Proceedings of the 2023 on Explainable and Safety Bounded, Fidelitous, Machine Learning for Networking
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
WelcomeIt is with great pleasure that we welcome you to the 2023 ACM CoNEXT Workshop on 'Explainable and Safety Bounded, Fidelitous, Machine Learning for Networking' -SAFE'23.We are excited to be hosting the first edition of this workshop, and it brings us pleasure to see the growing interest and enthusiasm surrounding the convergence of machine learning and networking.Machine learning offers promising solutions for network optimization, security, and management.Control and decision-making algorithms are critical for the operation of networks, hence we believe that the solutions should be safety bounded and interpretable.Understanding the decisions and behaviors of machine learning models is crucial for optimizing network performance, enhancing security, and ensuring reliable network operations.This is a very crucial topic which needs to be addressed, as network operators, managers or administrators are reluctant to use ML based solutions which are black box in nature.The production networks have a critical and sensitive nature, where outages or performance degradations can be very costly.Thus, with SAFE'23 we aim to create an engaging platform for researchers and industry experts to share their insights and experiences in this emerging field.It is a pivotal platform for fostering dialogue and collaboration among researchers, industry experts, and all those passionate about the intersection of machine learning and networking.It is here that we intend to build bridges between theory and practice, where knowledge is exchanged, and experiences are shared.Together, we can address the challenges and seize the opportunities that lie at the crossroads of machine learning and networking through Explainable and Safety Bounded, Fidelitous, Machine Learning.The call for papers attracted submissions from Asia, Canada, Europe and the United States and we accepted a total of 4 papers.We also encourage all attendees to make sure they do not miss our keynote presentation.Our distinguished keynote speaker will share invaluable insights and draw upon their extensive experience.This promises to be a highlight of the event, offering a unique opportunity to gain deep understanding and inspiration: The Quest for Safe Deep Reinforcement Learning-driven Network Slicing: Progress, Pitfalls and Potential by Yassine Hadjadj Aoul, who is currently a Full Professor at Univ Rennes/
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it