TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition

While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have effectively addressed GPU memory constraints during fine-tuning, their performance often falls short, especially in multidimensional task scenarios. To address this issue, one straightforward solution is to introduce task-specific LoRA modules as domain experts, leveraging the modeling of multiple experts' capabilities and thus enhancing the general capability of multi-task learning. Despite promising, these additional components often add complexity to the training and inference process, contravening the efficient characterization of PEFT designed for. Considering this, we introduce an innovative PEFT method, TeamLoRA, consisting of a collaboration and competition module for experts, and thus achieving the right balance of effectiveness and efficiency: (i) For collaboration, a novel knowledge-sharing and -organizing mechanism is devised to appropriately reduce the scale of matrix operations, thereby boosting the training and inference speed. (ii) For competition, we propose leveraging a game-theoretic interaction mechanism for experts, encouraging experts to transfer their domain-specific knowledge while facing diverse downstream tasks, and thus enhancing the performance. By doing so, TeamLoRA elegantly connects the experts as a "Team" with internal collaboration and competition, enabling a faster and more accurate PEFT paradigm for multi-task learning. To validate the superiority of TeamLoRA, we curate a comprehensive multi-task evaluation(CME) benchmark to thoroughly assess the capability of multi-task learning. Experiments conducted on our CME and other benchmarks indicate the effectiveness and efficiency of TeamLoRA. Our project is available at https://github.com/Lin-Tianwei/TeamLoRA.

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?

Transformer-based trajectory optimization methods have demonstrated exceptional performance in offline Reinforcement Learning (offline RL), yet it poses challenges due to substantial parameter size and limited scalability, which is particularly critical in sequential decision-making scenarios where resources are constrained such as in robots and drones with limited computational power. Mamba, a promising new linear-time sequence model, offers performance on par with transformers while delivering substantially fewer parameters on long sequences. As it remains unclear whether Mamba is compatible with trajectory optimization, this work aims to conduct comprehensive experiments to explore the potential of Decision Mamba in offline RL (dubbed DeMa) from the aspect of data structures and network architectures with the following insights: (1) Long sequences impose a significant computational burden without contributing to performance improvements due to the fact that DeMa's focus on sequences diminishes approximately exponentially. Consequently, we introduce a Transformer-like DeMa as opposed to an RNN-like DeMa. (2) For the components of DeMa, we identify that the hidden attention mechanism is key to its success, which can also work well with other residual structures and does not require position embedding. Extensive evaluations from eight Atari games demonstrate that our specially designed DeMa is compatible with trajectory optimization and surpasses previous state-of-the-art methods, outdoing Decision Transformer (DT) by 80\% with 30\% fewer parameters, and exceeds DT in MuJoCo with only a quarter of the parameters.

SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems

Recent advances in multi-agent reinforcement learning (MARL) have opened up vast application prospects, including swarm control of drones, collaborative manipulation by robotic arms, and multi-target encirclement. However, potential security threats during the MARL deployment need more attention and thorough investigation. Recent researches reveal that an attacker can rapidly exploit the victim's vulnerabilities and generate adversarial policies, leading to the victim's failure in specific tasks. For example, reducing the winning rate of a superhuman-level Go AI to around 20%. They predominantly focus on two-player competitive environments, assuming attackers possess complete global state observation. In this study, we unveil, for the first time, the capability of attackers to generate adversarial policies even when restricted to partial observations of the victims in multi-agent competitive environments. Specifically, we propose a novel black-box attack (SUB-PLAY), which incorporates the concept of constructing multiple subgames to mitigate the impact of partial observability and suggests the sharing of transitions among subpolicies to improve the exploitative ability of attackers. Extensive evaluations demonstrate the effectiveness of SUB-PLAY under three typical partial observability limitations. Visualization results indicate that adversarial policies induce significantly different activations of the victims' policy networks. Furthermore, we evaluate three potential defenses aimed at exploring ways to mitigate security threats posed by adversarial policies, providing constructive recommendations for deploying MARL in competitive environments.

Information retrieval in single cell chromatin analysis using TF-IDF transformation methods

Single-cell sequencing assay for transposase-accessible chromatin (scATAC-seq) assesses genome-wide chromatin accessibility in thousands of cells to reveal regulatory landscapes in high resolutions. However, the analysis presents challenges due to the high dimensionality and sparsity of the data. Several methods have been developed, including transformation techniques of term-frequency inverse-document frequency (TF-IDF), dimension reduction methods such as singular value decomposition (SVD), factor analysis, and autoencoders. Yet, a comprehensive study on the mentioned methods has not been fully performed. It is not clear what is the best practice when analyzing scATAC-seq data. We compared several scenarios for transformation and dimension reduction as well as the SVD-based feature analysis to investigate potential enhancements in scATAC-seq information retrieval. Additionally, we investigate if autoencoders benefit from the TF-IDF transformation. Our results reveal that the TF-IDF transformation generally leads to improved clustering and biologically relevant feature extraction.

Reference-Aided Part-Aligned Feature Disentangling for Video Person Re-Identification

Recently, video-based person re-identification (re-ID) has drawn increasing attention in compute vision community because of its practical application prospects. Due to the inaccurate person detections and pose changes, pedestrian misalignment significantly increases the difficulty of feature extraction and matching. To address this problem, in this paper, we propose a \textbf{R}eference-\textbf{A}ided \textbf{P}art-\textbf{A}ligned (\textbf{RAPA}) framework to disentangle robust features of different parts. Firstly, in order to obtain better references between different videos, a pose-based reference feature learning module is introduced. Secondly, an effective relation-based part feature disentangling module is explored to align frames within each video. By means of using both modules, the informative parts of pedestrian in videos are well aligned and more discriminative feature representation is generated. Comprehensive experiments on three widely-used benchmarks, i.e. iLIDS-VID, PRID-2011 and MARS datasets verify the effectiveness of the proposed framework. Our code will be made publicly available.