Masked Modeling for Self-supervised Representation Learning on Vision and Beyond

As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data. Among these varied self-supervised techniques, masked modeling has emerged as a distinctive approach that involves predicting parts of the original data that are proportionally masked during training. This paradigm enables deep models to learn robust representations and has demonstrated exceptional performance in the context of computer vision, natural language processing, and other modalities. In this survey, we present a comprehensive review of the masked modeling framework and its methodology. We elaborate on the details of techniques within masked modeling, including diverse masking strategies, recovering targets, network architectures, and more. Then, we systematically investigate its wide-ranging applications across domains. Furthermore, we also explore the commonalities and differences between masked modeling methods in different fields. Toward the end of this paper, we conclude by discussing the limitations of current techniques and point out several potential avenues for advancing masked modeling research. A paper list project with this survey is available at \url{https://github.com/Lupin1998/Awesome-MIM}.

MMDesign: Multi-Modality Transfer Learning for Generative Protein Design

Protein design involves generating protein sequences based on their corresponding protein backbones. While deep generative models show promise for learning protein design directly from data, the lack of publicly available structure-sequence pairings limits their generalization capabilities. Previous efforts of generative protein design have focused on architectural improvements and pseudo-data augmentation to overcome this bottleneck. To further address this challenge, we propose a novel protein design paradigm called MMDesign, which leverages multi-modality transfer learning. To our knowledge, MMDesign is the first framework that combines a pretrained structural module with a pretrained contextual module, using an auto-encoder (AE) based language model to incorporate prior semantic knowledge of protein sequences. We also introduce a cross-layer cross-modal alignment algorithm to enable the structural module to learn long-term temporal information and ensure consistency between structural and contextual modalities. Experimental results, only training with the small CATH dataset, demonstrate that our MMDesign framework consistently outperforms other baselines on various public test sets. To further assess the biological plausibility of the generated protein sequences and data distribution, we present systematic quantitative analysis techniques that provide interpretability and reveal more about the laws of protein design.

Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training

Multimodal reasoning is a challenging task that requires models to reason across multiple modalities to answer questions. Existing approaches have made progress by incorporating language and visual modalities into a two-stage reasoning framework, separating rationale generation from answer inference. However, these approaches often fall short due to the inadequate quality of the generated rationales. In this work, we delve into the importance of rationales in model reasoning. We observe that when rationales are completely accurate, the model's accuracy significantly improves, highlighting the need for high-quality rationale generation. Motivated by this, we propose MC-CoT, a self-consistency training strategy that generates multiple rationales and answers, subsequently selecting the most accurate through a voting process. This approach not only enhances the quality of generated rationales but also leads to more accurate and robust answers. Through extensive experiments, we demonstrate that our approach significantly improves model performance across various benchmarks. Remarkably, we show that even smaller base models, when equipped with our proposed approach, can achieve results comparable to those of larger models, illustrating the potential of our approach in harnessing the power of rationales for improved multimodal reasoning. The code is available at https://github.com/chengtan9907/mc-cot.

Robust Visual Imitation Learning with Inverse Dynamics Representations

Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems. However, current IL methods mainly assume that the environment for learning policies is the same as the environment for collecting expert datasets. Therefore, these methods may fail to work when there are slight differences between the learning and expert environments, especially for challenging problems with high-dimensional image observations. However, in real-world scenarios, it is rare to have the chance to collect expert trajectories precisely in the target learning environment. To address this challenge, we propose a novel robust imitation learning approach, where we develop an inverse dynamics state representation learning objective to align the expert environment and the learning environment. With the abstract state representation, we design an effective reward function, which thoroughly measures the similarity between behavior data and expert data not only element-wise, but also from the trajectory level. We conduct extensive experiments to evaluate the proposed approach under various visual perturbations and in diverse visual control tasks. Our approach can achieve a near-expert performance in most environments, and significantly outperforms the state-of-the-art visual IL methods and robust IL methods.

Protein 3D Graph Structure Learning for Robust Structure-based Protein Property Prediction

Protein structure-based property prediction has emerged as a promising approach for various biological tasks, such as protein function prediction and sub-cellular location estimation. The existing methods highly rely on experimental protein structure data and fail in scenarios where these data are unavailable. Predicted protein structures from AI tools (e.g., AlphaFold2) were utilized as alternatives. However, we observed that current practices, which simply employ accurately predicted structures during inference, suffer from notable degradation in prediction accuracy. While similar phenomena have been extensively studied in general fields (e.g., Computer Vision) as model robustness, their impact on protein property prediction remains unexplored. In this paper, we first investigate the reason behind the performance decrease when utilizing predicted structures, attributing it to the structure embedding bias from the perspective of structure representation learning. To study this problem, we identify a Protein 3D Graph Structure Learning Problem for Robust Protein Property Prediction (PGSL-RP3), collect benchmark datasets, and present a protein Structure embedding Alignment Optimization framework (SAO) to mitigate the problem of structure embedding bias between the predicted and experimental protein structures. Extensive experiments have shown that our framework is model-agnostic and effective in improving the property prediction of both predicted structures and experimental structures. The benchmark datasets and codes will be released to benefit the community.

