One-shot Federated Learning (OFL) significantly reduces communication costs in FL by aggregating trained models only once. However, the performance of advanced OFL methods is far behind the normal FL. In this work, we provide a causal view to find that this performance drop of OFL methods comes from the isolation problem, which means that local isolatedly trained models in OFL may easily fit to spurious correlations due to the data heterogeneity. From the causal perspective, we observe that the spurious fitting can be alleviated by augmenting intermediate features from other clients. Built upon our observation, we propose a novel learning approach to endow OFL with superb performance and low communication and storage costs, termed as FuseFL. Specifically, FuseFL decomposes neural networks into several blocks, and progressively trains and fuses each block following a bottom-up manner for feature augmentation, introducing no additional communication costs. Comprehensive experiments demonstrate that FuseFL outperforms existing OFL and ensemble FL by a significant margin. We conduct comprehensive experiments to show that FuseFL supports high scalability of clients, heterogeneous model training, and low memory costs. Our work is the first attempt using causality to analyze and alleviate data heterogeneity of OFL.

We consider a class of learning problem of point estimation for modeling high-dimensional nonlinear functions, whose learning dynamics is guided by model training dataset, while the estimated parameter in due course provides an acceptable prediction accuracy on a different model validation dataset. Here, we establish an evidential connection between such a learning problem and a hierarchical optimal control problem that provides a framework how to account appropriately for both generalization and regularization at the optimization stage. In particular, we consider the following two objectives: (i) The first one is a controllability-type problem, i.e., generalization, which consists of guaranteeing the estimated parameter to reach a certain target set at some fixed final time, where such a target set is associated with model validation dataset. (ii) The second one is a regularization-type problem ensuring the estimated parameter trajectory to satisfy some regularization property over a certain finite time interval. First, we partition the control into two control strategies that are compatible with two abstract agents, namely, a leader, which is responsible for the controllability-type problem and that of a follower, which is associated with the regularization-type problem. Using the notion of Stackelberg's optimization, we provide conditions on the existence of admissible optimal controls for such a hierarchical optimal control problem under which the follower is required to respond optimally to the strategy of the leader, so as to achieve the overall objectives that ultimately leading to an optimal parameter estimate. Moreover, we provide a nested algorithm, arranged in a hierarchical structure-based on successive approximation methods, for solving the corresponding optimal control problem. Finally, we present some numerical results for a typical nonlinear regression problem.

Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes, which is important for the reliable deployment of machine learning models in the open world. Various scoring functions are proposed to distinguish it from in-distribution (ID) data. However, existing methods generally focus on excavating the discriminative information from a single input, which implicitly limits its representation dimension. In this work, we introduce a novel perspective, i.e., employing different common corruptions on the input space, to expand that. We reveal an interesting phenomenon termed confidence mutation, where the confidence of OOD data can decrease significantly under the corruptions, while the ID data shows a higher confidence expectation considering the resistance of semantic features. Based on that, we formalize a new scoring method, namely, Confidence aVerage (CoVer), which can capture the dynamic differences by simply averaging the scores obtained from different corrupted inputs and the original ones, making the OOD and ID distributions more separable in detection tasks. Extensive experiments and analyses have been conducted to understand and verify the effectiveness of CoVer.

The attention mechanism plays an important role in the machine reading comprehension (MRC) model. Here, we describe a pipeline for building an MRC model with a pretrained language model and visualizing the effect of each attention zone in different layers, which can indicate the explainability of the model. With the presented protocol and accompanying code, researchers can easily visualize the relevance of each attention zone in the MRC model. This approach can be generalized to other pretrained language models. For complete details on the use and execution of this protocol, please refer to Cui et al. (2022).

Given the pace at which generative A.I. tools have flooded the market and the much slower rate at which school districts and universities develop new policies, it was only a matter of time before a case focused on A.I. and cheating made its way to court. That day came on Tuesday, when an attorney asked a federal judge to require Hingham High School, in Massachusetts, to raise the AP U.S. History grade of a student who had been penalized for allegedly using A.I. to research and outline a class project. The attorney for the student argued that because the school had no A.I. policy in the student handbook, using A.I. wasn't cheating--and that the low grade the student received in that course would unfairly prevent him from applying to selective colleges. Hingham school officials have argued that the use of A.I. was clearly prohibited by policies laid out in class and by existing policies against plagiarism. The case against the Hingham school system turns on the question of whether what the student did constituted cheating, according to the existing school policies: Were students allowed to use A.I. tools as these students did, or not? And is it, in fact, plagiarism to use research and an outline generated by a chatbot?

