Heuristic Rank Selection with Progressively Searching Tensor Ring Network
This work addresses a specific bottleneck in tensor network compression for deep learning, offering an incremental improvement over existing methods.
The paper tackles the problem of rank selection in Tensor Ring Networks, which is crucial for performance but previously unaddressed, by proposing a progressive genetic algorithm (PSTRN) that efficiently finds optimal ranks, achieving state-of-the-art results on benchmarks like MNIST and CIFAR10/100.
Recently, Tensor Ring Networks (TRNs) have been applied in deep networks, achieving remarkable successes in compression ratio and accuracy. Although highly related to the performance of TRNs, rank selection is seldom studied in previous works and usually set to equal in experiments. Meanwhile, there is not any heuristic method to choose the rank, and an enumerating way to find appropriate rank is extremely time-consuming. Interestingly, we discover that part of the rank elements is sensitive and usually aggregate in a narrow region, namely an interest region. Therefore, based on the above phenomenon, we propose a novel progressive genetic algorithm named Progressively Searching Tensor Ring Network Search (PSTRN), which has the ability to find optimal rank precisely and efficiently. Through the evolutionary phase and progressive phase, PSTRN can converge to the interest region quickly and harvest good performance. Experimental results show that PSTRN can significantly reduce the complexity of seeking rank, compared with the enumerating method. Furthermore, our method is validated on public benchmarks like MNIST, CIFAR10/100, UCF11 and HMDB51, achieving the state-of-the-art performance.