Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning

Reinforcement Learning (RL) empowers agents to acquire various skills by learning from reward signals. Unfortunately, designing high-quality instance-level rewards often demands significant effort. An emerging alternative, RL with delayed reward, focuses on learning from rewards presented periodically, which can be obtained from human evaluators assessing the agent's performance over sequences of behaviors. However, traditional methods in this domain assume the existence of underlying Markovian rewards and that the observed delayed reward is simply the sum of instance-level rewards, both of which often do not align well with real-world scenarios. In this paper, we introduce the problem of RL from Composite Delayed Reward (RLCoDe), which generalizes traditional RL from delayed rewards by eliminating the strong assumption. We suggest that the delayed reward may arise from a more complex structure reflecting the overall contribution of the sequence. To address this problem, we present a framework for modeling composite delayed rewards, using a weighted sum of non-Markovian components to capture the different contributions of individual steps. Building on this framework, we propose Composite Delayed Reward Transformer (CoDeTr), which incorporates a specialized in-sequence attention mechanism to effectively model these contributions. We conduct experiments on challenging locomotion tasks where the agent receives delayed rewards computed from composite functions of observable step rewards. The experimental results indicate that CoDeTr consistently outperforms baseline methods across evaluated metrics. Additionally, we demonstrate that it effectively identifies the most significant time steps within the sequence and accurately predicts rewards that closely reflect the environment feedback.

Word Alignment as Preference for Machine Translation

The problem of hallucination and omission, a long-standing problem in machine translation (MT), is more pronounced when a large language model (LLM) is used in MT because an LLM itself is susceptible to these phenomena. In this work, we mitigate the problem in an LLM-based MT model by guiding it to better word alignment. We first study the correlation between word alignment and the phenomena of hallucination and omission in MT. Then we propose to utilize word alignment as preference to optimize the LLM-based MT model. The preference data are constructed by selecting chosen and rejected translations from multiple MT tools. Subsequently, direct preference optimization is used to optimize the LLM-based model towards the preference signal. Given the absence of evaluators specifically designed for hallucination and omission in MT, we further propose selecting hard instances and utilizing GPT-4 to directly evaluate the performance of the models in mitigating these issues. We verify the rationality of these designed evaluation methods by experiments, followed by extensive results demonstrating the effectiveness of word alignment-based preference optimization to mitigate hallucination and omission.

Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment

The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word representation in low-resource languages is notably under-aligned with that in high-resource languages in current models. To address this, we introduce a novel framework that explicitly aligns words between English and eight low-resource languages, utilizing off-the-shelf word alignment models. This framework incorporates three primary training objectives: aligned word prediction and word translation ranking, along with the widely used translation ranking. We evaluate our approach through experiments on the bitext retrieval task, which demonstrate substantial improvements on sentence embeddings in low-resource languages. In addition, the competitive performance of the proposed model across a broader range of tasks in high-resource languages underscores its practicality.

Generating, Reconstructing, and Representing Discrete and Continuous Data: Generalized Diffusion with Learnable Encoding-Decoding

The vast applications of deep generative models are anchored in three core capabilities -- generating new instances, reconstructing inputs, and learning compact representations -- across various data types, such as discrete text/protein sequences and continuous images. Existing model families, like Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), autoregressive models, and diffusion models, generally excel in specific capabilities and data types but fall short in others. We introduce generalized diffusion with learnable encoder-decoder (DiLED), that seamlessly integrates the core capabilities for broad applicability and enhanced performance. DiLED generalizes the Gaussian noising-denoising in standard diffusion by introducing parameterized encoding-decoding. Crucially, DiLED is compatible with the well-established diffusion model objective and training recipes, allowing effective learning of the encoder-decoder parameters jointly with diffusion. By choosing appropriate encoder/decoder (e.g., large language models), DiLED naturally applies to different data types. Extensive experiments on text, proteins, and images demonstrate DiLED's flexibility to handle diverse data and tasks and its strong improvement over various existing models.

Reinforcement Learning from Bagged Reward: A Transformer-based Approach for Instance-Level Reward Redistribution

In reinforcement Learning (RL), an instant reward signal is generated for each action of the agent, such that the agent learns to maximize the cumulative reward to obtain the optimal policy. However, in many real-world applications, the instant reward signals are not obtainable by the agent. Instead, the learner only obtains rewards at the ends of bags, where a bag is defined as a partial sequence of a complete trajectory. In this situation, the learner has to face the significant difficulty of exploring the unknown instant rewards in the bags, which could not be addressed by existing approaches, including those trajectory-based approaches that consider only complete trajectories and ignore the inner reward distributions. To formally study this situation, we introduce a novel RL setting termed Reinforcement Learning from Bagged Rewards (RLBR), where only the bagged rewards of sequences can be obtained. We provide the theoretical study to establish the connection between RLBR and standard RL in Markov Decision Processes (MDPs). To effectively explore the reward distributions within the bagged rewards, we propose a Transformer-based reward model, the Reward Bag Transformer (RBT), which uses the self-attention mechanism for interpreting the contextual nuances and temporal dependencies within each bag. Extensive experimental analyses demonstrate the superiority of our method, particularly in its ability to mimic the original MDP's reward distribution, highlighting its proficiency in contextual understanding and adaptability to environmental dynamics.