Participatory budgeting (PB) is a voting paradigm for distributing a divisible resource, usually called a budget, among a set of projects by aggregating the preferences of individuals over these projects. It is implemented quite extensively for purposes such as government allocating funds to public projects and funding agencies selecting research proposals to support. This PhD dissertation studies the welfare-related and fairness-related objectives for different PB models. Our contribution lies in proposing and exploring novel PB rules that maximize welfare and promote fairness, as well as, in introducing and investigating a range of novel utility notions, axiomatic properties, and fairness notions, effectively filling the gaps in the existing literature for each PB model. The thesis is divided into two main parts, the first focusing on dichotomous and the second focusing on ordinal preferences. Each part considers two cases: (i) the cost of each project is restricted to a single value and partial funding is not permitted and (ii) the cost of each project is flexible and may assume multiple values.

With the resurgent interest in building open-domain dialogue systems, the dialogue generation task has attracted increasing attention over the past few years. This task is usually formulated as a conditional generation problem, which aims to generate a natural and meaningful response given dialogue contexts and specific constraints, such as persona. And maintaining a consistent persona is essential for the dialogue systems to gain trust from the users. Although tremendous advancements have been brought, traditional persona-based dialogue models are typically trained by leveraging a large number of persona-dense dialogue examples. Yet, such persona-dense training data are expensive to obtain, leading to a limited scale. This work presents a novel approach to learning from limited training examples by regarding consistency understanding as a regularization of response generation. To this end, we propose a novel stack-propagation framework for learning a generation and understanding pipeline.Specifically, the framework stacks a Transformer encoder and two Transformer decoders, where the first decoder models response generation and the second serves as a regularizer and jointly models response generation and consistency understanding. The proposed framework can benefit from the stacked encoder and decoders to learn from much smaller personalized dialogue data while maintaining competitive performance. Under different low-resource settings, subjective and objective evaluations prove that the stack-propagation framework outperforms strong baselines in response quality and persona consistency and largely overcomes the shortcomings of traditional models that rely heavily on the persona-dense dialogue data.

One of the most challenging problems facing NLP today is evaluation. Some of the most pressing issues pertain to benchmark saturation, data contamination, and diversity in the quality of test examples. To address these concerns, we propose Selection Methodology for Accurate, Reduced, and Targeted (SMART) filtering, a novel approach to select a high-quality subset of examples from existing benchmark datasets by systematically removing less informative and less challenging examples. Our approach applies three filtering criteria, removing (i) easy examples, (ii) data-contaminated examples, and (iii) examples that are similar to each other based on distance in an embedding space. We demonstrate the effectiveness of SMART on three multiple choice QA datasets, where our methodology increases efficiency by reducing dataset size by 48\% on average, while increasing Pearson correlation with rankings from ChatBot Arena, a more open-ended human evaluation setting. Our method enables us to be more efficient, whether using SMART to make new benchmarks more challenging or to revitalize older datasets, while still preserving the relative model rankings.

Zero-shot in-context learning (ZS-ICL) aims to conduct in-context learning (ICL) without using human-annotated demonstrations. Most ZS-ICL methods use large language models (LLMs) to generate (input, label) pairs as pseudo-demonstrations and leverage historical pseudo-demonstrations to help solve the current problem. They assume that problems are from the same task and traverse them in a random order. However, in real-world scenarios, problems usually come from diverse tasks, and only a few belong to the same task. The random traversing order may generate unreliable pseudo-demonstrations and lead to error accumulation. To address this problem, we reformulate ZS-ICL as a planning problem and propose a Demonstration-aware Monte Carlo Tree Search (MCTS) approach (DAWN-ICL), which leverages MCTS to strategically plan the problem-solving trajectories for ZS-ICL. In addition, to achieve effective and efficient Q value estimation, we propose a novel demonstration-aware Q-value function and use it to enhance the selection phase and accelerate the expansion and simulation phases in MCTS. Extensive experiments demonstrate the effectiveness and efficiency of DAWN-ICL on in-domain and cross-domain scenarios, and it even outperforms ICL using human-annotated labels. The code is available at https://github.com/RUCAIBox/MCTS4ZSICL.

Understanding long-form video content presents significant challenges due to its temporal complexity and the substantial computational resources required. In this work, we propose an agent-based approach to enhance both the efficiency and effectiveness of long-form video understanding by utilizing large language models (LLMs) and their tool-harnessing ability. A key aspect of our method is query-adaptive frame sampling, which leverages the reasoning capabilities of LLMs to process only the most relevant frames in real-time, and addresses an important limitation of existing methods which typically involve sampling redundant or irrelevant frames. To enhance the reasoning abilities of our video-understanding agent, we leverage the self-reflective capabilities of LLMs to provide verbal reinforcement to the agent, which leads to improved performance while minimizing the number of frames accessed. We evaluate our method across several video understanding benchmarks and demonstrate that not only it enhances state-of-the-art performance but also improves efficiency by reducing the number of frames sampled.