Towards Network Aware Recommendations Savvas Kastanakis - - PowerPoint PPT Presentation
Towards Network Aware Recommendations Savvas Kastanakis Postgraduate Student @ CSD UOC Supervisor: Xenofontas Dimitropoulos Advisor: Pavlos Sermpezis Agenda Motivation The concept of Joint Caching and Recommendations Simulation
Savvas Kastanakis Postgraduate Student @ CSD UOC
Supervisor: Xenofontas Dimitropoulos Advisor: Pavlos Sermpezis
Agenda
❖ Motivation ❖ The concept of Joint Caching and Recommendations ❖ Simulation Based Evaluation ❖ Real Users Evaluation ❖ Future Work
Agenda
❖ Motivation ❖ The concept of Joint Caching and Recommendations ❖ Simulation Based Evaluation ❖ Real Users Evaluation ❖ Future Work
The problem
❖ Internet mobile traffic, especially for online video services (e.g., YouTube, Netflix), increases exponentially ❖ Mobile networks struggle to atuain high QoE while serving all content requests ❖ This brings current network systems and architectures to the test
Caching: A traditional solution
❖ Win-Win (user & network) ➢ reduces access latency ➢
❖ Low Cache Hit Ratio (CHR ~= 15%) ➢ small caches ( cache size ~GB vs. catalog size ~PB) ➢ volatility in users’ preferences ➢ caching algorithms limitations (variable traffic, frequent changes of users)
5
Recommendation Systems: A modern solution
○ Help users explore the enormous content space ○ Drive content consumption (~80% in Netflix, >50% in YouTube) ○ Integrated in popular services (YouTube, Netflix, Spotify, etc.)
6
○ Recommend contents that are cached
e.g.,[ToMM’15, WoWMoM’18]
○ Cache contents that can be recommended
e.g., [Globecom’17, JSAC’18]
○ Jointly decide caching and recommendations
e.g., [INFOCOM’16]
Agenda
❖ Motivation ❖ The concept of Joint Caching and Recommendations ❖ Simulation Based Evaluation ❖ Real Users Evaluation ❖ Future Work
Caching and Recommendations: An example
8
low CHR high CHR
Caching and Recommendations: How about content similarity?
Initial Recommendations Biased Recommendations
9
CABaRet: Cache-Aware and BFS related Recommendations
initial content cached content directly related content
10
indirectly related content
Questions Raised
★ Is this approach going to improve CHR? ★ Are users going to follow your recommendations?
Agenda
❖ Motivation ❖ The concept of Joint Caching and Recommendations ❖ Simulation Based Evaluation ❖ Real Users Evaluation ❖ Future Work
Does this thing really work?
❖ Conducted a simulation-based evaluation ➢ CABaRet outperformed YouTube in terms
➢ CABaRet shows promising gains, providing an overall 10x increase in CHR
13
Yes, but... How about real users?
Agenda
❖ Motivation ❖ The concept of Joint Caching and Recommendations ❖ Simulation Based Evaluation ❖ Real Users Evaluation ❖ Future Work
CABaRet Experimental Testbed: Real world data
16
Video Player Ratings Cache Friendly Recommendations Original Recommendations
Do users follow the “biased” recommendations?
willing to select the “nudged” recommendations
○ the hit ratio, HR: this is the ratio of high-QoS (cached) videos that users selected, over the total number of viewed videos ○ the recommendation ratio, RR: this is the ratio of recommended high-QoS videos over the total number of recommended videos
Win Win Situation
★ Is this approach going to improve CHR? ★ Are users going to follow your recommendations?
Agenda
❖ Motivation ❖ The concept of Joint Caching and Recommendations ❖ Simulation Based Evaluation ❖ Real Users Evaluation ❖ Future Work
Future Work
QoE = f(QoS, Interest)
21
22
Results from real users’ ratings
Average CHR 58% Ratings (in %) Cached Contents (CABaRet Recommendations) Non Cached Contents QoS 88% 33% Interest 69% 72% QoR 68% 71% QoE 70% 42% Win for the Network/Content Provider Win for the End User