Xudong Zhang

Zhilin Lu, Xudong Zhang, Rui Zeng et al.

The channel state information (CSI) needs to be fed back from the user equipment (UE) to the base station (BS) in frequency division duplexing (FDD) multiple-input multiple-output (MIMO) system. Recently, neural networks are widely applied to CSI compressed feedback since the original overhead is too large for the massive MIMO system. Notably, lightweight feedback networks attract special attention due to their practicality of deployment. However, the feedback accuracy is likely to be harmed by the network compression. In this paper, a cost free distillation technique named codeword mimic (CM) is proposed to train better feedback networks with the practical lightweight encoder. A mimic-explore training strategy with a special distillation scheduler is designed to enhance the CM learning. Experiments show that the proposed CM learning outperforms the previous state-of-the-art feedback distillation method, boosting the performance of the lightweight feedback network without any extra inference cost.

Xudong Zhang, Zan Wang, Jingke Zhao et al.

News Recommendation System(NRS) has become a fundamental technology to many online news services. Meanwhile, several studies show that recommendation systems(RS) are vulnerable to data poisoning attacks, and the attackers have the ability to mislead the system to perform as their desires. A widely studied attack approach, injecting fake users, can be applied on the NRS when the NRS is treated the same as the other systems whose items are fixed. However, in the NRS, as each item (i.e. news) is more informative, we propose a novel approach to poison the NRS, which is to perturb contents of some browsed news that results in the manipulation of the rank of the target news. Intuitively, an attack is useless if it is highly likely to be caught, i.e., exposed. To address this, we introduce a notion of the exposure risk and propose a novel problem of attacking a history news dataset by means of perturbations where the goal is to maximize the manipulation of the target news rank while keeping the risk of exposure under a given budget. We design a reinforcement learning framework, called TDP-CP, which contains a two-stage hierarchical model to reduce the searching space. Meanwhile, influence estimation is also applied to save the time on retraining the NRS for rewards. We test the performance of TDP-CP under three NRSs and on different target news. Our experiments show that TDP-CP can increase the rank of the target news successfully with a limited exposure budget.

Yunbo Qiu, Yuzhu Zhan, Yue Jin et al.

Flocking control is a significant problem in multi-agent systems such as multi-agent unmanned aerial vehicles and multi-agent autonomous underwater vehicles, which enhances the cooperativity and safety of agents. In contrast to traditional methods, multi-agent reinforcement learning (MARL) solves the problem of flocking control more flexibly. However, methods based on MARL suffer from sample inefficiency, since they require a huge number of experiences to be collected from interactions between agents and the environment. We propose a novel method Pretraining with Demonstrations for MARL (PwD-MARL), which can utilize non-expert demonstrations collected in advance with traditional methods to pretrain agents. During the process of pretraining, agents learn policies from demonstrations by MARL and behavior cloning simultaneously, and are prevented from overfitting demonstrations. By pretraining with non-expert demonstrations, PwD-MARL improves sample efficiency in the process of online MARL with a warm start. Experiments show that PwD-MARL improves sample efficiency and policy performance in the problem of flocking control, even with bad or few demonstrations.

Yunbo Qiu, Yue Jin, Jian Wang et al.

Flocking control is a challenging problem, where multiple agents, such as drones or vehicles, need to reach a target position while maintaining the flock and avoiding collisions with obstacles and collisions among agents in the environment. Multi-agent reinforcement learning has achieved promising performance in flocking control. However, methods based on traditional reinforcement learning require a considerable number of interactions between agents and the environment. This paper proposes a sub-optimal policy aided multi-agent reinforcement learning algorithm (SPA-MARL) to boost sample efficiency. SPA-MARL directly leverages a prior policy that can be manually designed or solved with a non-learning method to aid agents in learning, where the performance of the policy can be sub-optimal. SPA-MARL recognizes the difference in performance between the sub-optimal policy and itself, and then imitates the sub-optimal policy if the sub-optimal policy is better. We leverage SPA-MARL to solve the flocking control problem. A traditional control method based on artificial potential fields is used to generate a sub-optimal policy. Experiments demonstrate that SPA-MARL can speed up the training process and outperform both the MARL baseline and the used sub-optimal policy.

Yue Jin, Shuangqing Wei, Jian Yuan et al.

Learning to coordinate is a daunting problem in multi-agent reinforcement learning (MARL). Previous works have explored it from many facets, including cognition between agents, credit assignment, communication, expert demonstration, etc. However, less attention were paid to agents' decision structure and the hierarchy of coordination. In this paper, we explore the spatiotemporal structure of agents' decisions and consider the hierarchy of coordination from the perspective of multilevel emergence dynamics, based on which a novel approach, Learning to Advise and Learning from Advice (LALA), is proposed to improve MARL. Specifically, by distinguishing the hierarchy of coordination, we propose to enhance decision coordination at meso level with an advisor and leverage a policy discriminator to advise agents' learning at micro level. The advisor learns to aggregate decision information in both spatial and temporal domains and generates coordinated decisions by employing a spatiotemporal dual graph convolutional neural network with a task-oriented objective function. Each agent learns from the advice via a policy generative adversarial learning method where a discriminator distinguishes between the policies of the agent and the advisor and boosts both of them based on its judgement. Experimental results indicate the advantage of LALA over baseline approaches in terms of both learning efficiency and coordination capability. Coordination mechanism is investigated from the perspective of multilevel emergence dynamics and mutual information point of view, which provides a novel perspective and method to analyze and improve MARL algorithms.

Siqi Chen, Ke Hong, Tianchen Zhao et al.

Scaling Diffusion Transformer (DiT) inference via sequence parallelism is critical for reducing latency in visual generation, but is severely hampered by workload imbalance when applied to models employing block-wise sparse attention. The imbalance stems from the inherent variation in sparsity across attention heads and the irregular distribution of dense blocks within the sparse mask, when sequence parallelism is applied along the head dimension (as in Ulysses) or the block dimension (as in Ring Attention). In this paper, we formalize a sparse imbalance ratio to quantify the imbalance, and propose db-SP, a sparsity-aware sequence parallelism technique that tackles the challenge. db-SP contains a dual-level partitioning approach that achieves near-perfect workload balance at both the head and block levels with negligible overhead. Furthermore, to handle the evolving sparsity patterns across denoising steps and layers, db-SP dynamically determines the parallel degrees for the head and block dimensions at runtime. Experimental results demonstrate that db-SP delivers an end-to-end speedup of 1.25x and an attention-specific speedup of 1.40x over state-of-the-art sequence parallel methods on average. Code is available at https://github.com/thu-nics/db-SP.