbalizers (Brown et al., 2020; Gao et al., 2020b). Prior work often performs black-box optimization or applies RL-based methods for direct generation (Deng et al., 2022; Sun et al., 2022; Prasad et al., 2022).

K are sparsity promoting, such as the black-box adversarial attack [4], model agnostic methods for explaining machine learning models [37] and sparse cox regression [34]. Despite the low dimensional structure restricted by r and K, standard stochastic mirror descent methods [27] and the conditional gradient methods [19] have oracle complexity depending linearly on d and are not optimal for high dimensional problems. The gradient descent algorithm is dimensionality independent when the first-order information is available [38]. For black-box objective functions, stronger dependence of the oracle complexity on dimensionality is caused by the biased gradient estimation [21]. In [50], the authors have proposed a LASSO-based gradient estimator for zerothorder optimisation of unconstrained convex objective functions.

AI is changing the landscape of education as people know it. It is predicted that in the future, most jobs will require some form of digital skills. That is why it is crucial to prepare students to live with AI and other cutting-edge technologies. AI is changing the landscape of education as people know it. It is predicted that in the future, most jobs will require some form of digital skills. That is why it is crucial to prepare students to live with AI and other cutting-edge technologies.

Introducing the Dev Library Contributor Spotlights - a blog series highlighting developers that are supporting the thriving development ecosystem by contributing their resources and tools to Google Dev Library. We met with Doug Duhaime, Full Stack Developer in Yale University's Digital Humanities Lab, to discuss his passion for Machine Learning, his processes and what inspired him to release his PixPlot project as an Open Source. I was an English major in undergrad and in graduate school. I have a PhD in English literature. To answer this question, I had to mine an enormous collection of data - half a million books, published before 1800 - to look at different patterns.

I'm super excited to announce the launch of the v2.0 Deep Reinforcement Learning Course with Hugging Face starting on December the 5th. After the first version from May to July 2022 with more than 5,000 students, we heard your feedback and we updated the course: adding more RL libraries, new environments such as Minecraft and Doom, and creating contests with our AI vs AI to compete with your trained agents against your classmates. Let's see in more detail what you're going to do. In this course, you're going to compare your agent's results with other classmates using our updated leaderboard: But the addition in this v2.0 is that for some environments you'll be able to make them play against other's classmates' AI For instance, in Snowball fight, you're going to try to beat other AIs: For now, you can sign up to our discord server to exchange with the community and with us https://discord.gg/ydHrjt3WP5 Please check our FAQ, and if you don't find answers you can contact us on our Discord Server .