Label distribution learning (LDL) trains a model to predict the relevance of a set of labels (called label distribution (LD)) to an instance. The previous LDL methods all assumed the LDs of the training instances are accurate. However, annotating highly accurate LDs for training instances is time-consuming and very expensive, and in reality the collected LD is usually inaccurate and disturbed by annotating errors. For the first time, this paper investigates the problem of inaccurate LDL, i.e., developing an LDL model with noisy LDs. We assume that the noisy LD matrix is a linear combination of an ideal LD matrix and a sparse noise matrix. Consequently, the problem of inaccurate LDL becomes an inverse problem, where the objective is to recover the ideal LD and noise matrices from the noisy LDs. We hypothesize that the ideal LD matrix is low-rank due to the correlation of labels and utilize the local geometric structure of instances captured by a graph to assist in recovering the ideal LD. This is based on the premise that similar instances are likely to share the same LD. The proposed model is finally formulated as a graph-regularized low-rank and sparse decomposition problem and numerically solved by the alternating direction method of multipliers. Furthermore, a specialized objective function is utilized to induce a LD predictive model in LDL, taking into account the recovered label distributions. Extensive experiments conducted on multiple datasets from various real-world tasks effectively demonstrate the efficacy of the proposed approach. \end{abstract}

The use of large transformer-based models such as BERT, GPT, and T5 has led to significant advancements in natural language processing. However, these models are computationally expensive, necessitating model compression techniques that reduce their size and complexity while maintaining accuracy. This project investigates and applies knowledge distillation for BERT model compression, specifically focusing on the TinyBERT student model. We explore various techniques to improve knowledge distillation, including experimentation with loss functions, transformer layer mapping methods, and tuning the weights of attention and representation loss and evaluate our proposed techniques on a selection of downstream tasks from the GLUE benchmark. The goal of this work is to improve the efficiency and effectiveness of knowledge distillation, enabling the development of more efficient and accurate models for a range of natural language processing tasks.

Kinodynamic motion planners allow robots to perform complex manipulation tasks under dynamics constraints or with black-box models. However, they struggle to find high-quality solutions, especially when a steering function is unavailable. This paper presents a novel approach that adaptively biases the sampling distribution to improve the planner's performance. The key contribution is to formulate the sampling bias problem as a non-stationary multi-armed bandit problem, where the arms of the bandit correspond to sets of possible transitions. High-reward regions are identified by clustering transitions from sequential runs of kinodynamic RRT and a bandit algorithm decides what region to sample at each timestep. The paper demonstrates the approach on several simulated examples as well as a 7-degree-of-freedom manipulation task with dynamics uncertainty, suggesting that the approach finds better solutions faster and leads to a higher success rate in execution.

Recently, more and more research has focused on using Graph Neural Networks (GNN) to solve the Graph Similarity Computation problem (GSC), i.e., computing the Graph Edit Distance (GED) between two graphs. These methods treat GSC as an end-to-end learnable task, and the core of their architecture is the feature fusion modules to interact with the features of two graphs. Existing methods consider that graph-level embedding is difficult to capture the differences in local small structures between two graphs, and thus perform fine-grained feature fusion on node-level embedding can improve the accuracy, but leads to greater time and memory consumption in the training and inference phases. However, this paper proposes a novel graph-level fusion module Different Attention (DiffAtt), and demonstrates that graph-level fusion embeddings can substantially outperform these complex node-level fusion embeddings. We posit that the relative difference structure of the two graphs plays an important role in calculating their GED values. To this end, DiffAtt uses the difference between two graph-level embeddings as an attentional mechanism to capture the graph structural difference of the two graphs. Based on DiffAtt, a new GSC method, named Graph Edit Distance Learning via Different Attention (REDRAFT), is proposed, and experimental results demonstrate that REDRAFT achieves state-of-the-art performance in 23 out of 25 metrics in five benchmark datasets. Especially on MSE, it respectively outperforms the second best by 19.9%, 48.8%, 29.1%, 31.6%, and 2.2%. Moreover, we propose a quantitative test Remaining Subgraph Alignment Test (RESAT) to verify that among all graph-level fusion modules, the fusion embedding generated by DiffAtt can best capture the structural differences between two graphs.

Data features and class probabilities are two main perspectives when, e.g., evaluating model results and identifying problematic items. Class probabilities represent the likelihood that each instance belongs to a particular class, which can be produced by probabilistic classifiers or even human labeling with uncertainty. Since both perspectives are multi-dimensional data, dimensionality reduction (DR) techniques are commonly used to extract informative characteristics from them. However, existing methods either focus solely on the data feature perspective or rely on class probability estimates to guide the DR process. In contrast to previous work where separate views are linked to conduct the analysis, we propose a novel approach, class-constrained t-SNE, that combines data features and class probabilities in the same DR result. Specifically, we combine them by balancing two corresponding components in a cost function to optimize the positions of data points and iconic representation of classes -- class landmarks. Furthermore, an interactive user-adjustable parameter balances these two components so that users can focus on the weighted perspectives of interest and also empowers a smooth visual transition between varying perspectives to preserve the mental map. We illustrate its application potential in model evaluation and visual-interactive labeling. A comparative analysis is performed to evaluate the DR results.