Revisiting the Temporal Modeling in Spatio-Temporal Predictive Learning under A Unified View

Spatio-temporal predictive learning plays a crucial role in self-supervised learning, with wide-ranging applications across a diverse range of fields. Previous approaches for temporal modeling fall into two categories: recurrent-based and recurrent-free methods. The former, while meticulously processing frames one by one, neglect short-term spatio-temporal information redundancies, leading to inefficiencies. The latter naively stack frames sequentially, overlooking the inherent temporal dependencies. In this paper, we re-examine the two dominant temporal modeling approaches within the realm of spatio-temporal predictive learning, offering a unified perspective. Building upon this analysis, we introduce USTEP (Unified Spatio-TEmporal Predictive learning), an innovative framework that reconciles the recurrent-based and recurrent-free methods by integrating both micro-temporal and macro-temporal scales. Extensive experiments on a wide range of spatio-temporal predictive learning demonstrate that USTEP achieves significant improvements over existing temporal modeling approaches, thereby establishing it as a robust solution for a wide range of spatio-temporal applications.

Rethinking Memory and Communication Cost for Efficient Large Language Model Training

As model sizes and training datasets continue to increase, large-scale model training frameworks reduce memory consumption by various sharding techniques. However, the huge communication overhead reduces the training efficiency, especially in public cloud environments with varying network bandwidths. In this paper, we rethink the impact of memory consumption and communication overhead on the training speed of large language model, and propose a memory-communication balanced \underline{Pa}rtial \underline{R}edundancy \underline{O}ptimizer (PaRO). PaRO reduces the amount and frequency of inter-group communication by grouping GPU clusters and introducing minor intra-group memory redundancy, thereby improving the training efficiency of the model. Additionally, we propose a Hierarchical Overlapping Ring (HO-Ring) communication topology to enhance communication efficiency between nodes or across switches in large model training. Our experiments demonstrate that the HO-Ring algorithm improves communication efficiency by 32.6\% compared to the traditional Ring algorithm. Compared to the baseline ZeRO, PaRO significantly improves training throughput by 1.2x-2.6x and achieves a near-linear scalability. Therefore, the PaRO strategy provides more fine-grained options for the trade-off between memory consumption and communication overhead in different training scenarios.

SemiReward: A General Reward Model for Semi-supervised Learning

Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias. However, existing pseudo-label selection strategies are limited to pre-defined schemes or complex hand-crafted policies specially designed for classification, failing to achieve high-quality labels, fast convergence, and task versatility simultaneously. To these ends, we propose a Semi-supervised Reward framework (SemiReward) that predicts reward scores to evaluate and filter out high-quality pseudo labels, which is pluggable to mainstream SSL methods in wide task types and scenarios. To mitigate confirmation bias, SemiReward is trained online in two stages with a generator model and subsampling strategy. With classification and regression tasks on 13 standard SSL benchmarks of three modalities, extensive experiments verify that SemiReward achieves significant performance gains and faster convergence speeds upon Pseudo Label, FlexMatch, and Free/SoftMatch.

IMM: An Imitative Reinforcement Learning Approach with Predictive Representation Learning for Automatic Market Making

Market making (MM) has attracted significant attention in financial trading owing to its essential function in ensuring market liquidity. With strong capabilities in sequential decision-making, Reinforcement Learning (RL) technology has achieved remarkable success in quantitative trading. Nonetheless, most existing RL-based MM methods focus on optimizing single-price level strategies which fail at frequent order cancellations and loss of queue priority. Strategies involving multiple price levels align better with actual trading scenarios. However, given the complexity that multi-price level strategies involves a comprehensive trading action space, the challenge of effectively training profitable RL agents for MM persists. Inspired by the efficient workflow of professional human market makers, we propose Imitative Market Maker (IMM), a novel RL framework leveraging both knowledge from suboptimal signal-based experts and direct policy interactions to develop multi-price level MM strategies efficiently. The framework start with introducing effective state and action representations adept at encoding information about multi-price level orders. Furthermore, IMM integrates a representation learning unit capable of capturing both short- and long-term market trends to mitigate adverse selection risk. Subsequently, IMM formulates an expert strategy based on signals and trains the agent through the integration of RL and imitation learning techniques, leading to efficient learning. Extensive experimental results on four real-world market datasets demonstrate that IMM outperforms current RL-based market making strategies in terms of several financial criteria. The findings of the ablation study substantiate the effectiveness of the model components.

IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse

Humans have the ability to reuse previously learned policies to solve new tasks quickly, and reinforcement learning (RL) agents can do the same by transferring knowledge from source policies to a related target task. Transfer RL methods can reshape the policy optimization objective (optimization transfer) or influence the behavior policy (behavior transfer) using source policies. However, selecting the appropriate source policy with limited samples to guide target policy learning has been a challenge. Previous methods introduce additional components, such as hierarchical policies or estimations of source policies' value functions, which can lead to non-stationary policy optimization or heavy sampling costs, diminishing transfer effectiveness. To address this challenge, we propose a novel transfer RL method that selects the source policy without training extra components. Our method utilizes the Q function in the actor-critic framework to guide policy selection, choosing the source policy with the largest one-step improvement over the current target policy. We integrate optimization transfer and behavior transfer (IOB) by regularizing the learned policy to mimic the guidance policy and combining them as the behavior policy. This integration significantly enhances transfer effectiveness, surpasses state-of-the-art transfer RL baselines in benchmark tasks, and improves final performance and knowledge transferability in continual learning scenarios. Additionally, we show that our optimization transfer technique is guaranteed to improve target policy learning.