TLMCM Network for Medical Image Hierarchical Multi-Label Classification

Medical Image Hierarchical Multi-Label Classification (MI-HMC) is of paramount importance in modern healthcare, presenting two significant challenges: data imbalance and \textit{hierarchy constraint}. Existing solutions involve complex model architecture design or domain-specific preprocessing, demanding considerable expertise or effort in implementation. To address these limitations, this paper proposes Transfer Learning with Maximum Constraint Module (TLMCM) network for the MI-HMC task. The TLMCM network offers a novel approach to overcome the aforementioned challenges, outperforming existing methods based on the Area Under the Average Precision and Recall Curve($AU\overline{(PRC)}$) metric. In addition, this research proposes two novel accuracy metrics, $EMR$ and $HammingAccuracy$, which have not been extensively explored in the context of the MI-HMC task. Experimental results demonstrate that the TLMCM network achieves high multi-label prediction accuracy($80\%$-$90\%$) for MI-HMC tasks, making it a valuable contribution to healthcare domain applications.

Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association

Reporting bias arises when people assume that some knowledge is universally understood and hence, do not necessitate explicit elaboration. In this paper, we focus on the wide existence of reporting bias in visual-language datasets, embodied as the object-attribute association, which can subsequentially degrade models trained on them. To mitigate this bias, we propose a bimodal augmentation (BiAug) approach through object-attribute decoupling to flexibly synthesize visual-language examples with a rich array of object-attribute pairing and construct cross-modal hard negatives. We employ large language models (LLMs) in conjunction with a grounding object detector to extract target objects. Subsequently, the LLM generates a detailed attribute description for each object and produces a corresponding hard negative counterpart. An inpainting model is then used to create images based on these detailed object descriptions. By doing so, the synthesized examples explicitly complement omitted objects and attributes to learn, and the hard negative pairs steer the model to distinguish object attributes. Our experiments demonstrated that BiAug is superior in object-attribute understanding. In addition, BiAug also improves the performance on zero-shot retrieval tasks on general benchmarks like MSCOCO and Flickr30K. BiAug refines the way of collecting text-image datasets. Mitigating the reporting bias helps models achieve a deeper understanding of visual-language phenomena, expanding beyond mere frequent patterns to encompass the richness and diversity of real-world scenarios.

Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding

Learning multi-lingual sentence embeddings is a fundamental and significant task in natural language processing. Recent trends of learning both mono-lingual and multi-lingual sentence embeddings are mainly based on contrastive learning (CL) with an anchor, one positive, and multiple negative instances. In this work, we argue that leveraging multiple positives should be considered for multi-lingual sentence embeddings because (1) positives in a diverse set of languages can benefit cross-lingual learning, and (2) transitive similarity across multiple positives can provide reliable structural information to learn. In order to investigate the impact of CL with multiple positives, we propose a novel approach MPCL to effectively utilize multiple positive instances to improve learning multi-lingual sentence embeddings. Our experimental results on various backbone models and downstream tasks support that compared with conventional CL, MPCL leads to better retrieval, semantic similarity, and classification performances. We also observe that on unseen languages, sentence embedding models trained on multiple positives have better cross-lingual transferring performance than models trained on a single positive instance.

WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction

Most existing word alignment methods rely on manual alignment datasets or parallel corpora, which limits their usefulness. Here, to mitigate the dependence on manual data, we broaden the source of supervision by relaxing the requirement for correct, fully-aligned, and parallel sentences. Specifically, we make noisy, partially aligned, and non-parallel paragraphs. We then use such a large-scale weakly-supervised dataset for word alignment pre-training via span prediction. Extensive experiments with various settings empirically demonstrate that our approach, which is named WSPAlign, is an effective and scalable way to pre-train word aligners without manual data. When fine-tuned on standard benchmarks, WSPAlign has set a new state-of-the-art by improving upon the best-supervised baseline by 3.3~6.1 points in F1 and 1.5~6.1 points in AER. Furthermore, WSPAlign also achieves competitive performance compared with the corresponding baselines in few-shot, zero-shot and cross-lingual tests, which demonstrates that WSPAlign is potentially more practical for low-resource languages than existing methods.

A Deep Learning Approach to Predicting Ventilator Parameters for Mechanically Ventilated Septic Patients

We develop a deep learning approach to predicting a set of ventilator parameters for a mechanically ventilated septic patient using a long and short term memory (LSTM) recurrent neural network (RNN) model. We focus on short-term predictions of a set of ventilator parameters for the septic patient in emergency intensive care unit (EICU). The short-term predictability of the model provides attending physicians with early warnings to make timely adjustment to the treatment of the patient in the EICU. The patient specific deep learning model can be trained on any given critically ill patient, making it an intelligent aide for physicians to use in emergent medical situations.