Recent approaches have attempted to personalize dialogue systems by leveraging profile information into models. However, this knowledge is scarce and difficult to obtain, which makes the extraction/generation of profile information from dialogues a fundamental asset. To surpass this limitation, we introduce the Profile Generation Task (PGTask). We contribute with a new dataset for this problem, comprising profile sentences aligned with related utterances, extracted from a corpus of dialogues. Furthermore, using state-of-the-art methods, we provide a benchmark for profile generation on this novel dataset. Our experiments disclose the challenges of profile generation, and we hope that this introduces a new research direction.

We investigate experiments that are designed to select a treatment arm for population deployment. Multi-armed bandit algorithms can enhance efficiency by dynamically allocating measurement effort towards higher performing arms based on observed feedback. However, such dynamics can result in brittle behavior in the face of nonstationary exogenous factors influencing arms' performance during the experiment. To counter this, we propose deconfounded Thompson sampling (DTS), a more robust variant of the prominent Thompson sampling algorithm. As observations accumulate, DTS projects the population-level performance of an arm while controlling for the context within which observed treatment decisions were made. Contexts here might capture a comprehensible source of variation, such as the country of a treated individual, or simply record the time of treatment. We provide bounds on both within-experiment and post-experiment regret of DTS, illustrating its resilience to exogenous variation and the delicate balance it strikes between exploration and exploitation. Our proofs leverage inverse propensity weights to analyze the evolution of the posterior distribution, a departure from established methods in the literature. Hinting that new understanding is indeed necessary, we show that a deconfounded variant of the popular upper confidence bound algorithm can fail completely.

We establish a framework of distributed random inverse problems over network graphs with online measurements, and propose a decentralized online learning algorithm. This unifies the distributed parameter estimation in Hilbert spaces and the least mean square problem in reproducing kernel Hilbert spaces (RKHS-LMS). We transform the convergence of the algorithm into the asymptotic stability of a class of inhomogeneous random difference equations in Hilbert spaces with L2-bounded martingale difference terms and develop the L2 -asymptotic stability theory in Hilbert spaces. It is shown that if the network graph is connected and the sequence of forward operators satisfies the infinite-dimensional spatio-temporal persistence of excitation condition, then the estimates of all nodes are mean square and almost surely strongly consistent. Moreover, we propose a decentralized online learning algorithm in RKHS based on non-stationary and non-independent online data streams, and prove that the algorithm is mean square and almost surely strongly consistent if the operators induced by the random input data satisfy the infinite-dimensional spatio-temporal persistence of excitation condition.

Efficient exploration is a challenging topic in reinforcement learning, especially for sparse reward tasks. To deal with the reward sparsity, people commonly apply intrinsic rewards to motivate agents to explore the state space efficiently. In this paper, we introduce a new intrinsic reward design called GoBI - Go Beyond Imagination, which combines the traditional lifelong novelty motivation with an episodic intrinsic reward that is designed to maximize the stepwise reachability expansion. More specifically, we apply learned world models to generate predicted future states with random actions. States with more unique predictions that are not in episodic memory are assigned high intrinsic rewards. Our method greatly outperforms previous state-of-the-art methods on 12 of the most challenging Minigrid navigation tasks and improves the sample efficiency on locomotion tasks from DeepMind Control Suite.

In Africa, and the world at large, there is an increasing focus on developing Neural Machine Translation (NMT) systems to overcome language barriers. NMT for Low-resource language is particularly compelling as it involves learning with limited labelled data. However, obtaining a well-aligned parallel corpus for low-resource languages can be challenging. The disparity between the technological advancement of a few global languages and the lack of research on NMT for local languages in Chad is striking. End-to-end NMT trials on low-resource Chad languages have not been attempted. Additionally, there is a dearth of online and well-structured data gathering for research in Natural Language Processing, unlike some African languages. However, a guided approach for data gathering can produce bitext data for many Chadian language translation pairs with well-known languages that have ample data. In this project, we created the first sba-Fr Dataset, which is a corpus of Ngambay-to-French translations, and fine-tuned three pre-trained models using this dataset. Our experiments show that the M2M100 model outperforms other models with high BLEU scores on both original and original+synthetic data. The publicly available bitext dataset can be used for research purposes.