Haotian Zhou, Tingkai Liu, Qianli Ma, Yufeng Zhang, Jianbo Yuan, Pengfei Liu, Yang You, Hongxia Yang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

We introduce FedCostAware, a cost-aware scheduling algorithm designed to optimize synchronous federated learning (FL) on cloud spot instances, which addresses the challenges of training on spot instances and different client budgets by employing intelligent management of the lifecycle of spot instances. This approach minimizes idle resource time and overall expenses. Experiments on real-world medical datasets demonstrate that FedCostAware significantly reduces cloud computing costs compared to conventional spot and on-demand schemes, enhancing the accessibility and affordability of FL.

Yiren Jian, Tingkai Liu, Yunzhe Tao, Chunhui Zhang, Soroush Vosoughi, Hongxia Yang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Tingkai Liu, Yunzhe Tao, Haogeng Liu, Qihang Fang, Ding Zhou, Huaibo Huang, Ran He, Hongxia Yang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Recent advances in molecular transduction of odorants in the Olfactory Sensory Neurons (OSNs) of the Drosophila Antenna have shown that the odorant object identity is multiplicatively coupled with the odorant concentration waveform. The resulting combinatorial neural code is a confounding representation of odorant semantic information (identity) and syntactic information (concentration). To distill the functional logic of odor information processing in the Antennal Lobe (AL) a number of challenges need to be addressed including 1) how is the odorant semantic information decoupled from the syntactic information at the level of the AL, 2) how are these two information streams processed by the diverse AL Local Neurons (LNs) and 3) what is the end-to-end functional logic of the AL? By analyzing single-channel physiology recordings at the output of the AL, we found that the Projection Neuron responses can be decomposed into a concentration-invariant component, and two transient components boosting the positive/negative concentration contrast that indicate onset/offset timing information of the odorant object. We hypothesized that the concentration-invariant component, in the multi-channel context, is the recovered odorant identity vector presented between onset/offset timing events. We developed a model of LN pathways in the Antennal Lobe termed the differential Divisive Normalization Processors (DNPs), which robustly extract the semantics (the identity of the odorant object) and the ON/OFF semantic timing events indicating the presence/absence of an odorant object. For real-time processing with spiking PN models, we showed that the phase-space of the biological spike generator of the PN offers an intuit perspective for the representation of recovered odorant semantics and examined the dynamics induced by the odorant semantic timing events. Finally, we provided theoretical and computational evidence for the functional logic of the AL as a robust ON-OFF odorant object identity recovery processor across odorant identities, concentration amplitudes and waveform profiles.

We developed a set of tools designed to provide rapid feedback to students as they learn to write programs in assembly language (LC-3, a RISC-like educational instruction set architecture). At the heart of the system is an extended version of KLEE, KLC3, that enables us to both identify issues and perform equivalence checking between student code and a gold (correct) version of each assignment. Feedback begins when students edit their code using a VSCode extension that leverages static analysis to perform a variety of correctness and style checks, encouraging students to improve their code quality. Each time a student commits code to their Git repository, our system triggers. Using KLC3 (KLEE), the student code is executed along with the gold version, and issues and behavioral differences are delivered back to the student through their Git repository as a human-readable report, test cases, and scripts. A queueing system allows students to monitor progress, but responses are generally available within minutes. We also extended the LC-3 simulation tools to support reverse debugging, making the process of finding complex bugs much more tractable for students, and used Emscripten to develop a browser-based interface for use in testing and debugging. Finally, our system maintains an individual regression test suite for each student and requires a submission to pass all previous tests before re-evaluation in KLC3, thus avoiding encouraging programming-by-guesswork. We deployed the system to provide feedback for the assembly programming assignments in a class of over 100 students in Fall 2020. Students wrote a median of around 700 lines of assembly for these assignments, making heavy use of our tools to understand and eliminate their bugs. Anonymous student feedback on the tools was uniformly positive. Since that semester, we have continued to refine and expand our tools’ analysis capabilities and performance, and plan to deploy the system again in the near future (the class is offered every Fall).

Despite recent advances in the understanding of olfactory signal processing [1], [2], [3], [4], [5], robust odorant sensing in complex environments with time-varying odorant identities and concentrations remains an open problem. Particularly, the operational principles of biological and biomimetic olfactory sensors define a new class of sampling problems in which the odorant identity and intensity are multiplicatively coupled into a volatile signal format. We solve the sampling problem by developing the Odorant Encoding Machine (OEM), a biomimetic system based on the latest insights in the architectural organization of the fruit fly early olfactory system. The OEM provides event-driven sensing, reconstruction and robust representation of odorant identity as a combinatorial code of multidimensional spike trains. Like its biological counterpart, OEM 1) decouples odorant identity and concentration encoding via a predictive coding circuit, 2) enables real-time responses to changing odorant input through an on-off circuit, and 3) provides robust representation of odorant identity with a real-time hashing circuit. Furthermore, the OEM is directly applicable for future in silico implementations.